New Publications are available for Optical, image and video signal processing
http://dl-live.theiet.org
New Publications are available now online for this publication.
Please follow the links to view the publication.Fractional derivative filter for image contrast enhancement with order prediction
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0432
Fractional derivative based techniques have been proposed for preprocessing of digital images. Although these techniques address the texture enhancement and other issues to a certain extent, none of them have proposed a method of determining the fractional order adaptively. In this paper, we propose a Grunwald-Letnikov derivative based fractional derivative mask for image contrast enhancement. The proposed mask is multidirectional thus enhancing the image in several directions in one pass. The regularisation based prediction network learns from the training set of images and determines the fractional order based on the statistics of the image at hand. Also the blur reduction is achieved in a controlled fashion as the fractional order is predicted according to the desired blur improvement. Experimental results with the comparative blur metric show the effectiveness of the proposed novel filter on a wide range of images. (6 pages)Epidural needle length measurement by video processing
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0446
This paper presents a novel image processing algorithm to measure the length and depth of an epidural needle during insertion. A wireless camera is used which transmits video during insertion to a host computer. The computer contains the image processing algorithm to detect the visible needle in the image and measures the length. The measurement is done by HSV background removal, colour comparison and using RGB histograms to locate 10mm markings on the Tuohy needle shaft. The visible length is then subtracted from the known length of the needle to calculate the depth of the needle tip. The camera can be placed in the operating theatre up to one meter away from the needle insertion site. The purpose of measuring needle depth in real time is to precisely place the needle in the epidural space. (6 pages)An improved enhancement of degraded binary text document images using morphological and single scale retinex operations
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0420
This paper proposes a novel enhancement algorithm for degraded binary document images captured using a low end cell phone camera. The algorithm starts with colour to grey scale conversion followed by contrast stretching. Then single scale retinex enhancement is performed to increase the contrast, reduce global variance and improve the background uniformity of the image. Otsu's binarisation method is then used to dichotomize the image and finally, morphological dilation is performed to preserve stroke connectivity of the document characters by bridging any gaps resulting from the thresholding process. Computer simulation experiments have been used to demonstrate the effectiveness of the proposed algorithm. The results show a significant improvement over the Otsu's method in terms shadow removal, document legibility and optical character recognition. The results also compare well with the state of the art Sauvola's method results. (6 pages)Stereoscopic 3D visual attention model considering comfortable viewing
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0445
Stereoscopic 3D images have depth perception as one of characteristics differ from conventional 2D images. Therefore, the conventional 2D oriented visual attention model cannot be directly applied to stereoscopic 3D images. In addition, visual fatigue is considered as another 3D related characteristics when viewing stereoscopic 3D images. In this paper, we propose a novel 3D visual attention model that combines bottom-up and top-down methods which considers comfortable viewing. The proposed model is based on 2D oriented features extracted from the image: intensity, colour, local orientation information, and the detection of human representation. Then, this model is combined with depth information obtained by considering the comfortable viewing. The experimental results show that the proposed model increase the simulation efficiency of visual characteristics of human visual system. (5 pages)Person tracking via audio and video fusion
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0410
In this paper we present a joint audio-video (AV) tracker which can track the active source between two freely moving persons speaking in turn to simulate a meeting scenario, but less constrained. Our tracker differs from existing work in that it requires only a small number of sensors, works when speaker is not close to the sensors and relies on simple, yet efficient, inference techniques in AV processing. The system uses audio and video measures of the target position on the ground plane to strengthen the single modality predictions that would be weak if taken on their own as occlusions, clutter, reverberations and speech pauses happen in the test environment. In particular, the inter-microphone signal delays and the target image locations are input to single modality Bayesian filters, whose proposed likelihoods are multiplied in a Kalman Filter to give the joint AV final estimation. Despite the low complexity of the system, results show that the multi-modal tracker does not fail, tolerating video occlusion and intermittent speech (within 50 cm of accuracy) in the context of a non-meeting scenario. The system evaluation is done both on single modality than multi-modality tracking, and the performance improvement given by the AV fusion is discussed and quantified i.e 24 % improvement on the audio tracker accuracy. (6 pages)Mass detection in digital mammograms using gabor filter bank
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0465
Digital Mammograms are currently the most effective imaging modality for early detection of breast cancer but the number of false negatives and false positives is high. Mass is one type of breast lesion and the detection of masses is highly challenged problem. Almost all methods that have been proposed so far suffer from high number of false positives and false negatives. In this paper, a method for detecting true masses is presented, especially, for the reduction of false positives and false negatives. The key idea of the proposal is the use of Gabor filter banks for extracting the most representative and discriminative local spatial textural properties of masses that are present in mammograms at different orientations and scales. The system is evaluated on 512 (256 normal+256 true mass) regions of interests (ROIs) extracted from digital mammograms of DDSM database. We performed experiments with Gabor filter banks having different numbers of orientations and scales to find the best parameter setting. Using a powerful feature selection technique and support vector machines (SVM) with 10-fold cross validation, we report to achieve Az = 0.995±0.011, the area under ROC. Comparison with state-of-the-art techniques suggests that the proposed system outperforms similar methods, which are based on texture description, and the difference is statistically significant. (6 pages)Performance of bearing-only ESM-radar track association
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0409
The bearing-only association of tracks from dissimilar sensors is considered, in particular the association of radar and electronic support measures (ESM) tracks. An approach to characterising performance is suggested, namely the curve representing the relationship between the median time to reach a correct association decision and the mean number of incorrect associations, as the association threshold is varied. Results are presented for artificially generated tracks, showing the variation of performance with track density and accuracy. Results are also given for the association of real radar tracks of ships with simulated ESM tracks. In particular, it is concluded that the ability to attach identity information from ESM to long-range radar tracks will be significantly improved if the ESM bearing errors are reduced, for example from a magnitude of order 50° to 10°. (6 pages)Semi automated segmentation of chromosomes in metaphase cells
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0463
Image segmentation plays a crucial role in many medical imaging applications by automating or facilitating the delineation of anatomical structures and other regions of interest. Since the birth of the automated karyotyping systems by the aid of computers, building a fully automated chromosome analysis system has been an ultimate goal. Along with many other challenges, accurate segmentation of the chromosomes has been a major challenge especially due to the non rigid nature of the chromosomes. The earlier reported approaches for the segmentation have limited success as they are sensitive to scale variation, experimented only on gray images, unable to segment the clusters and the highly bent chromosomes. This work, describes an effective approach of segmentation of chromosomes in Metaphase images using Random Walker Algorithm [RWA] which is yet unexplored and not reported in the literature. The efforts are also done to compare the results with traditional methods so as to prove the efficiency of the implemented RWA algorithm. The algorithm is tested on publically available database and has shown encouraging and acceptable results. (6 pages)Selectively filtering image features using a percentage occupancy hit-or-miss transform
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0427
The Hit-or-Miss Transform (HMT) is a well known morphological transform which can be used for template matching and other applications. Recent developments in this area include extensions of the HMT which have employed a variety of techniques in order to improve the noise robustness of the transform. Rank order filters feature heavily in these approaches, and recently, a novel design tool, known as a PO plot, has been introduced. This tool can be used to determine the optimum rank parameter when using these extensions of the HMT to locate features in noisy data. In this paper, the properties of the PO plot are exploited in such a way that an extension of the HMT, known as a POHMT, can be used as a discriminatory filter which selectively marks or discards features in an image. This paper summarises the POHMT, and the PO plot, before demonstrating how these can be used to implement a discriminatory filter. This filter is then shown to produce promising results when applied to the problem of selectively detecting dice in images. (6 pages)Discriminative training of patch-based models using joint boosting for occupant classification
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0449
This paper presents a vision-based occupant classification method which is essential for developing a system that can intelligently decide when to turn on airbags based on vehicle occupancy. To circumvent intra-class variance, this work considers the empty class as a reference and describes the occupant class by using appearance difference. Context contrast histogram is used to represent the patch appearance. Each class is modelled using a set of locally representative parts called patches that alleviate the mis-classification problem resulting from severe lighting change. The selection and estimating the parameters of the patches are learned through joint boosting by minimizing training error. Experimental results from many videos from a camera deployed on a moving platform demonstrate the effectiveness of the proposed approach. (4 pages)Colour texture segmentation using evidence gathering
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0441
A new approach to colour-texture segmentation is presented which uses Local Binary Pattern data and a new colour quantisation scheme based on hue and saturation to provide evidence from which pixels can be classified into texture classes. The proposed algorithm, which we contend to be the first use of evidence gathering in the field of texture classification, uses Generalised Hough Transform style R-tables as unique descriptors for each texture class. Tests on remotely sensed images demonstrate the superiority of the colour-texture algorithm compared to the established JSEG algorithm; a notable advantage of the new approach is the absence of over-segmentation. The VisTex database is used to compare the colour-texture algorithm with alternative methods, including its grey-scale equivalent, for the segmentation of colour texture images; providing good results with smooth texture boundaries and low noise within texture segments. (6 pages)Total electron content mapping using global navigation satellite systems
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0390
We present the results of application high-orbital (GPS/GLONASS) and low-orbital (Parus/TRANSIT) satellite navigation systems to the study of different-scale irregularities in the ionospheric total electron content (TEC), such as troughs, crests of equatorial anomaly, traveling ionospheric disturbances and so on. We also present the results of the comparison of the global ionospheric maps (GIM) of vertical TEC, which are now widely used in ionospheric research, with the results of low- and high-orbital radio tomographic ionospheric imaging and with the data of UV spectral imaging form GUVI instrument (Global Ultraviolet Imager). The data from low-orbital radiotomography systems in Russia (Moscow-Svalbard) and Alaska (Arctic Village-Cordova) were involved in the comparison as well as the data of the IGS (International GNSS Service) network. The comparisons cover the time interval from 2003 to 2008, which includes both geomagnetically quiet and disturbed periods. We also demonstrate the possibilities of GPS/GLONASS TEC studies in connection with solar flares and artificial ionospheric heating. (5 pages)A new mutual information based similarity measure for medical image registration
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0424
Medical image registration (IR) is the systematic process of aligning spate images, often involving different modalities with common reference framework, so complementary information can be combined and compared. This paper presents a new similarity measure which uses Expectation Maximization for Principal Component Analysis allied with mutual information (EMPCA-MI) for medical IR. The new measure has been analysed on multimodal, three band magnetic resonance images (MRI) T1, T2 and PD weighted, in the presence of both intensity non-uniformities (INU) and noise. Both quantitative and qualitative experimental results clearly demonstrate both improved robustness and lower computational complexity of the new EMPCA-MI paradigm compared with existing MI-based similarity measures, for various MRI test datasets. (6 pages)Normalized cuts and watersheds for image segmentation
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0440
In this paper problem of image segmentation is considered. Specifically, normalized graph cut algorithm is regarded. In its source version the Ncut approach is computationally complex and time consuming, what decreases possibilities of its application in practical applications of machine vision. The segmentation approach proposed in this paper overcomes these limitations by incorporating watershed transform and normalized cuts. Results of the proposed method are presented, compared with results of the original normalized cut method and discussed. (6 pages)Validating the neutrosophic approach of MRI denoising based on structural similarity
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0419
This paper focuses on validating the proposed Neutrosophic Set (NS) approach of Magnetic Resonance Image (MRI) denoising based on structural similarity such as Structural Similarity Index (SSIM) and Quality Index based on Local Variance (QILV). The Neutrosophic Set approach of median filter is used to reduce the Rician noise in MR image. The experiments have conducted on real MR image with Rician noise added. The visual and the diagnostic quality of the denoised image is well preserved. The performance of this filter is compared with median filter and non local mean filter (NLM). (6 pages)Closed form spherical omnidirectional image unwrapping
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0443
This paper proposed a novel method of image unwrapping for spherical omnidirectional images acquired through a non-single viewpoint omnidirectional sensor. The proposed method comprises of three key steps, i.e. 1) calibrate the camera to obtain parameters describing the spherical omnidirectional sensor, 2) map world points onto mirror points and, subsequently, onto image points, and 3) set up the projection plane for the final image unwrapping. Depending on the projection plane selected, the algorithm is able to produce either the cylindrical panoramic, the cubloid panoramic, or the ground plane view using closed form mapping equations derived herein. The motivation for developing this technique is to address the complexity in using non-single viewpoint omnidirectional sensor; and ultimately promotes its adoption in robotics. (5 pages)Segmentation of sputum cell image for early lung cancer detection
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0433
Lung cancer has been the largest cause of cancer deaths worldwide with an overall 5-year survival rate of only 15%. Its early detection significantly increases the chances of an effective treatment. To that end, computer-aided diagnosis system using images of sputum stained smears has been an attractive approach due to its practicality, low cost, and invasiveness. In this context, we present a framework for the detection and segmentation of sputum cells in sputum images using respectively, a Bayesian classification and mean shift segmentation. Our methods are validated and compared with an other competitive technique via a series of experimentation conducted with a data set of 88 images. (6 pages)MRI mammogram image classification using ID3 algorithm
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0464
Breast cancer is one of the most common forms of cancer in women. In order to reduce the death rate , early detection of cancerous regions in mammogram images is needed. The existing system is not so accurate and it is time consuming. The Proposed system is mainly used for automatic segmentation of the mammogram images and classify them as benign,malignant or normal based on the decision tree ID3 algorithm. A hybrid method of data mining technique is used to predict the texture features which play a vital role in classification. The sensitivity, the specificity, positive prediction value and negative prediction value of the proposed algorithm accounts to 93.45% , 99.95%,94% and 98.5% which rates very high when compared to the existing algorithms. The size and the stages of the tumor is detected using the ellipsoid volume formula which is calculated over the segmented region. (5 pages)A genetic based generic filter for image impulse noise reduction
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0421
The captured images usually are influenced by impulse noise therefore removing impulse noise is one of most important pre-processing phases in many applications. In this paper, we have proposed a genetic based method to remove impulse noise. This method proposes a composite filter which is a combination of several standard filters to reduce the noise effect. The experimental results showed the proposed method could efficiently restore degraded image while it is approximately stable to noise ratio increment. (5 pages)Image segmentation based on semi-greedy region merging
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0431
Region merging algorithms are known to be fast when the merge criteria are relatively loose but very slow when extended schemes are applied. However, since region merging is greedy and looks only at local information, it is susceptible to suboptimal merge pathways as well as to outliers. This paper presents a fast and effective region merging scheme using a semi-greedy merging criterion and an adaptive threshold (SGAT) to control segmentation resolution. In quantitative analysis on standard benchmarks data, the proposed method performs the best, with respect to specific metrics as well as overall, compared to other segmentation methods. (4 pages)Learning based objective evaluation of image segmentation algorithms
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0444
Image segmentation plays an important role in a broad range of applications and many image segmentation methods have been proposed, therefore it is necessary to be able to evaluate the performance of image segmentation algorithms objectively. In this paper we present a new fuzzy metric to evaluate the accuracy of image segmentation algorithms, based on the features of each segments using neural networks. The neural network after training can distinguish the similarity or dissimilarity of each pairs of segments and finally the segmentation algorithms accuracy have been computed by novel presented metric quantitatively. Our proposed method does not require a manually-segmented reference image for comparison therefore can be used for real-time evaluation and is sensitive to both oversegmentation and under-segmentation. Experimental results were obtained for a selection of images from Berkeley segmentation data set and demonstrated that it's a proper measure for comparing image segmentation algorithms. (6 pages)Video analytics: past, present, and future
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0403
Over the last quarter of a century or so a great deal of money and effort has been devoted developing video analytic solutions which until relatively recently has led to little deployment of these technologies. It could be argued that this has been rather disappointing but the availability of much greater computer power, realistic data sets, and potential customers having more confidence in deploying these technologies we will see the developers' efforts gaining more widespread use in the years ahead. (5 pages)A thresholding approach for detection of sputum cell for lung cancer early diagnosis
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0442
In this paper, we address the problem of detection and extraction of sputum cells that help in lung cancer early diagnosis. Our approach is based on thresholding classifier looking at the distribution of sputum pixels and non sputum pixels in RGB space for extracting the sputum cell from the raw sputum image. In this method the problem is viewed as a segmentation problem focusing on extraction of such sputum cells from the images whereby we want to partition the image into sputum cell regions including the nuclei, cytoplasm and the background that includes all the rest. These cells will be analyzed to check whether they are cancerous or not. In this study, we used a database of 100 sputum color images to test the thresholding classifier by comparing it with the ground truth data of extracted sputum cells and it has shown a better extraction result than previous work. Moreover, we computed a histogram for different color spaces (RGB, YCbCr, HSV, L*a*b* and XYZ) to find the best color space with low false detection rate. We used some performance criteria such as precision, specificity and accuracy to evaluate the improved thresholding classifier. (6 pages)Noise power estimation under generalized detector employment in automotive detection and tracking systems
http://dl-live.theiet.org/content/conferences/10.1049/cp.2012.0416
The noise power estimation process is a vital factor to adaptively define a threshold of target return signal in radar sensor systems and controller area networks (CAN) that are employed to design safety driving applications, collision avoidance systems, and target vehicle tracking systems. This research derives the required detection threshold under implementation of the generalized detector (GD) in frequency modulation continuous wave (FMCW) radar sensor systems for safety driving and tracking applications, for example, under closing vehicle detection. In this paper we propose an appropriate adaptive noise power estimation technique to define the GD threshold based on locally observed noise samples. The improvement in the detection performance reflects an effectiveness of the proposed solution. (4 pages)Time-reversal-based multipath mitigation technique for entropy minimization of SAR images
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0139
Synthetic Aperture Radar (SAR) images a target region reflectivity function in the multi-dimensional spatial domain of range and cross-range with a finer azimuth resolution than the one provided by any on-board real antenna. Conventional SAR techniques just consider a single reflection of transmitted waveforms from targets. Nevertheless, today's new applications force SAR systems to work in much more complex scenes such as urban environments. Consequently, multiple- bounce returns are additionally superposed to direct-scatter echoes. We refer to these as ghost images, since they obscure true target image and lead to poor resolution. By applying Time Reversal concept to SAR imaging (TR-SAR), it is possible to reduce considerably -or even mitigate-ghosting artifacts, recovering the lost resolution due to multipath propagation. Furthermore, some focusing indicators such as entropy (E), contrast (C) and Rényi entropy (RE) provide us with a good focusing criterion when using TR-SAR. (5 pages)A visual voice activity detection method with adaboosting
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0145
Spontaneous speech in videos capturing the speaker's mouth provides bimodal information. Exploiting the relationship between the audio and visual streams, we propose a new visual voice activity detection (VAD) algorithm, to over-come the vulnerability of conventional audio VAD techniques in the presence of background interference. First, a novel lip extraction algorithm combining rotational templates and prior shape constraints with active contours is introduced. The visual features are then obtained from the extracted lip region. Second, with the audio voice activity vector used in training, adaboosting is applied to the visual features, to generate a strong final voice activity classifier by boosting a set of weak classifiers. We have tested our lip extraction algorithm on the XM2VTS database (with higher resolution) and some video clips from YouTube (with lower resolution). The visual VAD was shown to offer low error rates. (5 pages)WiSE-MNet: an experimental environment for wireless multimedia sensor networks
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0171
We propose a simulation environment for networks for Wireless Multimedia Sensor Networks (WMSNs), i.e. net- works with sensors capturing complex vectorial data, such as for example video and audio. The proposed simulation environment allows us to model the communication layers, the sensing and distributed applications of a WMSN. This Wireless Simulation Environment for Multimedia Networks (WiSE-MNet) is based on Castalia/Omnet++ and is available as open source to the research community [1]. The environment is designed to be flexible and extensible, and has a simple camera model that enables the simulation of distributed computer-vision algorithms at a high level of abstraction. We demonstrate the effectiveness of WiSE-MNet with a distributed tracking application. (5 pages)People counting with re-identification using depth cameras
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0113
Low cost real-time depth cameras offer new sensors for a wide field of applications apart from the gaming world. Other active research scenarios as for example surveillance, can take advantage of the capabilities offered by this kind of sensors that integrate depth and visual information. In this paper, we present a system that operates in a novel application context for these devices, in troublesome scenarios where illumination conditions can suffer sudden changes. We focus on the people counting problem with re-identification and trajectory analysis. Automatic people counting offers different application contexts related to security, safety, energy saving or fraud control. Here we go one step further and give hints to extract useful information using depth cameras. The processing of that information allows us to analyze the individuals behavior, particularly if they go away from the typical trajectory, and the problem of re-identifying people. (6 pages)CT-based robust statistical shape modeling for forensic craniofacial reconstruction
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0126
Estimating the facial outlook from an unidentified skull is a challenging task in forensic investigations. This paper presents the definition and implementation of a craniofacial model for computerized craniofacial reconstruction (CFR). The craniofacial model consists of a craniofacial template that is warped towards an unidentified target skull. The allowed transformations for this warping are statistically defined using a PCA-based transformation model, resulting in a linear combination of major modes of deformations. This work builds on previous work [1] in which a statistical model was constructed based on facial shape (represented as a dense set of points) variations and sparse soft tissue depths at 52 craniofacial landmarks. The main contribution of this work is the extension of the soft tissue depth measurements to a dense set of points derived from a database of head CT-images of 156 patients. Despite the limited amount of training data compared to the number of degrees of freedom, the reconstruction tests show good results for a larger part of the test data. Root mean squared error (RMSE) values between reconstruction results and ground truth data smaller than 4 mm over the total head and neck region are observed. (6 pages)Stationary traffic monitor
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0128
Stationary traffic on busy roads can present a safety or security risks. This paper reports on an automated algorithm that detects vehicles that have stopped. It is designed for outdoor use and is extremely robust against lighting variations and occlusions. The algorithm performs well and it is tested against several state of the art techniques. (6 pages)GPGPU-accelerated visual search in large surveillance archives
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0103
Surveillance archives encompass vast amount of data. Given the amount of data the need for search and data exploration arises naturally. Various authorities such as infrastructure operators and law enforcement agencies are confronted with search needs based on a visual description (size, color, clothing, number plates, facial biometry, etc.) and/or behavioral patterns (limping, loitering, etc.) in order to find a ”needle in a haystack” of digital data. In this paper we present a framework which allows for an efficient video archive forensic search and data exploration in an interactive manner, and exploiting hardware accelerated video analytics at the same time. Furthermore we present a query concept to facilitate and improve the search for a specific person in large video surveillance archives using a synthetic human model in a query-by-example manner. The presented overall framework combines know-how on user interfaces, computer vision algorithms and video archive management. The system is designed with an open archive interface in mind enabling it to operate with CCTV (Closed Circuit Tele Vision) video archives from a wide variety of manufacturers. (6 pages)Pervasive monitoring: appreciating citizen's surveillance as digital evidence in legal proceedings
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0130
Images or video streams, extracted from data acquired through surveillance systems and intended to be used as evidence in court, should have all attributes of conventional digital evidence, meaning that they should be admissible, authentic, reliable, complete and believable. This paper discusses the first three attributes that surveillance systems should comply with to be submitted as evidence in legal proceedings and it identifies some of the obstacles in the way through harmonization. The focus is on data gathered from a range of ad hoc sources present at the scene of an incident, including smartphones and wireless sensor networks (used for safety, security or traffic management/environmental monitoring). New scenarios for crowd-sourced surveillance mediated by law enforcement supervision are further considered. Specific attention is brought to the compliance with privacy requirements that often condition the admissibility of the evidence. (6 pages)Coastline detection using coupled variational level-set formulation
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0107
In this paper, we describe a method of detecting dynamic coast-lines from ground-level images using an integrated level-set framework. A dynamic coastline is represented as the longest boundary of intersection of multiple moving fronts (geometric active contours) corresponding to multiple regions within the image together with model of their evolution using the level set formulation. The evolution of the various moving front is modelled using an adaptive variational formulation of the level set function that in-turn minimizes an appropriate energy function. We explore the performance of the model and show that the proposed method achieves better accuracy than other widely used methods for coastline extraction. (6 pages)Efficient 3D face reconstruction from low quality video
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0117
3D shape information is crucial in many video analytic applications, such as face recognition and expression analysis. However, most commercial 3D modeling systems rely on dedicated equipment, which lacks operational flexibility. We present an efficient approach to reconstruct 3D face from low quality video, concentrated on recovering the depth information lost in imaging process. There are two novelties in the proposed method. First, depth error is explicitly estimated, which ensures a fully linear shape recovery process. Second, the shape is adjusted locally using local feature analysis (LFA) model, which effectively alleviates the model dominance problem. A prototype system is established based on the proposed approach, and evaluated on a publicly available database. Experimental results show that, compared with state-of-the-art approaches, our method increase accuracy of estimated shape in an efficient way. (6 pages)Real-time active visual tracking with level sets
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0122
This paper presents a new real-time active visual tracker which improves standard mean shift tracking by using level sets to extract contours from the target. We use colour and the disparity map computed from a stereo camera pair which prove to be powerful features for tracking in an indoor surveillance scenario. To combine the features in the level sets process, we enhance Chen's et al appearance model of [5] by using a probabilistic model determined via Expectation-Maximization (EM) clustering. The level set result is used as the weighting kernel which improves the accuracy of the similarity measurement in the mean shift method. Finally a Kalman filter deals with complete occlusions. (6 pages)Hooligan detection: the effects of saliency and expert knowledge
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0131
We investigated differences in visual search of dangerous events between security experts and naive observers during the observation of large scenes, typically encountered on the grandstand of stadiums during soccer matches. Our main technical objective was the reduction of computational effort required for the detection and recognition of such events. To overcome the scarcity and legal issues associated with real footage, we designed a new algorithm for the synthesis of crowd scenes with well-controlled statistical properties. We characterize the relative importance of saliency and expert knowledge for the generation of correct detections and the visual search strategies for both security experts and naive observers. We found that during the first few seconds of this search task, experts and naive observers look at the scenes in a similar fashion, but experts see more. We compare the results with theoretical models for saliency and event classification. We show that the recognition model can deliver reasonable classification/detection performance even when operating under real-time constraints. When real-time operation is not a concern, performance can be improved further by allowing the model to grow. (6 pages)Medical image security using LSB and chaotic logistic map
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0086
In this modem era, many researchers have been concentrating more on using the field of chaos and its applications for their research. Particularly, medical image encryption and decryption using chaotic signals are proposed frequently for medical image cryptography and steganography. In this article, the patient medical details in text form and medical image of the organ in pictorial form are encrypted and decrypted using two different set of algorithms. One of the advantages of this method is its security, which is provided by the chaotic signal.Further studies on forensic features for source camera identification
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0119
Most camera identification schemes focus on finding image features that can increase classification accuracy as well as computational efficiency. For forensic investigation purposes, however, these selection criteria are not enough since most real-world photos may have undergone common image processing due to various reasons. Therefore, source camera classifiers must have the capability to resist the influence of common image processing when they tackle these processed photos. In this work, we implement a published camera classifier and investigate the performance of the classifier on images under shearing, histogram equalization, and contrast-stretching operations. Besides, we probe into the impact of camera databases of different sizes on the performance of the classifier. (6 pages)A comparison of image fusion methods on visible, thermal and multi-focus images for surveillance applications
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0129
Because of rapid development in sensor technology in recent years, machine perception for security purposes can be improved by using different sensor types. Fusing of images from different sensors is the key point of this development. In this paper, seven well-known image fusion methods are compared visually and quantitatively on three surveillance applications including enhanced night vision, concealed weapon detection and extending depth of the field of an optical camera. (6 pages)Accurate 3D footwear impression recovery from photographs
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0121
The recovery of footwear impression in crime scenes plays an important role in investigations to corroborate or refute information, or to narrow down the number of suspects. Casting 3D footwear impressions is a long-standing standard to obtain the 3D models of the prints, slowly being replaced by a less invasive method, 3D scanning. In this paper, we present an alternative method based on multiview stereo that yields an accurate 3D model and provides some benefits over existing methods. We evaluate the results comparing our reconstructed 3D models with the ones acquired by 3D scanning. We also examine the advantages and drawbacks of each method. (6 pages)Image segmentation using Gabor filters
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0080
In this project image segmentation is implemented and the features are computed over multiple spatial orientations and frequencies. A given image is passed through a bank of even symmetric Gabor filters. A clustering algorithm performs selection of these filtered images and yields segmentation. In order to simplify the results of the above process, a color label is associated with each cluster thereby making it an easier task to pursue the above approach.View synthesis of KDEX imagery for 3D security X-ray imaging
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0137
We demonstrate the synthesis of intermediary views within a sequence of X-ray images that exhibit depth from motion or kinetic depth effect in a visual display. Each synthetic image replaces the requirement for a linear X-ray detector array during the image acquisition process. Scale invariant feature transform, SIFT, in combination with epipolar morphing is employed to produce synthetic imagery. Comparison between synthetic and ground truth images is reported to quantify the performance of the approach. Our work is a key aspect in the development of a new 3D imaging modality for the screening of luggage at airport checkpoints. This programme of research is in collaboration with the UK Home Office and the US Dept. of Homeland Security. (6 pages)Latent fingerprint segmentation using ridge template correlation
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0125
Even with the high accuracy of automated fingerprint identification in matching plain to rolled prints, latent to rolled print matching continues to require human input. Latent prints are those that are lifted from a surface, typically at a crime scene, whereas plain prints are obtained under supervision with quality control. In comparison to plain or rolled prints, latent prints are usually of poor quality and have a small fingerprint surface area, making it difficult to extract a large number of features reliably. Manually processing latent prints is time consuming, so efforts are being made to speed up the process through partial automation. One of the first steps is image segmentation, which is the separation of the foreground (fingerprint region) from the background. Traditional automated methods for segmentation are designed for backgrounds with random noise and perform poorly on structured/textured backgrounds, resulting in many spurious minutiae, thus inhibiting the matching process. This paper presents a novel approach for improving the performance of segmentation in latent prints, with and emphasis on structured backgrounds. The results show that the proposed method reduces the average detected fingerprint area from 60.7% of the total image to 33.6% while maintaining the rate of true minutiae in the fingerprint region; in effect, low-quality portions of the print are being removed from consideration. In a separate test, the rate of true minutiae labelled as background was reduced from 1.41% to 0.29% while maintaining the same average fingerprint region size in comparison to a traditional segmentation method. The results were obtained using a database of 258 latent fingerprint images with ground truth minutiae. (6 pages)A multi-feature tracking algorithm enabling adaptation to context variations
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0127
We propose in this paper a tracking algorithm which is able to adapt itself to different scene contexts. A feature pool is used to compute the matching score between two detected objects. This feature pool includes 2D, 3D displacement distances, 2D sizes, color histogram, histogram of oriented gradient (HOG), color covariance and dominant color. An offline learning process is proposed to search for useful features and to estimate their weights for each context. In the online tracking process, a temporal window is defined to establish the links between the detected objects. This enables to find the object trajectories even if the objects are misdetected in some frames. A trajectory filter is proposed to remove noisy trajectories. Experimentation on different contexts is shown. The proposed tracker has been tested in videos belonging to three public datasets and to the Caretaker European project. The experimental results prove the effect of the proposed feature weight learning, and the robustness of the proposed tracker compared to some methods in the state of the art. The contributions of our approach over the state of the art trackers are: (i) a robust tracking algorithm based on a feature pool, (ii) a supervised learning scheme to learn feature weights for each context, (iii) a new method to quantify the reliability of HOG descriptor, (iv) a combination of color covariance and dominant color features with spatial pyramid distance to manage the case of object occlusion. (6 pages)Clustering performance analysis of FCM algorithm on iterative relaxed median filtered medical images
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0069
Noise removal is a major concern in image processing particularly in medical imaging. In this paper, a novel noise removal technique called Iterative relaxed median filter (IRMF) has been proposed and the effect of noise removal, by means of median filtering, on Fuzzy C-Means Clustering (FCM) has been analysed. Noise removal is carried out by various median filtering methods such as standard median filter (SMF), adaptive median filter (AMF), hybrid median filter (HMF) & relaxed median filter (RMF) and the performance of these methods is compared with the proposed method.On the location-dependent quality of the sensor pattern noise and its implication in multimedia forensics
http://dl-live.theiet.org/content/conferences/10.1049/ic.2011.0134
Due to its uniqueness and potential in forensic applications, the sensor pattern noise (SPN) has drawn much attention in the digital forensic community and academia in the past few years. While much work has been done on the application of the SPN, little investigation into its characteristics has been reported in the literature. It is our intention to fill this gap by providing insight into the dependency of the SPN quality on the location in images. We have observed that the SPN components at the image periphery are distorted to the extent that when used for source camera identification, they tend to cause higher false positive rates. Empirical evidence is presented in this work. We suspect that this location-dependent SPN quality degradation has strong connection with the vignetting effect as they exhibit the same type of location-dependency. We recommend that when image blocks are to be used for forensic investigation, they should be taken from the image centre before SPN extraction is performed in order to reduce false positive rate. (6 pages)Mesh simplification method based on vision feature
http://dl-live.theiet.org/content/conferences/10.1049/cp.2011.0918
In order to improve the quality of the simplified mesh model, this paper proposes an algorithm that takes advantage of the vertex vision importance to simplify the mesh based on quadric measurement error. It adopts visual importance of vertex factor, the curvature at the vertex and the texture error factor in the cost function to control the sequence of half-edge collapse, which is usable to retain good visual characteristics of the original model in the simplify process. Through experimental comparison and analysis, it shows that the algorithm is effective in improving the quality of the simplified model and can maintain some good visual characteristics of the original model.LTE and future evolutions for the benefits of security wireless networks
http://dl-live.theiet.org/content/conferences/10.1049/cp.2011.0927
First responders make use of professional wireless system (e.g. TETRA) for conducting their missions. Those systems are today mainly used to convey voice and short messages. To improve the operational effectiveness, these organisations need wireless data transmission capabilities to exchange images, access to databases or transmit live video streams from the incident area. But, these needs cannot be realised with narrow-band technologies. However, LTE can bring these capabilities to first responders with timely exchange of files and transmission of live high definition video streams. Besides, future enhancements of LTE, LTE-Advanced, will further improve the performance not only to the benefits of mobile operators but also for first responders by providing additional coverage flexibility and more capacity especially at the cell edge, two key performance indicators of a radio security network.Effective camera calibration in free-viewpoint systems
http://dl-live.theiet.org/content/conferences/10.1049/cp.2011.0847
Multi-camera calibration parameters are needed in free-viewpoint video system to obtain virtual viewpoint. Most existing calibration technologies are for single camera and further research is needed for multi-camera calibration. A multi-camera calibration method based on 2D plane calibration algorithm combined with stereo vision calibration is proposed in this paper. Camera intrinsic parameters can be obtained using 2D plane calibration algorithm. Through transforming the world coordinate system, the unique extrinsic parameters are got. The validity of the proposed method is verified by experiments.The research of foggy blurring image restoration
http://dl-live.theiet.org/content/conferences/10.1049/cp.2011.0775
In this paper the restoring technique of foggy gray blurring image and foggy color blurring image are mainly studied. Global histogram equalization method and local histogram equalization method are all used to restore foggy blurring gray image, hue saturation adjustment method and Retinex method are all used for restoring foggy blurring color image. The experimental results show that the optimal restoring algorithm is different for different image because of the difference in light, fog seriousness degree, ratio between bright and dark areas, and noise. Therefore, it is needed to select right algorithm to restore foggy blurring image with different degradation reason.