In India, cervical cancer is the second most common type of cancer in females. Pap smear is a simple cytology test for the detection of cancer in its early stages. To obtain the best results from the Pap smear, expert pathologist are required. Availability of pathologist in India is far below the required numbers, especially in rural parts. In this paper, multiple texture-based features are introduced for the extraction of relevant and informative features from single-cell images. First-order histogram, GLCM, LBP, Laws, and DWT are used for texture feature extraction. These methods help to recognise the contour of the nucleus and cytoplasm. ANN and SVM are used to classify the single-cell images either normal or cancerous based on the trained features. ANN and SVM are used on every single feature as well as on the combination of all features. Best results are obtained with a combination of all features. The system is evaluated on generated dataset MNITJ, containing 330 single cervical cell images and also on publicly available benchmark Herlev data set. Experimental results show that the proposed texture-based features give significantly better results in cervical cancer detection when compared with state of the art shape-based features regarding accuracy.

Considering the importance of early diagnosis of breast cancer, a supervised patch-wise texton-based approach has been developed for the classification of mass abnormalities in mammograms. The proposed method is based on texture-based classification of masses in mammograms and does not require segmentation of the mass region. In this approach, patches from filter bank responses are utilised for generating the texton dictionary. The methodology is evaluated on the publicly available Digital Database for Screening Mammography database. Using a naive Bayes classifier, a classification accuracy of 83% with an area under the receiver operating characteristic curve of 0.89 was obtained. Experimental results demonstrated that the patch-wise texton-based approach in conjunction with the naive Bayes classifier constructs an efficient and alternative approach for automatic mammographic mass classification.

Automated segmentation of tumors in breast ultrasound (US) images is challenging due to poor image quality, presence of speckle noise, shadowing effects and acoustic enhancement. This paper improves the multi-scale Gaussian kernel induced fuzzy C-means clustering method with spatial bias correction (MsGKFCM_S). Furthermore, it presents a hybrid segmentation method, using both the features of the MsGKFCM_S clustering and active contour driven by a region-scalable fitting energy function. The result obtained from the MsGKFCM_S method is utilised to initialise the contour that spreads to identify the estimated regions. It also helps to estimate the several controlling parameters of the curve evolution process. The proposed approach is evaluated on a database of 127 breast US images consisting of 75 malignant and 52 solid benign cases. The performance of proposed approach is compared with other related techniques, using performance measures such as Jaccard Index, dice similarity, shape similarity, Hausdroff difference, area difference, accuracy and F-measure. Results indicate that the proposed approach can successfully detect lesions in breast US images, with high accuracy of 97.889 and 97.513%. Moreover, the proposed approach has the capability of handling shadowing effects, acoustic enhancement and multiple lesions.

Hepatocellular carcinoma, the primary liver cancer and other liver-related pathologies are diagnosed with the help of contrast enhanced computed tomography (CECT) images. The CECT imaging technology is claimed to be an invasive technique, as the intravenous contrast agent injected prior to computed tomography (CT) acquisition is harmful and is not advised for patients with pre-existing diabetes and kidney disorders. This study presents a novel enhancement technique for the diagnosis of liver lesions from unenhanced CT images by means of fuzzy histogram equalisation in the non-sub-sampled contourlet transform domain followed by decorrelation stretching. The enhanced images obtained in this study substantiate that the proposed method improves the diagnostic value from the unenhanced CT images thereby providing an alternate painless solution for CT acquisition for the subset of patients mentioned above. Another major highlight of this work is the characterisation of lesions from the enhanced output for five different classes of pathology. The obtained results presented in this study demonstrate the potency of the proposed enhancement technique in achieving an appreciable performance in lesion characterisation. The images used for this research study have been obtained from Jawaharlal Institute of Medical Education and Research Puducherry, India.

Skin cancer is the most common type of cancer in the world and the incidents of skin cancer have been rising over the past decade. Even with a dermoscopic imaging system, which magnifies the lesion region, detecting and classifying skin lesions by visual examination is laborious due to the complex structures of the lesions. This necessitates the need for an automated skin lesion diagnosis system to enhance the diagnostic capability of dermatologists. In this study, the authors propose an automatic skin lesion segmentation method which can be used as a preliminary step for lesion classification. The proposed method comprises two major steps, namely preprocessing and segmentation. In the preprocessing step, noise such as illumination, hair and rulers are removed using filtering techniques and in the segmentation phase, skin lesions are segmented using the GrabCut segmentation algorithm. The k-means clustering algorithm is then used along with the colour features learnt from the training images to improve the boundaries of the segments. To evaluate the authors’ proposed method, they have used ISIC 2017 challenge dataset and dataset. They have obtained Dice coefficient values of 0.8236 and 0.9139 for ISIC 2017 test dataset and dataset, respectively.

Of all the skin cancer that is prevalent, melanoma has the highest mortality rates. Melanoma becomes life threatening when it penetrates deep into the dermis layer unless detected at an early stage, it becomes fatal since it has a tendency to migrate to other parts of our body. This study presents an automated non-invasive methodology to assist the clinicians and dermatologists for detection of melanoma. Unlike conventional computational methods which require (expensive) domain expertise for segmentation and hand crafted feature computation and/or selection, a deep convolutional neural network-based regularised discriminant learning framework which extracts low-dimensional discriminative features for melanoma detection is proposed. Their approach minimises the whole of within-class variance information and maximises the total class variance information. The importance of various subspaces arising in the within-class scatter matrix followed by dimensionality reduction using total class variance information is analysed for melanoma detection. Experimental results on ISBI 2016, MED-NODE, PH2 and the recent ISBI 2017 databases show the efficacy of their proposed approach as compared to other state-of-the-art methodologies.

The authors propose a novel deep learning model for classifying medical images in the setting where there is a large amount of unlabelled medical data available, but the amount of labelled data is limited. They consider the specific case of classifying skin lesions as either benign or malignant. In this setting, the authors’ proposed approach – the semi-supervised, denoising adversarial autoencoder – is able to utilise vast amounts of unlabelled data to learn a representation for skin lesions, and small amounts of labelled data to assign class labels based on the learned representation. They perform an ablation study to analyse the contributions of both the adversarial and denoising components and compare their work with state-of-the-art results. They find that their model yields superior classification performance, especially when evaluating their model at high sensitivity values.

Common non-destructive material testing technology has some well-known problems such as slow detection, low detection accuracy, and low level of information obtained. To solve these problems, this study applied recent advances in convolution neural networks to propose an effective deep learning network using casting datasets. The approach achieves non-destructive material testing with automatic, intelligent detection technology. For most existing deep learning networks, an image is eventually transformed into a multidimensional visual feature vector for comparison and classification. However, such vectors may not optimally improve detection precision and speed, and can lead to significant storage problems. A deep hashing network is proposed in which images are mapped into compact binary codes. There are three key components: (i) a sub-network with multiple convolution-pooling layers to capture image representations; (ii) a hashing layer to generate compact binary hash codes; (iii) an encoder module to divide the image feature vector from the output of the sub-network above into multiple branches, each encoded into one hash bit. Extensive experiments using a casting dataset show promising performance compared with the state-of-the-art approach.

Recent advances in large-scale image and video analysis have empowered the potential capabilities of visual surveillance systems. In particular, deep learning-based approaches bring in substantial benefits in solving certain computer vision problems such as fine-grained object recognition. Here, the authors mainly concentrate on classification and identification of maritime vessels and land vehicles, which are the key constituents of visual surveillance systems. Employing publicly available data sets for maritime vessels and land vehicles, the authors aim to improve visual recognition. Specifically, the authors focus on five tasks regarding visual recognition; coarse-grained classification, fine-grained classification, coarse-grained retrieval, fine-grained retrieval, and verification. To increase the performance in these tasks, the authors utilise a multi-task learning framework and present a novel loss function which simultaneously considers deep feature learning and classification by exploiting the available hierarchical labels of individual samples and the global statistics of distances between the data pairs. The authors observe that the proposed multi-task learning model improves the fine-grained recognition performance on MARVEL and Stanford Cars data sets, compared to training of a model targeting a single recognition task.

Falls sustained by subjects can have severe consequences, especially for elderly persons living alone. A fall detection method for indoor environments based on the Kinect sensor and analysis of three-dimensional skeleton joints information is proposed. Compared with state-of-the-art methods, the authors’ method provides two major improvements. First, possible fall activity is quantified and represented by a one-dimensional float array with only 32 items, followed by fall recognition using a support vector machine (SVM). Unlike typical deep learning methods, the input parameters of their method are dramatically reduced. Hence, videos are trained and recognised by an SVM with a low time cost. Second, the torso angle is imported to detect the start key frame of a possible fall, which is much more efficient than using a sliding window. Their approach is evaluated on the telecommunication systems team (TST) fall detection dataset v2. The results show that their approach achieves an accuracy of 92.05%, better than other typical methods. According to the characters of machine learning, when more samples are imported, their method is expected to achieve a higher accuracy and stronger capability of fall-like discrimination. It can be used in real-time video surveillance because of its time efficiency and robustness.

The task of visual question answering (VQA) has gained wide popularity in recent times. Effectively solving the VQA task requires the understanding of both the visual content in the image and the language information associated with the text-based question. In this study, the authors propose a novel method of encoding the visual information (categorical and spatial object information) of all the objects present in the image into a sequential format, which is called an object sequence. These object sequences can then be suitably processed by a neural network. They experiment with multiple techniques for obtaining a joint embedding from the visual features (in the form of object sequences) and language-based features obtained from the question. They also provide a detailed analysis on the performance of a neural network architecture using object sequences, on the Oracle task of GuessWhat dataset (a Yes/No VQA task) and benchmark it against the baseline.

In recent years, palmprint recognition has made great progress and many methods have been put forward. The extraction of robust orientation features and finding efficient matching strategies are two key points for palmprint recognition. Traditional coding methods usually only use a dominant filter response to extract orientation features of palmprint images while not taking into account the other useful filter responses. Without increasing the number of filers, this study presents a modified Competitive Code to extract orientation features more accurately, which makes use of the relation between the filter responses. Besides, a distinctive extended eight-pixel neighbourhood method is proposed to select the sample points for matching by extracting the local features. At the matching stage, an effective fusion matching scheme with a double-layer image pyramid is designed to calculate the similarity between two palmprint images. Extensive experiments on four types of public palmprint databases show that the proposed method has excellent performance compared with the other state-of-the-art algorithms.

Background subtraction has been a fundamental task in video analytics and smart surveillance applications. In the field of background subtraction, Gaussian mixture model is a canonical model for many other methods. However, the unconscious learning of this model often leads to erroneous motion detection under high variation scenes. This article proposes a new method that incorporates entropy estimation and a removal framework into the Gaussian mixture model to improve the performance of background subtraction. Firstly, entropy information is computed for each pixel of a frame to classify frames into silent or high variation categories. Secondly, the removal framework is used to determine which frames from the background subtraction process are updated. The proposed method produces precise results with fast execution time, which are two critical factors in surveillance systems for more advanced tasks. The authors used two publicly available test sequences from the 2014 Change Detection and Scene background modelling data sets and internally collected data sets of scenes with dense traffic.

Scene parsing is a very challenging work for complex and diverse scenes. In this study, the authors address the problem of semantic segmentation of indoor scenes for red, green, blue-depth (RGB-D) images. Most existing works use only the colour or photometric information for this problem. Here, they present an approach to fusing feature maps between colour network branch and depth network branch to integrate the photometric information and geometric information, which improves the semantic segmentation performance. They propose a novel convolutional neural network that uses ResNet as a baseline network. Their proposed network adopts a spatial pyramid pooling module to make full use of different sub-region representations. Their proposed network also adopts multiple feature maps fusion modules to integrate texture and structure information between the colour branch and depth branch. Moreover, their proposed network has multiple auxiliary loss branches together with the main loss function to prevent the gradient of frontal layers disappear and accelerate the training phase of the fusion part. Comprehensive experimental evaluations show that their proposed network ‘ResFusion’ improves the performance greatly over the baseline network and has achieved competitive performance compared with other state-of-the-art methods on the challenging SUN RGB-D benchmark.

In this study, a novel multi-layer fused convolution neural network (MLF-CNN) is proposed for detecting pedestrians under adverse illumination conditions. Currently, most existing pedestrian detectors are very likely to be stuck under adverse illumination circumstances such as shadows, overexposure, or nighttime. To detect pedestrians under such conditions, the authors apply deep learning for effective fusion of the visible and thermal information in multispectral images. The MLF-CNN consists of a proposal generation stage and a detection stage. In the first stage, they design an MLF region proposal network and propose to use summation fusion method for integration of the two convolutional layers. This combination can detect pedestrians in different scales, even in adverse illumination. Furthermore, instead of extracting features from a single layer, they extract features from three feature maps and match the scale using the fused ROI pooling layers. This new multiple-layer fusion technique can significantly reduce the detection miss rate. Extensive evaluations of several challenging datasets well demonstrate that their approach achieves state-of-the-art performance. For example, their method performs 28.62% better than the baseline method and 11.35% better than the well-known faster R-CNN halfway fusion method in detection accuracy on KAIST multispectral pedestrian dataset.

Circle detection has numerous applications towards industry, robotics, and science in general. Therefore, a significant effort has been made in order to develop an accurate and fast method for circle extraction. Commonly, different techniques such as the ones based on the Hough transform have been widely used because of their robustness. However, these techniques usually demand a considerable computational load and large storage, and therefore meta-heuristic approaches such as evolutionary and swarm-based algorithms have been studied as an alternative. This study introduces a circle-detection method based on a recently proposed meta-heuristic technique: the teaching learning based optimisation algorithm, which is a population-based technique that is inspired by the teaching and learning processes. The algorithm uses the encoding of three points as candidate circles over the edge image. To evaluate if such candidate circles are actually present within the edge map, an objective function is used to guide the search. To validate the efficacy of the proposed approach, several tests using noisy and complex images as input were carried out, and the results were compared with different approaches for circle detection.

Discriminative tracking methods can achieve state-of-the-art performance by considering tracking as a classification problem tackled with both object and background information. As a high efficient discriminative tracker, compressive tracking (CT) has attracted much attention recently. However, it may easily fail when the object suffers from long-term occlusions, and severe appearance and illumination changes. To address these issues, the authors develop a robust tracking framework based on CT by considering balanced feature representation as well as dual-mode classifier construction. First, the original measurement matrix of CT works as a dominated texture feature extractor. To obtain a balanced feature representation, they propose to induce a complementary measurement matrix by considering both texture and colour features. Then, they develop two classifiers (dual mode) by using previous and current sample sets, respectively, and subsequently combine them into one ensemble classifier to track the target, which can help to avoid tracking failure suffering from severe appearance changes and long term occlusion. Moreover, they propose a classifier updating schema to prevent the inclusion of unsatisfied positive samples by predicting the occlusions with their ensemble classifier. The extensive experiments demonstrate the superior performance of their tracking framework under various situations.

Tracking of moving objects in video sequences is an important research problem because of its many industrial, biomedical, and security applications. Significant progress has been made on this topic in the last few decades. However, the ability to track objects accurately in video sequences that have challenging conditions and unexpected events, e.g. background motion and shadows; objects with different sizes and contrasts; a sudden change in illumination; partial object camouflage; and low signal-to-noise ratio, remains an important research problem. To address such difficulties, the authors developed a robust multiscale visual tracker that represents a captured video frame as different subbands in the wavelet domain. It then applies N independent particle filters to a small subset of these subbands, where the choice of this subset of wavelet subbands changes with each captured frame. Finally, it fuses the outputs of these N independent particle filters to obtain final position tracks of multiple moving objects in the video sequence. To demonstrate the robustness of their multiscale visual tracker, they applied it to four example videos that exhibit different challenges. Compared to a standard full-resolution particle filter-based tracker and a single wavelet subband (LL)₂-based tracker, their multiscale tracker demonstrates significantly better tracking performance.

This study proposes progressive unsupervised co-learning for unsupervised person re-identification by introducing a co-training strategy in an iterative training process. The authors’ method adopts an iterative training process to improve transferred models by iterating among clustering, selection, exchange, and fine-tuning. To solve the problem of transferring representations learned from multiple source datasets, their method utilises multiple convolutional neural network (CNN) models trained on different labelled source datasets by feeding soft labels obtained by clustering on target dataset to each other. The enhanced model can learn more discriminative person representations than the single model trained on multiple datasets. Experimental results on two large-scale benchmark datasets (i.e. DukeMTMC-reID and Market-1501) demonstrate that their method can enhance transferred CNN models by using more source datasets and is competitive to the state-of-the-art methods.