Depth maps are crucial for many visual applications, where they represent the positioning information of the objects in a three-dimensional scene. Usually, depth maps can be acquired via various devices, including Time of Flight, Kinect or light field camera, in practical applications. However, a brutal truth is that both intrinsic and extrinsic artefacts can be found in these depth maps which limits the prosperity of three-dimensional visual applications. In this study, the authors survey the depth map artefacts reduction methods proposed in the literature, from mono- to multi-view, via spatial to temporal dimension, in local to global manner, with signal processing to learning-based methods. They also compare the state-of-the-arts via different metrics to show their potentials in future visual applications.

Phase unwrapping is a fundamental task in phase-based profilometry. Existing spatial and temporal approaches are facing challenges such as error propagation and low efficiency. In this study, the authors propose a learning-based method that uses a support vector machine (SVM) to perform phase unwrapping, where the problem is solved as a classification task. To be specific, seven elements, extracted from the captured patterns and the wrapped phase, form the input feature vector and the fringe order is the output class. Besides, a radial basis function kernel SVM is adopted as the model. The proposed method is conducted independently for every pixel, and does not suffer from error propagation in the spatial unwrapping. Moreover, it needs fewer patterns than temporal unwrapping since only one phase map is required. Simulation and experimental results demonstrate that the proposed scheme produces precise depth maps, which are comparable with the complex quality-guided methods but at a much faster speed.

The disparity refinement phase of existing end-to-end stereo matching networks refines the disparity by learning the mapping from the concatenated coarse disparity and corresponding features to fine disparity. It depends on the scenarios' characteristics, such as the distribution of disparity and semantic categories contained in the domain, which makes the network fail to work on unseen domain. In this paper, we propose a geometry and context guided refinement network (GCGR-Net) containing a Fine Matching module and an Upsampling module. GCGR-Net learns to utilize pixels' relationship to get high resolution dense disparity, which is independent of the data's content. The Fine Matching module performs a minimum range search based on the relationship between the possible matching pixel pairs, i.e. the called geometry information, to recover the internal structure of the object. The Upsampling module obtains context information, the relationship between central pixel and the pixels in its neighborhood, to upsample the lower resolution disparity. The final disparity map is obtained step by step through an iterative refinement model. Experiment results show that our method not only has good performance in the training scenarios, but also outperforms previous methods on the unseen domain without fine-tuning.

Geometric primitives contained in three-dimensional (3D) point clouds can provide the meaningful and concise abstraction of 3D data, which plays a vital role in improving 3D vision-based intelligent applications. However, how to efficiently and robustly extract multiple geometric primitives from point clouds is still a challenge, especially when multiple instances of multiple classes of geometric primitives are present. In this study, a novel energy minimisation-based algorithm for multi-class multi-instance geometric primitives extraction from the 3D point cloud is proposed. First, an improved sampling strategy is proposed to generate model hypotheses. Then, an improved strategy to establish the neighbourhood is proposed to help construct and optimise an energy function for points labelling. After that, hypotheses and parameters of models are refined. Iterate this process until the energy does not decrease. Finally, models of multi-class multi-instance geometric primitives are simultaneously and robustly extracted from the 3D point cloud. In comparison with the state-of-the-art methods, it can automatically determine the classes and numbers of geometric primitives in the 3D point cloud. Experimental results with synthetic and real data validate the proposed algorithm.

Estimating human pose and shape without markers is a challenging problem. This study proposes a multiple-view markerless human motion capture framework. Firstly, a multi-view camera system is built for capturing real-time images of moving humans on multiple views. Secondly, by employing the OpenPose method, the authors calculate robust 3D key points from 2D key points of the human body, which are estimated from the multi-view images. And dense 3D point cloud is reconstructed from images. Thirdly, they propose a novel SMPL-based method to represent human motion by fitting the SMPL model to 3D key points and 3D point clouds. In order to achieve a more accurate human pose, a penalty term is utilised to solve the problem of error accumulation in the process of human motion capture. In addition, they present a dense mesh template-based SMPL that can be deformed to point cloud to recover a real human body shape. Finally, they map multi-view colour images onto the human mesh model to acquire rendered mesh. The experimental results show that the proposed method improves the accuracy of human pose and realises the 3D human body model more realistic.

In this study, the authors present a novel individual retrieval method based on oral cavity point cloud data and correntropy-based registration algorithm. Since the three-dimensional oral cavity data contains a large amount of noise and outliers, it may lead to a decrease in registration accuracy, which affects the accuracy of retrieval rate. Therefore, the authors introduce the correntropy into the rigid registration algorithm to solve this problem. Then, they filter the matched point cloud data and then use the mean squared error to judge the individual differences of the model data. Finally, the accurate retrieval of the oral cavity data is realised. Experimental results demonstrate the proposed retrieval three-dimensional model algorithm can be successfully searched under different model data, which can help forensics use the characteristics of biological individuals to accurately search and identify, and improve recognition efficiency.

Electron microscopy (EM) image segmentation plays an important role in computer-aided diagnosis of specific pathogens or disease. However, EM image segmentation is a laborious task and needs to impose experts knowledge, which can take up valuable time from research. Convolutional neural network (CNN)-based methods have been proposed for EM image segmentation and achieved considerable progress. Among those CNN-based methods, UNet is regarded as the state-of-the-art method. However, the UNet usually has millions of parameters to increase training difficulty and is limited by the issue of vanishing gradients. To address those problems, the authors present a novel highly parameter efficient method called DenseUNet, which is inspired by the approach that takes particular advantage of recent advances in both UNet and DenseNet. In addition, they successfully apply the weighted loss, which enables us to boost the performance of segmentation. They conduct several comparative experiments on the ISBI 2012 EM dataset. The experimental results show that their method can achieve state-of-the-art results on EM image segmentation without any further post-processing module or pre-training. Moreover, due to smart design of the model, their approach has much less parameters than currently published encoder–decoder architecture variants for this dataset.

This study addresses the problem of non-perspective pose estimation from line correspondences in the traffic scenarios. A coarse-to-fine 3D road registration method is proposed for this problem in two stages. Firstly, the iterative closest point algorithm is exploited to estimate the pose coarsely. An objective function is then established to incorporate the feature correspondences for refining the coarse pose. Besides, the framework including road registration is employed for traffic video augmentation. The framework begins with the inputs of traffic videos, road information from Geographic Information Systems and 3D models of traffic elements (e.g. vehicles, pedestrians). Subsequently, 3D road model generation and point-to-line correspondence establishment are achieved in the preprossessing stage. After road and viewpoint registration, the 3D graphic engine is employed to simulate the traffic scene with the road, viewpoints and traffic elements. The augmented videos are generated by fusing the original frames and newly projected traffic elements. The authors demonstrate the superiority of the proposed registration method by the comparison to state-of-the-arts in both quantitative and qualitative experiments. In addition, the frames of the augmented videos validate the proposed method in the application.

Inspection of physical surface defects is a significant concern in many industrial areas. In railway systems, this process mainly includes the detection and classification of defects in rails and wheels, for which laser-based optical inspection technologies have gradually been applied in the form of 2D profile measurement, benefiting from its high precision and robustness to surface conditions. However, defect classification and evaluation after the initial detection works still rely heavily on human inspectors to make maintenance suggestions. The linear nature of rails makes it possible to increase the dimension of rail measurement data from 2D to 3D by aligning 2D profiles along the rail, from which more comprehensive diagnosis information becomes available. In combination with appropriate artificial intelligence algorithms, this approach can potentially replace human-dominated defect classification and evaluation work. This study presents a 3D model-based railway track surface defect classification and evaluation method. A set of geometrical features are extracted from the 3D model of track surface defects to describe a distinguishable pattern for each category of defect. Multi-class classifiers are then tested and have shown promising results on a group of artificial track surface defects, giving a systemic solution for 3D model-based automatic track surface defect inspection.

360 video is very popular due to its 360 views of a scene. Although 360 videos are also compressed by a hybrid coding framework like 2D video, its high resolution and serious shape deformation affect coding efficiency. In equirectangular projection (ERP) format of 360 videos, if an object moves from equator regions to pole regions or vice versa, large deformation will be introduced and motion estimation cannot find the best-matched part. To solve the above problem, the authors propose to generate a better reference frame for the current to be encoded frame. First, they project the frame prior to the current one from ERP to the sphere and rotate it at an appropriate angle depending on motion vectors. Subsequently, they insert this generated frame to the rear of the reference queue and let the encoder work as usual. The advantage is that the inserted frame has a more similar shape deformation as the current frame, which greatly helps motion estimation and makes full use of 360 video characters. Their method is simple and friendly compatible with the existing compression standard. Experiments prove that their method achieves 1.57% Bjøntegaard Delta (BD)-gain compared with standard high efficiency video coding.

Big data analytics gain significant interest over the traditional data-processing methodologies that engage in extracting the hidden patterns and correlations from the massive data, termed as big data. With the aim of relieving the computational complexity the clustering method plays a significant role. With the knowledge of the clustering algorithms, the big data arriving from the distributed sources is processed using the MapReduce framework (MRF). The MRF possesses two functions, namely, map function and reduce function, such that the map function is based on the proposed Fractional Sparse Fuzzy C-Means (FrSparse FCM) algorithm and reduce function is based on particle swarm optimisation-based whale optimisation algorithm (P-Whale). Initially, the optimal centroids are computed using the proposed algorithm in the mapper phase that is optimally tuned in the reducer phase, and it is clear that the proposed FrSparse FCM-based MRF ensures the parallel processing of the big data. Experimentation is performed using the Skin data set and the localisation data set taken from the UCI machine learning repository, and the analysis is progressed using the metrics, such as accuracy and DB Index. The analysis proves that the proposed method acquired a maximum accuracy of 90.6012% and a minimum DB Index of 5.33.

The multi-atlas-based methods are widely applied in the automatic labelling in magnetic resonance (MR) images. However, most multi-atlas-based methods require that all atlases be registered to the target image accurately to have a correct label propagation. In this study, the authors introduce the term spatial indexes and construct a hybrid atlas forest model to gather the labelling information from all atlases without propagating labels from every single atlas. Furthermore, a new automatic labelling method using the hybrid atlas forest model based on spatial indexes is proposed. In the proposed framework, an atlas is chosen arbitrarily as a reference image and the spatial indexes are constructed on this image space. Then, the samples are selected from all atlases in the dataset based on the spatial indexes to construct a samples pool. Finally, the hybrid atlas forest model will be trained on the samples pool and used to predict the labelling of the target. Experiments are conducted on two public datasets to evaluate the effectiveness of the proposed method. The experimental results show that the proposed method reduces the requirement of strong dependence on precise registration and improve the accuracy of labelling.

Sensor noise sources cause differences in the signal recorded across pixels in a single image and across multiple images. This study presents a Bayesian approach to decomposing and characterising the sensor noise sources involved in imaging with digital cameras. A Bayesian probabilistic model based on the (theoretical) model for noise sources in image sensing is fitted to a set of a time-series of images with different reflectance and wavelengths under controlled lighting conditions. The image sensing model is a complex model, with several interacting components dependent on reflectance and wavelength. The properties of the Bayesian approach of defining conditional dependencies among parameters in a fully probabilistic model, propagating all sources of uncertainty in inference, makes the Bayesian modelling framework more attractive and powerful than classical methods for approaching the image sensing model. A feasible correspondence of noise parameters to their expected theoretical behaviours and well-calibrated posterior predictive distributions with a small root mean square error for model predictions have been achieved in this study, thus showing that the proposed model accurately approximates the image sensing model. The Bayesian approach could be extended to formulate further components aimed at identifying even more specific parameters of the imaging process.

Magnetic resonance imaging (MRI) is a very effective method for identifying any abnormality in the structure and physiology of the spine. However, MRI is time consuming as well as costly. In this work, the authors propose an algorithm which can reduce the time of MRI and thus the cost, with minimal compromise on accuracy. They reconstruct a three-dimensional (3D) image of the spine from a sequence of 2D MRI slices along any one axis with reasonable slice gap. In order to preserve the image at the edges properly, they regenerate the 3D image by using a combination of bicubic and bilinear interpolation along the orthogonal axis. From the reconstructed 3D, they use a simple geometric method to slice out any possible location along any axis and get the information in that region. They have tested their algorithm on real data, and found that their algorithm reduces the time by 80%, with high internal data preservation accuracy of about 96%.

In this study, a novel approach based on multi-objective genetic algorithm (MO-GA) is used for simultaneous tuning the unscented Kalman Filter (UKF) parameters and camera and inertial measurement unit camera calibration in a vision inertial navigation system (VINS). This system consists of visual odometry and inertial navigation system (INS) which integrates with a UKF. In order to obtain simultaneous tuning and calibration of the parameters and variables, the MO-GA minimises the root mean square error of the position and velocity of the vehicle on a selected trajectory of the benchmark data set. Then, the tuned parameters and calibrated variables are placed in the VINS and an adjusted VINS (AVINS) is obtained. For investigating the AVINS, the mentioned system is compared with INS only, VINS based on calibration data of the benchmark data set, and GPS/INS as Real Data on the identical trajectory. Furthermore, in order to evaluate the results of the proposed approach, the AVINS is examined in the second trajectory. The results indicate the proper performance of the presented approach in the simultaneous tuning the filter parameters and calibrating the variables of sensors that are used in the uncalibrated VINS.

Depth maps are used to describe object positioning information in three-dimensional (3D) space, and they are crucial for RGB-D data representation, which is useful for numerous interactive visual applications. In practice, depth maps are often contaminated by compound noise, including intrinsic noise and missing regions owing to active illumination shadows. As existing noise models cannot describe the above-mentioned compound noise effectively, the subsequent filter design is a challenging task. In this study, an adaptive colour-guided non-local mean (NLM) filter is proposed to address such compound noise. First, the authors classify the depth map into hole and non-hole pixels. Then, the proposed filter is designed on the basis of the NLM framework, where the colour image is used as a guide prior for hole-artifact removal. Finally, the authors use a shock filter to effectively address the non-regularisation of the restored depth map edges and remove the remaining noise. Experiments show that the proposed filter qualitatively and quantitatively outperforms existing colour-guided and unguided filters. Moreover, the authors verify the superiority of the proposed filter through virtual view synthesis and 3D scene reconstruction applications.

Unsupervised domain adaptation aims to learn a classifier for the unlabelled target domain by leveraging knowledge from a labelled source domain. This study presents a novel domain adaptation framework from global and local transfer perspectives, referred to as multi-metric domain adaptation (MMDA) for unsupervised transfer learning. At the global level, MMDA minimises the marginal and within-class distances and maximises the between-class distance between domains while maintaining the features of the source domain to improve the cross-domain adaptability. At the local level, MMDA exploits both in- and cross-domain manifold structures embedded in data samples to increase the discriminative ability. The authors learn a coupled transformation that projects the source and target domain data onto respective subspace where the statistical and geometrical divergences are reduced simultaneously. They formulate global and local adaptation methods in an optimisation problem and derive an analytic solution to the objective function. Extensive experiments demonstrate that MMDA shows improvements in classification accuracy compared with several existing state-of-the-art methods.

The low rank approximation for MR image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In spite of the great success of existing low rank approximation methods, these tend to lose the subtle edge texture when removing noise. It could degrade the image visual quality and affect the final clinical diagnosis. In this paper, a novel MR image denoising approach is proposed based on low rank approximation model and the Laplacian-of-Gaussian edge detector. In the proposed approach, a similarity evaluation scheme for noisy patch is employed to avoid the effect of the noise in the patch matching, and the details of the edge texture are preserved by the Laplacian-of-Gaussian edge detector. Experimental results show that the proposed approach is efficient and superior to some of the existing approaches in both objective criterion and visual fidelity. The proposed method can retrieve a clear MR image from the noisy one, with the detail of the edge texture, which could be very important in the clinical diagnosis.

Copy-move forgery (CMF) detection is one of the most practical problems in image forensics. The authenticity of the image becomes more crucial when the images are used in the criminal investigations, intelligence services, and medical documentations. In this study, the authors suggest a CMF detection algorithm. At first they they suggest to use a sparse recovery algorithm to identify the suspicious segments. To incorporate the colour information of the image segments, they propose to compare the histograms of the identified segments to detect the similar ones. The keypoints of those parts are obtained and the matched ones are located. In the last step, they suggest a morphology scheme to extract the forged region. They have evaluated the proposed method in the detection of various forged images. The simulation results reveal the forgery detection capabilities of the suggested algorithm compared to the other state-of-the-art schemes. The proposed method has superiority over its counterparts in detecting the scaled forgeries. Moreover, the sparse recovery step enables the proposed algorithm to remove the genuine repeated patterns of the image, while the other CMF detection techniques wrongly consider those parts as a forgery. Furthermore, the proposed scheme is on-average faster than the other schemes.

Image segmentation of magnetic resonance image (MRI) is a crucial process for visualisation and examination of abnormal tissues, especially during clinical analysis. Complexity and variations of the tumour structure magnify the challenges in the automated detection of a brain tumour in MRIs. This study presents an automatic lesion recognition method in the MRI followed by classification. In the proposed multistage image segmentation method, the intent region initialisation is performed using low-level information by the keypoint descriptors. A set of the linear filter is used to transform low-level information into higher-level image features. The set of features and filter training data are accomplished to track the tumour region. The authors adopt a possibilistic model for region growing, and disparity map for the refinement process to grave consist boundary. Further, the features are extracted using the Fisher vector and autoencoder. A set of handcrafted features is also extracted using a segmentation-based localised region to train and test the support vector machine and multilayer perceptron classifiers. The experiments that are performed using five MRI datasets confirm the superiority of proposal as that of the state-of-the-art methods. It reports 94.5 and 91.76%, average accuracy of segmentation and classification, respectively.

This study presents a generative adversarial network (GAN) called conditional Wasserstein GAN-gradient penalty (CWGAN-GP)&DenseNet and ResNet, and a convolutional neural network (CNN) called improved CNN to complete underwater sonar image classification. Specifically, to solve the problem of insufficient underwater sonar image data, the CWGAN-GP&DR is developed to expand underwater sonar image data set. Besides, to improve the analysis and utilisation of the feature map and reduce the misclassification rate of categories with similar probabilities, improved CNN is proposed to complete the final underwater sonar image classification. Finally, compared with other methods, the CWGAN-GP&DR generate better underwater sonar images and effectively expand the underwater sonar image data set. Moreover, compared with the original data set and other expanded data set, the highest accuracy rate of 85.00% can be obtained on the CWGAN-GP&DR expanded data set by CNN. Furthermore, CNN, CNN-bais and improved CNN are used to perform classification experiments on each data set, and the accuracy of the improved CNN is the highest on all data sets and reached the highest accuracy of 87.71% on CWGAN-GP&DR expanded data set. The experimental results demonstrate that the proposed method can effectively improve the performance of underwater sonar image classification.

Cellular morphology analysis has been widely used to detect abnormalities in biological processes. Clinicians have observed that lymphocytes become highly deformable under special conditions, particularly when graft rejection occurs. The characterisation of lymphocyte boundary deformation provides important quantitative parameters to assist clinical rejection diagnosis. To evaluate the dynamic features of the boundaries of target lymphocyte when a graft rejection occurs, a contourlet transform-based method is proposed to extract the characteristics of cell boundary variation. First, the lymphocyte is segmented and tracked to obtain their edge-to-centroid distance signals. Subsequently, a contourlet transform is performed on these signals, during which the edge-to-centroid distance signals of the lymphocyte is decomposed at multiple scales using the Laplacian pyramid; a multi-directional decomposition is then performed using a direction filter to merge the singularities distributed along the same direction and obtain the contourlet transform coefficients. Finally, statistical parameters of the cell dynamic boundaries are calculated, then fed into the support vector machine for classification of the cell deformation. Our findings demonstrate that contourlet transform has better performance in representing image features such as cell boundaries than wavelet transform for its prosperities of multi-scale and multi-directional decomposition for cell images.

Sparse reconstruction is used to solve the inverse problem of single image super-resolution (SR) as a patch-based sparsity promoting regularisation problem. A coupled trained overcomplete dictionary from high-resolution (HR) and low-resolution (LR) image patches containing significant features is proposed using sparse representation to produce HR patches from their LR counterparts. In this study, the authors develop a multi-core single image SR technique for LR multi-spectral images based on patch-wise sparse representation coupled with morphological component analysis driven feature extraction. Simulations are carried out to evaluate the proposed method using real remote sensing images of a few Indian satellites, RESOURCESAT-2 and CARTOSAT-2, as well as other satellites, such as QuickBird etc. Results are also compared with other existing SR methods to establish the superiority of the proposed method in terms of both objective metrics and visual analysis.

In this study, the authors propose a subpixel image registration framework that detects and matches feature points. Rigid and nonrigid registration models are employed to solve the problem of subpixel image registration problem. A rigid registration model based on the norm is proposed to regularise the rotation coefficients using the indicator function to estimate the rigid transformation parameters. The latter estimation simplified is made easy by the reduction in the rigid transformation from two dimensions to one dimension. Furthermore, a non-rigid registration model based on the and norms is proposed to estimate the elastic coefficients of the compact support radial basis functions. Due to the linear representation of the transformation function, the rigid and nonrigid subpixel image registration models can be solved efficiently using the fast iterative shrinkage-thresholding algorithm. Experiments on a demosaicing data set, the ocean of remote sensing data set, a brain data set and the fundus image registration data set show that the proposed rigid and non-rigid registration models can accurately perform subpixel image registration.

The research of CAPTCHA recognition is helpful to discover the security vulnerabilities in time and improve its safety. In comparison with digits and English letters, Chinese characters have many more categories which lead to the requirement of a large amount of training data. Therefore, this study proposes a novel method for one-shot and few-shot Chinese CAPTCHA recognition, using the deep Siamese network, based on the idea of template matching. In this method, the residual convolutional neural network branches are used for feature extraction of CAPTCHAs, a fully-connected layer is used for calculating the similarity of features, and a hard negative mining algorithm is designed to promote convergence. Experiments are done on a self-built small-scale Chinese CAPTCHA dataset. The results show that this proposed method can achieve higher accuracy on the known characters than traditional methods. For the brand-new characters, only one template is required to recognise them and the accuracy is close to known characters. To summarise, it is able to build a Chinese CAPTCHA recognition model with high accuracy and extensibility by using a small-scale dataset.

A mammogram is an image of a breast used to detect and diagnose breast cancer. This paper emphases a Computer-Aided Detection system based on convolutional neural network (CNN) that uses the concept of deep learning to classify the mammogram images into benign, malignant and normal. The proposed CNN model consists of eight convolutional, four max-pooling and two fully connected layers and achieved better results compared to the pre-trained nets, AlexNet and VGG16. The proposed model demonstrates the feasibility of using CNNs on medical image processing techniques for the classification of breast masses. The results are also compared with the state-of-the-art machine learning algorithm like kNN classifier. Experimentation is done with three datasets. Among them, two are publicly available, Mammographic Image Analysis Society (MIAS), digital database for screening mammography (DDSM) and an internally collected dataset. The proposed model achieved accuracies of 92.54, 96.47 and 95 and the Area under the ROC curve (AUC) score of 0.85, 0.96 and 0.94 for MIAS, DDSM and the internally collected dataset respectively. Furthermore, the images of the three datasets are merged to build one large set and used to fine tune the proposed CNN model and produced accuracy of 98.32 and AUC of 0.98.

The study introduces an adaptive switching interpolation filter (ASIF) for restoring images contaminated with salt & pepper impulse noise. The new method restores noisy pixels by applying a new interpolation scheme that combines Shepard's inverse distance weighting and Simpson's natural neighbour interpolation techniques. The new interpolation scheme is designed based on the percentage of the overlapping area and the distance between the sites created by noisy pixels with the sites of uncorrupted pixels in the Voronoi tessellation. Since natural neighbour-based techniques do not support extrapolation, the proposed algorithm performs Shepard's inverse distance weighting-based restoration when the noisy pixels fall outside the convex hull formed by uncorrupted pixels. As the proposed method combines the advantages of Simpson's natural neighbour and Shepard's inverse distance weighting interpolation methods, it better preserves the natural intensity variations in images and provides smoother approximation than other methods used in the comparative study. Visual and quantitative experimental analysis performed on various images with peak signal to noise ratio, mean structural similarity index measure, image enhancement factor, and feature-similarity index measure demarcates the improved capability of ASIF over other comparative filters.

The use of computer vision technology to analyse the characteristics of smoke such as Ringelmann blackness coefficient and colour information can directly and efficiently reflect the situation of smoke emissions in industrial production, which has great significance in improving air quality. As many factors stand in the way, including the amount and speed of industrial smoke emissions, natural wind speed, illumination etc., an accurate and complete detection of the targeted smoke in images becomes a difficult issue in this field. In this study, a local binary pattern Silhouettes coefficient variant (LBPSCV) is proposed to segment industrial smoke images. The variant of Silhouettes coefficient was used as the weight when calculating the local binary pattern (LBP) feature vector in the LBPSCV. The algorithm overcame the shortcoming that the texture information described by LBP lacks local contrast information, making the extracted texture features more easily to be distinguished between smoke and non-smoke images. Smoke emission monitoring videos with different characteristics have been used in experiments, such as smoke emission videos with low light, multiple chimney exhaust, multi-colour smoke etc. The results show that the proposed method has higher detection accuracy and a lower false-positive rate.

The mitral valve orifice area is a reliable measure for evaluating mitral valve stenosis (MS) severity, which is obtained by the planimetry of the mid-diastole frame in the echocardiography sequences. Since the manual method for determining this frame is time-consuming and user-dependent, a novel automatic method has been proposed in this study. First, the region of interest (ROI) containing the mitral valve orifice region is detected using circular Hough transform and k-means algorithms. Then, the dimension reduction method is applied to the ROI of each frame to map it into a point in a 2D space. The performance of the local linear embedding (LLE), isometric mapping, kernel principal component analysis (PCA), and linear PCA algorithms has been evaluated in this study. Finally, a distance curve is obtained by calculating the Euclidean distance between consecutive points in 2D space, and the mid-diastole frame is determined by interpreting this curve. The proposed algorithm was validated using 2D echocardiography of the 20 MS patients. Finally, the LLE method showed the best result, and the average frame difference for 20 cases using the proposed method compared with the gold standard (the echo-cardiologist opinion) was 1.40.

Multi-region segmentation plays a major role in numerous medical diagnostics especially brain tumour identification and classification in Magnetic Resonance Imaging (MRI). Brain tumour segmentation is used in medical field for early diagnostics and detection of tumour. The main goal of this work is to improve the performance of detection by using grid based techniques with Weighted Bee Swarm Intelligence and K-means clustering. This technique is more effective due to hybrid combination of segmentation and optimisation as it seems to possess specific tasks of image information and detection to obtain a detailed and accurate image analysis. Grid based segmentation balance overall computation time and reduces complexity. Weighted Bee Swarm Optimisation is used to optimise segmentation parameters to get maximum performance. The various informative regions such as cerebrospinal fluid, grey matter, white matter are segmented by using proposed algorithm which will be most useful to study and characterise the tumour. The experimental outcomes show that the proposed strategy enhances performance measures in terms of sensitivity and specificity analysis. The performance of this technique is also improved by a factor of 1.5%.

In the case of the glass tube for pharmaceutical applications, high-quality defect detection is made via inspection systems based on image processing. Such processing must be fast enough to guarantee real-time inspection and to meet the increasing rate and quality required by the market. Defect detection is complex due to specific problems of the production process: vibration, rotation and irregularity of the tube. All these aspects prevent the efficient use of known techniques. The authors present an algorithm that decreases the processing time of the defect detection phase. The algorithm is based on a moving average filter working at row level, that allows to minimize the effects of rotation, vibration, and irregularity of the tube. Luminosity variations due to the tube curvature are cut by the filter and a threshold algorithm can be applied. They made the evaluation considering different solutions taken from literature. The algorithm outperforms, in processing time, all these solutions with increased accuracy. Experimental measures show that the algorithm achieves a throughput gain of 2.6 times with respect to Canny. They develop also a methodology to get the best values for the algorithm parameters directly at the factory, during the change of production batches.

Molecular-docking is an essential tool in the drug designing process, where a small molecule ligand (drug) binds with disease-causing protein molecule to prevent its further activity. Docking process helps in predicting the most appropriate configuration and the optimal interaction energy between the interacting molecules (ligand and protein) to form a stable complex. Based on this idea, a new learning-based single image super-resolution reconstruction (LSI-SRR) method is proposed here. Estimation of a high resolution (HR) patch is achieved by optimising the interaction energy between the input low resolution patch and its corresponding candidate patches appropriately chosen from the training image dataset via Genetic algorithm. Structured-spatiogram based measure; a new and competent similarity criterion is proposed to select potentially efficient training images which encompass better statistical and structural co-relation with the input image. The proposed method is tested on synthetic and real-time images at different magnification factors. Performance analysis of the proposed work is compared with some of the representative state-of-the-art LSI-SRR methods. Experimental results demonstrate that the proposed method produces HR images with enhanced image details, minimal artefacts and most importantly enables an efficient trade-off between the image qualities to speed than the competing methods.

ImageJ is an open-source application widely used for image processing. It has developer API that can be used to implement new plugins for specific image processing tasks. However, ImageJ wasn't designed to work on distributed systems. Currently, it is still being used on single machines to process large medical images, which takes several hours to complete. In this article, we present the approaches to make several essential and widely used ImageJ plugins to work in a cluster. As the cluster nodes parallelly run the existing plugins for image processing, they write the results on a shared drive. But one of the main challenges is, merging those results with high accuracy. Several ImageJ plugins were developed to distribute tasks and generate combined results efficiently. The existing 3D-Object-Counter plugin was used for testing the designed system. The experimental results on the test images of 3D objects stored in Tagged Image File Format(TIFF) show faster processing time with high accuracy and similarity compared to the single machine-based results. The image processing time depends on the number of nodes in the cluster. So, we present a mathematical model that determines the cluster size automatically for optimizing the overall image processing time.

This study explores the use of point clouds for both representation and genetic morphogenesis of complex geometry. The accurate representation of existing objects of complex curved geometry, which are subsequently geometrically modified by evolutionary morphogenetic processes, is analysed. To this end, as a method of representation and generation of complex geometries, a point-based genetic algorithm and the use of large unstructured point clouds are proposed. A study of convergence and diversity of the implemented algorithm is detailed, as well as a comparison with the Coyote optimisation algorithm in terms of representation error demonstrating its efficiency. Some commonly used three-dimensional formats in architecture, such as NURBS and polygon meshes, are analysed, and compared against point clouds. This study also includes an evaluation regarding whether the use of point clouds is a more suitable format for realistic representation, rationalisation and genetic morphogenesis.