Capsule-Based Regression Tracking via Background Inpainting.

Background cues play an accompanying role in most regression trackers, where they directly learn a mapping from dense sampling to soft label by giving a search area. In essence, the trackers need to identify a large amount of background information (i.e., other objects and distractor objects) under the circumstance of extreme target-background data imbalance. Therefore, we believe that it is more worth performing regression tracking depending on the informative background cues and using target cues as supplementary. To do this, we propose a capsule-based approach, referred to as CapsuleBI, which performs regression tracking based on a background inpainting network and a target-aware network. The background inpainting network explores the background representations by restoring the region of the target with all available scenes, and a target-aware network captures the target representations by focusing on the target itself only. To explore the subjects/distractors in the whole scene, we propose a global-guided feature construction module, which helps enhance the local features with global information. Both the background and target are encoded in capsules, which can model the relationships between objects or object parts in the background scene. Apart from this, the target-aware network assists the background inpainting network with a novel background-target routing algorithm that guides the background and target capsules to estimate the target location with multi-video relationships information precisely. Extensive experimental results show that the proposed tracker achieves favorably against state-of-the-art methods.

Latent Space Semantic Supervision Based on Knowledge Distillation for Cross-Modal Retrieval.

As an important field in information retrieval, fine-grained cross-modal retrieval has received great attentions from researchers. Existing fine-grained cross-modal retrieval methods made several improvements in capturing the fine-grained interplay between vision and language, failing to consider the fine-grained correspondences between the features in the image latent space and the text latent space respectively, which may lead to inaccurate inference of intra-modal relations or false alignment of cross-modal information. Considering that object detection can get the fine-grained correspondences of image region features and the corresponding semantic features, this paper proposed a novel latent space semantic supervision model based on knowledge distillation (L3S-KD), which trains classifiers supervised by the fine-grained correspondences obtained from an object detection model by using knowledge distillation for image latent space fine-grained alignment, and by the labels of objects and attributes for text latent space fine-grained alignment. Compared with existing fine-grained correspondence matching methods, L3S-KD can learn more accurate semantic similarities for local fragments in image-text pairs. Extensive experiments on MS-COCO and Flickr30K datasets demonstrate that the L3S-KD model consistently outperforms state-of-the-art methods for image-text matching.

Scene Text Detection and Segmentation based on Cascaded Convolution Neural Networks.

Scene text detection and segmentation are two important and challenging research problems in the field of computer vision. This paper proposes a novel method for scene text detection and segmentation based on cascaded convolution neural networks (CNNs). In this method, a CNN based text-aware candidate text region (CTR) extraction model (named detection network, DNet) is designed and trained using both the edges and the whole regions of text, with which coarse CTRs are detected. A CNN based CTR refinement model (named segmentation network, SNet) is then constructed to precisely segment the coarse CTRs into text to get the refined CTRs. With DNet and SNet, much fewer CTRs are extracted than with traditional approaches while more true text regions are kept. The refined CTRs are finally classified using a CNN based CTR classification model (named classification network, CNet) to get the final text regions. All of these CNN based models are modified from VGGNet-16. Extensive experiments on three benchmark datasets demonstrate that the proposed method achieves state-of-the-art performance and greatly outperforms other scene text detection and segmentation approaches.

Automated layer segmentation of macular OCT images via graph-based SLIC superpixels and manifold ranking approach.

Using the graph-based a simple linear iterative clustering (SLIC) superpixels and manifold ranking technology, a novel automated intra-retinal layer segmentation method is proposed in this paper. Eleven boundaries of ten retinal layers in optical coherence tomography (OCT) images are exactly, fast and reliably quantified. Instead of considering the intensity or gradient features of the single-pixel in most existing segmentation methods, the proposed method focuses on the superpixels and the connected components-based image cues. The image is represented as some weighted graphs with superpixels or connected components as nodes. Each node is ranked with the gradient and spatial distance cues via graph-based Dijkstra's method or manifold ranking. So that it can effectively overcome speckle noise, organic texture and blood vessel artifacts issues. Segmentation is carried out in a three-stage scheme to extract eleven boundaries efficiently. The segmentation algorithm is validated on 2D and 3D OCT images in three databases, and is compared with the manual tracings of two independent observers. It demonstrates promising results in term of the mean unsigned boundaries errors, the mean signed boundaries errors, and layers thickness errors.

Retinal Microaneurysms Detection Using Gradient Vector Analysis and Class Imbalance Classification.

Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification, which is composed of two stages, i.e. candidate MAs extraction and classification. In the first stage, a candidate MAs extraction algorithm is devised by analyzing the gradient field of the image, in which a multi-scale log condition number map is computed based on the gradient vectors for vessel removal, and then the candidate MAs are localized according to the second order directional derivatives computed in different directions. Due to the complexity of fundus image, besides a small number of true MAs, there are also a large amount of non-MAs in the extracted candidates. Classifying the true MAs and the non-MAs is an extremely class imbalanced classification problem. Therefore, in the second stage, several types of features including geometry, contrast, intensity, edge, texture, region descriptors and other features are extracted from the candidate MAs and a class imbalance classifier, i.e., RUSBoost, is trained for the MAs classification. With the Retinopathy Online Challenge (ROC) criterion, the proposed method achieves an average sensitivity of 0.433 at 1/8, 1/4, 1/2, 1, 2, 4 and 8 false positives per image on the ROC database, which is comparable with the state-of-the-art approaches, and 0.321 on the DiaRetDB1 V2.1 database, which outperforms the state-of-the-art approaches.

Deformed Palmprint Matching Based on Stable Regions.

Palmprint recognition (PR) is an effective technology for personal recognition. A main problem, which deteriorates the performance of PR, is the deformations of palmprint images. This problem becomes more severe on contactless occasions, in which images are acquired without any guiding mechanisms, and hence critically limits the applications of PR. To solve the deformation problems, in this paper, a model for non-linearly deformed palmprint matching is derived by approximating non-linear deformed palmprint images with piecewise-linear deformed stable regions. Based on this model, a novel approach for deformed palmprint matching, named key point-based block growing (KPBG), is proposed. In KPBG, an iterative M-estimator sample consensus algorithm based on scale invariant feature transform features is devised to compute piecewise-linear transformations to approximate the non-linear deformations of palmprints, and then, the stable regions complying with the linear transformations are decided using a block growing algorithm. Palmprint feature extraction and matching are performed over these stable regions to compute matching scores for decision. Experiments on several public palmprint databases show that the proposed models and the KPBG approach can effectively solve the deformation problem in palmprint verification and outperform the state-of-the-art methods.

Retinal vessel segmentation: an efficient graph cut approach with retinex and local phase.

Our application concerns the automated detection of vessels in retinal images to improve understanding of the disease mechanism, diagnosis and treatment of retinal and a number of systemic diseases. We propose a new framework for segmenting retinal vasculatures with much improved accuracy and efficiency. The proposed framework consists of three technical components: Retinex-based image inhomogeneity correction, local phase-based vessel enhancement and graph cut-based active contour segmentation. These procedures are applied in the following order. Underpinned by the Retinex theory, the inhomogeneity correction step aims to address challenges presented by the image intensity inhomogeneities, and the relatively low contrast of thin vessels compared to the background. The local phase enhancement technique is employed to enhance vessels for its superiority in preserving the vessel edges. The graph cut-based active contour method is used for its efficiency and effectiveness in segmenting the vessels from the enhanced images using the local phase filter. We have demonstrated its performance by applying it to four public retinal image datasets (3 datasets of color fundus photography and 1 of fluorescein angiography). Statistical analysis demonstrates that each component of the framework can provide the level of performance expected. The proposed framework is compared with widely used unsupervised and supervised methods, showing that the overall framework outperforms its competitors. For example, the achieved sensitivity (0:744), specificity (0:978) and accuracy (0:953) for the DRIVE dataset are very close to those of the manual annotations obtained by the second observer.

Palm vein verification using multiple features and locality preserving projections.

Biometrics is defined as identifying people by their physiological characteristic, such as iris pattern, fingerprint, and face, or by some aspects of their behavior, such as voice, signature, and gesture. Considerable attention has been drawn on these issues during the last several decades. And many biometric systems for commercial applications have been successfully developed. Recently, the vein pattern biometric becomes increasingly attractive for its uniqueness, stability, and noninvasiveness. A vein pattern is the physical distribution structure of the blood vessels underneath a person's skin. The palm vein pattern is very ganglion and it shows a huge number of vessels. The attitude of the palm vein vessels stays in the same location for the whole life and its pattern is definitely unique. In our work, the matching filter method is proposed for the palm vein image enhancement. New palm vein features extraction methods, global feature extracted based on wavelet coefficients and locality preserving projections (WLPP), and local feature based on local binary pattern variance and locality preserving projections (LBPV_LPP) have been proposed. Finally, the nearest neighbour matching method has been proposed that verified the test palm vein images. The experimental result shows that the EER to the proposed method is 0.1378%.

Evaluation of crowded optic nerve head and small scleral canal in intrapapillary hemorrhage with adjacent peripapillary subretinal hemorrhage.

BACKGROUND: Intrapapillary hemorrhage with adjacent peripapillary subretinal hemorrhage (IHAPSH) is a clinical syndrome most commonly affecting myopic eyes with tilted discs that usually resolves spontaneously without treatment. Subretinal hemorrhage usually occurs peripapillary on the nasally adjacent side near the optic disc. The etiology of this condition is still unknown. The purpose of this study was to determine if a crowded optic nerve head and small scleral canal are involved in the pathogenetic mechanisms of IHAPSH. METHODS: Twelve subjects with IHAPSH diagnosed at the Affiliated Ophthalmology Hospital of the First Clinical College of Harbin Medical University and 24 control subjects were examined. The size of the inner aspect of the scleral canal and level of nerve fiber crowding of the optic nerve head were analyzed with optic nerve head analysis software packet of the Stratus Optical Coherence Tomography software and manual segmentation software. The Mann-Whitney U test and multiple comparisons (with the Bonferroni correction method) were performed. p values less than 0.002 (two-sided) were considered statistically significant. The area, perimeter, and the perimeter/area ratio of the optic disc, vertical and horizontal diameter of the inner aspect of the scleral canal, vertical integrated rim area (VIRA), and the rim area were calculated. RESULTS: The area and perimeter of the optic disc and the horizontal diameter of the inner aspect of the scleral canal were significantly lower in the affected and contralateral eyes of the subjects with IHAPSH than in the eyes of the controls. Conversely, the IHAPSH-affected and contralateral eyes had significantly higher perimeter/area ratio of the optic disc, VIRA, and rim area values than the control eyes. The VIRA and rim area were greater in the IHAPSH-affected eyes than in the contralateral eyes. CONCLUSIONS: Patients with IHAPSH have smaller optic discs and scleral canals than control subjects, with a higher level of nerve fiber crowding.

Retinopathy online challenge: automatic detection of microaneurysms in digital color fundus photographs.

The detection of microaneurysms in digital color fundus photographs is a critical first step in automated screening for diabetic retinopathy (DR), a common complication of diabetes. To accomplish this detection numerous methods have been published in the past but none of these was compared with each other on the same data. In this work we present the results of the first international microaneurysm detection competition, organized in the context of the Retinopathy Online Challenge (ROC), a multiyear online competition for various aspects of DR detection. For this competition, we compare the results of five different methods, produced by five different teams of researchers on the same set of data. The evaluation was performed in a uniform manner using an algorithm presented in this work. The set of data used for the competition consisted of 50 training images with available reference standard and 50 test images where the reference standard was withheld by the organizers (M. Niemeijer, B. van Ginneken, and M. D. Abràmoff). The results obtained on the test data was submitted through a website after which standardized evaluation software was used to determine the performance of each of the methods. A human expert detected microaneurysms in the test set to allow comparison with the performance of the automatic methods. The overall results show that microaneurysm detection is a challenging task for both the automatic methods as well as the human expert. There is room for improvement as the best performing system does not reach the performance of the human expert. The data associated with the ROC microaneurysm detection competition will remain publicly available and the website will continue accepting submissions.

[Recent progress in molecular genetics and gene therapy for retinitis pigmentosa].

Retinitis pigmentosa (RP) is a common genetic eye disease affecting about 1 in 3500 people worldwide with pan-ethnic occurrence. So far there is no effective treatment for RP. This paper gives an overview on recent advances in molecular genetics of RP with emphasis on the important gene mutations for diagnosis and prognosis, and a review on gene therapy of RP.

Pathogenic mutations of the lipoprotein lipase gene in Chinese patients with hypertriglyceridemic type 2 diabetes.

Elevated plasma triglyceride and nonesterified fatty acid concentrations may cause insulin resistance. Lipoprotein lipase (LPL) is a rate-determining enzyme in lipid metabolism. To investigate the role of the LPL gene in Chinese patients with hypertriglyceridemic type 2 diabetes, 277 patients with type 2 diabetes and 241 healthy control subjects were recruited and screened for sequence changes in the LPL gene by PCR, SSCP, restriction analysis and direct DNA sequencing. Ten mutations were identified: four missense mutations, Ala71Thr, Val181Ile, Gly188Glu and Glu242Lys; one nonsense mutation Ser447Ter; and five silent mutations. Ser447Ter was found in both patients and controls with no significant difference in frequency. The four missense mutations were located in the highly conserved exon 3, 5, and 6 regions and in highly conserved amino acid sites. They led to reduced LPL mass and enzyme activities in both post-heparin plasma and in vitro expression. The modeled structures displayed major differences between the mutant and wildtype molecules. These results indicated that the four missense mutations lead to LPL deficiency and subsequent hypertriglyceridemia. Based on our study and published data, a putative pathogenic pathway was suggested: LPL enzyme deficiency causes elevated plasma triglyceride level and subsequent insulin resistance; both increased free fatty acids and insulin resistance promote gluconeogenesis and hyperglycaemia, a vicious circle leading to type 2 diabetes.

Novel mitochondrial 16S rRNA mutation, 3200T-->C, associated with adult-onset type 2 diabetes.

OBJECTIVE: To investigate the role of a potential diabetes-related mitochondrial region, which includes two previously reported mutations, 3243A-->G and 3316G-->A, in Chinese patients with adult-onset type 2 diabetes. METHODS: A total of 277 patients and 241 normal subjects were recruited for the study. Mitochondrial nt 3116 - 3353, which spans the 16S rRNA, tRNA(leu(UUR)) and the NADH dehydrogenase 1 gene, were detected using polymerase chain reaction (PCR), direct DNA sequencing, PCR-restriction fragment length polymorphism and allele-specific PCR. Variants were analyzed by two-tailed Fisher exact test. The function of the variants in 16S rRNA were predicted for minimal free energy secondary structures by RNA folding software mfold version 3. RESULTS: Four homoplasmic nucleotide substitutions were observed, 3200T-->C, 3206C-->T, 3290T-->C and 3316G-->A. Only the 3200T-->C mutation is present in the diabetic population and absent in the control population. No statistically significant associations were found between the other three variants and type 2 diabetes. The 3200T-->C and 3206C-->T nucleotide substitutions located in 16S rRNA are novel variants. The 3200T-->C caused a great alteration in the minimal free energy secondary structure model while the 3206C-->T altered normal 16S rRNA structure little. CONCLUSIONS: The results suggest that the 3200T-->C mutation is linked to the development of type 2 diabetes, but that the other observed mutations are neutral. In contrast to the Japanese studies, the 3316G-->A does not appear to be related to type 2 diabetes.