Cataract remains one of the leading causes of blindness and visual impairment worldwide, representing a significant public health concern. Anterior segment optical coherence tomography (AS-OCT) provides high-resolution visualization of ocular structures and has become a key imaging modality for nuclear cataract (NC) grading. However, existing convolutional neural network (CNN)-based methods often struggle to differentiate subtle variations between adjacent severity levels due to limited capacity for capturing long-range dependencies, thereby affecting classification accuracy. To address this challenge, we propose an automatic nuclear cataract grading network based on the Mamba architecture. This framework combines the local feature extraction capabilities of traditional CNNs with the long-range dependency modeling power of Mamba modules. Furthermore, we introduce a Hybrid Wavelet Feature Refinement Module (HWFRM), which employs wavelet transforms to extract multi-frequency representations. Integrated with a detail-guided enhancement mechanism, the module adaptively strengthens discriminative features. Channel and spatial attention mechanisms are applied to each wavelet sub-band, enabling the network to selectively emphasize important frequency components and remain sensitive to both structural and fine-detail cues. Finally, an ordinal regression loss is incorporated to explicitly model the progressive nature of cataract severity, improving the network’s ability to reduce misclassifications between adjacent categories. Extensive experiments on both a local AS-OCT dataset and a public benchmark demonstrate that our approach achieves state-of-the-art performance.

Accurate segmentation of key anatomical structures in anterior segment OCT (AS-OCT) images is critical for diagnosing serious ophthalmic conditions such as keratitis and cataract. However, due to the scarcity of labeled data in this domain, most existing methods struggle to precisely segment both the lens and the anterior chamber angle simultaneously. To address these limitations, we propose a semi-supervised segmentation framework based on collaborative training between U-Net and Mamba-UNet. A Scale Fusion Module (SFM) is introduced to integrate the outputs of both models, generating multi-scale predictions and fused pseudo-labels. A multi-scale supervision strategy is then employed to guide learning at different levels. Additionally, we design a novel anatomical structure consistency loss that leverages anatomical properties from the fused pseudo-labels to preserve anatomical correctness. Experimental results on two AS-OCT datasets demonstrate the effectiveness and superiority of our proposed approach.

Myocardial infarction remains a global health challenge. Accurate myocardial segmentation in late gadolinium enhancement cardiac magnetic resonance imaging (LGE-CMRI) is critical for diagnosis and treatment planning. Although deep learning architectures have demonstrated excellent segmentation performance in conventional CMRI, their accuracy significantly declines in LGE-CMRI due to low tissue contrast and complex background interference. To address these challenges, we propose a Progressive Multi-scale Vision Transformer (PMVT) for myocardial segmentation in LGE-CMRI, which enhances spatial representation capabilities and improves adaptability in complex scenarios through multi-scale feature fusion and interaction. Specifically, PMVT includes a Multi-scale Progressive Attention Decoder (MPSD) for modeling both long and short-term dependencies, and a Multi-layer Hybrid Context Purification (MHCP) that combines different combinations of four prediction heads for prediction and loss calculation, effectively suppressing background interference. Experiments demonstrate that the proposed PMVT outperforms state-of-the-art (SOTA) models, achieving a Dice score of 89.61% for myocardial segmentation (a 1.56% improvement over the current SOTA). This result highlights its considerable potential for clinical applications in automated LGE-CMRI analysis.

Medical image translation enables the generation of contrast-enhanced CT (CECT) images from non-contrast CT (NCCT) scans, reducing dependence on iodinated contrast agents (ICAs) and minimizing associated health risks. Although diffusion models outperform generative adversarial networks (GANs) in medical image translation, challenges remain in improving sampling speed and restoring anatomical details. To address these issues, we propose a Decoupled Diffusion Model (DDM). Specifically, we first decouple the input image into high-frequency and low-frequency components via discrete wavelet transform (DWT) to enable parallel computing for accelerated sampling. Furthermore, we design a Wavelet UNet (WUNet) to enhance the recovery of anatomical details by leveraging the multi-scale representation capabilities of wavelet transform. Extensive experiments on two clinical datasets, TAP-CT and Coltea-Lung-CT-100W, demonstrate the superior performance of our method, indicating its potential for real-world clinical translation.

Accurate structural segmentation and landmark detection in anterior segment optical coherence tomography (AS-OCT) images are crucial for extracting clinical parameters that guide the diagnosis and treatment of diseases such as glaucoma. However, current mainstream algorithmic paradigms suffer from an inherent limitation: their performance improvements heavily rely on large amounts of high-quality annotations. To overcome this bottleneck, we propose a novel semi-supervised multi-task learning framework. Our framework first incorporates the powerful Segment Anything Model (SAM) image encoder to enhance the model’s general feature extraction capability. To address SAM’s adaptability issues in the medical imaging domain, we design an adaptive feature fusion adapter (AFFA) for targeted fine-tuning, thereby improving its performance on AS-OCT images. Simultaneously, our proposed synergistic feature exchange module (SFEM) enables mutual promotion between the segmentation and detection tasks. Experimental results on a local dataset demonstrate that our proposed method achieves superior performance.

Thyroid nodules are among the most common space-occupying lesions in the endocrine system, making accurate differentiation between benign and malignant cases critical for early diagnosis and treatment. Ultrasound imaging, due to its cost-effectiveness and operational ease, is the primary modality for thyroid nodule screening. The Segment Anything Model (SAM) has recently advanced medical image segmentation through the visual foundation model paradigm, enhanced by large-scale training and domain-specific adapters such as MedSAM and Medical-SAM-Adapter. However, SAM-based methods face key limitations: high computational demands, reliance on precise click-based inputs that misalign with clinical practices, and instability in segmentation quality across interactions. To address these challenges, we propose ThyroSAM, an efficient and robust interactive segmentation framework. ThyroSAM integrates a lightweight EfficientViT encoder with LoRAConv2d for improved generalization, introduces a hybrid prompting mechanism (points, boxes, scribbles, masks) aligned with clinical workflows, and incorporates a confidence-guided iterative correction algorithm to enhance segmentation stability. Experimental results on the TN3K, TG3K, and DTTI thyroid ultrasound datasets demonstrate that ThyroSAM achieves an average Dice coefficient of 88.78% using only ten prompts, surpassing SAMUS by 8.51 percentage points while significantly reducing model size and computational cost. These results underscore ThyroSAM’s potential for deployment in resource-constrained clinical settings.

Aortic dissection (AD) is a life-threatening condition caused by a tear in the aortic intima, allowing blood to enter the vessel wall and form a false lumen. Due to its high mortality rate, timely diagnosis and precise treatment are critical. Clinical diagnosis and treatment of AD rely heavily on accurate 3D vascular image segmentation. To address existing methods’ low segmentation accuracy and insufficient geometric detail preservation, this paper proposes a Transformer-based Dual-Branch Mesh Segmentation Network (TD-MSeg) for AD. This network employs a mesh-based self-attention mechanism to retain vascular geometric details while adopting a dual-branch decoder to effectively fuse features and model long-range dependencies. Specifically, TD-MSeg incorporates three key components: a Hierarchical Mesh Transformer (HMT) module that enhances feature modeling of critical anatomical structures (e.g., intimal tears), a dual-branch decoder that facilitates collaborative optimization of multi-scale local and global features, and a mesh label refinement module that uses a wide-path exploration algorithm to eliminate deformation artifacts and improve spatial label continuity. Moreover, experiments on two AD mesh segmentation datasets demonstrate that the proposed TD-MSeg achieves a 6% improvement in accuracy compared to traditional models and significantly enhances the recognition of complex vascular structures, thereby providing high-precision 3D reconstruction support for endovascular surgical planning.

In cloud storage, symmetric encryption is a common method to protect the confidentiality of volume data. One critical issue in symmetric encryption is the management of volume symmetric keys such as key generation, update and distribution. Many schemes have adopted hierarchical structures based on key derivation to generate and organize the keys. However, the efficient update of these derived and associated keys and the distribution of multiple derived keys have not been well studied. This paper mainly studies in-situ key update and traffic cost of key distribution. First, we redesign the key node structure of our binary key-derivation tree to provide the basis of the in-situ key update. Then, secure in-situ key update algorithms are proposed, in which forward secrecy and backward secrecy are guaranteed. Finally, we propose a minimal key set generation algorithm, which can effectively reduce the communication cost of key distribution. We also describe the key distribution and derivation process. Security analysis and extensive experimental evaluations show the proposed algorithms are secure, efficient and practical.

Crop growth prediction can help agricultural workers to make accurate and reasonable decisions on farming activities. Existing crop growth prediction models focus on one crop and train a single model for each crop. In this article, we develop a ubiquitous growth prediction model for multiple crops, aiming at training a single model for multiple crops. A ubiquitous vision and sensor transformer (ViST) model for crop growth prediction with image and sensor data is developed to achieve the goals. In the proposed model, a cross-attention mechanism is proposed to facilitate the fusion of multimodal feature maps to reduce computational costs and balance the interactive effects among features. To train the model, we combine the data from multiple crops to create a single (ViST) model. A sensor network system is established for data collection on the farm where rice, soybean, and maize are cultivated. Experimental results show that the proposed ViST model has an excellent ubiquitous ability for crop growth prediction with multiple crops.

Choroidal neovascularization (CNV) is a prevalent retinal disease that can result in vision loss and blindness. Therefore, accurate segmentation of CNV is crucial for ophthalmologists to effectively treat patients with CNV. However, due to the complex pathological features of CNV, there exist significant variations in the size and shape of different CNV lesions. As a result, the challenge of segmenting CNV in optical coherence tomography (OCT) images remains unresolved. In this paper, we propose a Graph Convolutional Network with Feature Enhancement (GCFE-Net) for CNV segmentation. Our approach introduces a Graph Attention Module (GAM) on top of the encoder to extract pixel characteristics and enhance the model's space utilization. Additionally, we propose a Dynamic Fusion Module (DFM) in the decoder to address the issue of semantic misalignment when the CNV scale undergoes substantial changes. The effectiveness of the proposed method is demonstrated through experiments conducted on the Cell public dataset.

Optical coherence tomography (OCT) is a widely used ophthalmic imaging technique, and accurate detection of retinal biomarkers in OCT images can help physicians diagnose diseases. However, OCT images are not easy to obtain and are time-consuming and laborious. In addition, the size of biomarkers varies widely. Past deep learning-based methods can hardly solve the above problems well. Thus, to overcome the above challenges, we propose a weakly semi-supervised method called PO-Net for the detection of retinal biomarkers in OCT images. In the proposed method, we utilize a small set containing images with bounding box labels and a large set of weakly annotated images with only one point annotation per biomarker. The training of the net is composed of several steps. In the first step, we use the weakly annotated images to train a point-to-box regression network. In the second step, the point-annotated images are used to generate pseudo-bounding boxes. In the third step, the images with bounding box annotations and the generated images with pseudo-bounding box labels are used as inputs to the detection network. Furthermore, we propose a multi-scale feature fusion module to deal with the problem of biomarker appearance changes. The effectiveness of the proposed method is evaluated on a local dataset, and the state-of-the-art performance of our method is achieved in all datasets with different percentages of bounding box annotations.

OBJECTIVE: Intracranial aneurysms (IA) are lethal, with high morbidity and mortality rates. Reliable, rapid, and accurate segmentation of IAs and their adjacent vasculature from medical imaging data is important to improve the clinical management of patients with IAs. However, due to the blurred boundaries and complex structure of IAs and overlapping with brain tissue or other cerebral arteries, image segmentation of IAs remains challenging. This study aimed to develop an attention residual U-Net (ARU-Net) architecture with differential preprocessing and geometric postprocessing for automatic segmentation of IAs and their adjacent arteries in conjunction with 3D rotational angiography (3DRA) images. METHODS: The proposed ARU-Net followed the classic U-Net framework with the following key enhancements. First, we preprocessed the 3DRA images based on boundary enhancement to capture more contour information and enhance the presence of small vessels. Second, we introduced the long skip connections of the attention gate at each layer of the fully convolutional decoder-encoder structure to emphasize the field of view (FOV) for IAs. Third, residual-based short skip connections were also embedded in each layer to implement in-depth supervision to help the network converge. Fourth, we devised a multiscale supervision strategy for independent prediction at different levels of the decoding path, integrating multiscale semantic information to facilitate the segmentation of small vessels. Fifth, the 3D conditional random field (3DCRF) and 3D connected component optimization (3DCCO) were exploited as postprocessing to optimize the segmentation results. RESULTS: Comprehensive experimental assessments validated the effectiveness of our ARU-Net. The proposed ARU-Net model achieved comparable or superior performance to the state-of-the-art methods through quantitative and qualitative evaluations. Notably, we found that ARU-Net improved the identification of arteries connecting to an IA, including small arteries that were hard to recognize by other methods. Consequently, IA geometries segmented by the proposed ARU-Net model yielded superior performance during subsequent computational hemodynamic studies (also known as "patient-specific" computational fluid dynamics [CFD] simulations). Furthermore, in an ablation study, the five key enhancements mentioned above were confirmed. CONCLUSIONS: The proposed ARU-Net model can automatically segment the IAs in 3DRA images with relatively high accuracy and potentially has significant value for clinical computational hemodynamic analysis.

Optical coherence tomography angiography (OCTA) technology has been applied to retinal examination for clinical diagnosis. OCTA images reveal important details of eye diseases such as diabetic retinopathy (DR), glaucoma and age-related macular degeneration (AMD). DR and AMD are the leading causes of blindness in these diseases. Quantitative analysis of retinal vessel can help doctors diagnose retinal diseases and track the progression of these diseases. In this paper, we propose a new OCTA vessel segmentation framework based on variable vessel thickness. Specifically, to guide the network to adapt to the scale changes of vessels, we construct a vessel structure attention module. It can better capture the vessel structure by guiding the network to pay attention to the vessel edge information and help the network to establish a good context dependency. By assigning corresponding weights to different pixels, it helps the network to better learn vessels of different thicknesses and segment a more complete vessel structure. Finally, the framework is evaluated on the OCTA500 dataset, and experimental results demonstrate the effectiveness of the proposed segmentation framework.

Optical Coherence Tomography Angiography (OCTA) is a rapid, non-invasive imaging technique, which can display the vascular system in detail. Retinal vascular segmentation on OCTA images is of great significance for the diagnosis and treatment of many vision-related diseases. However, there is still much room for improvement in the research of retinal vascular segmentation due to the low visibility of vascular edges and high vascular complexity. Therefore, we propose a novel OCTA vascular segmentation network (VCT-Net). The network is a U-shaped network consisting of a transformer branch and a convolution branch. The structure enables the network to make full use of global and local information. The transformer branch uses a swin transformer to reduce computational complexity. Experimental results show that VCT-Net achieves better vascular segmentation performance than other deep learning methods on OCTA-6M dataset.

Remote Attestation (RA) is a security service by which a Verifier (Vrf) can verify the platform state of a remote Prover (Prv). However, in most existing RA schemes, the Prv might be vulnerable to denial of service (DoS) attacks due to the interactive challenge-response methodology while there is no authentication about the challenge. Worse, many schemes cannot effectively detect mobile malware that can be inactive during the on-demand attestation launched by the Vrf. In this paper, we propose a self-measurement RA for SGX-based platforms, which can effectively mitigate DoS attacks and defend against mobile malware. To this end, a two-way identity authentication is first enforced between the Prv and Vrf with the help of a blockchain system, in which a shared session key is also generated. Secondly, trigger conditions of measurements on the Prv’s side are time points generated by the Prv self instead of Vrf’s requests. The Vrf can retrieve multiple self-measurement results during one execution of the protocol to monitor the Prv’s platform over a period of time continuously, which can detect mobile malware effectively. Our scheme utilizes SGX to provide the runtime protection for sensitive information such as session key, self-measurement code, time points of self-measurements, and self-measurement results, making a higher security guarantee. In addition, the session key, time points of self-measurements, and self-measurement code can be changed or upgraded, making our scheme more flexible and scalable. The simulation implementation and results show that our scheme is feasible and practical.

COVID-19 has been spread around the world and has caused a huge number of deaths. Early detection of this disease is the most efficient way to prevent its rapid spread. Due to the development of internet technology and edge intelligence, developing an early detection system for COVID-19 in the medical environment of the Internet of Things (IoT) can effectively alleviate the spread of the disease. In this paper, a detection algorithm is developed, which can detect COVID-19 effectively by utilizing the features from Chest X-ray (CXR) images. First, a pre-trained model (ResNet18) is adopted for feature extraction. Then, a discrete social learning particle swarm optimization algorithm (DSLPSO) is proposed for feature selection. By filtering redundant and irrelevant features, the dimensionality of the feature vector is reduced. Finally, the images are classified by a Support Vector Machine (SVM) for COVID-19 detection. Experimental results show that the proposed algorithm can achieve competitive performance with fewer features, which is suitable for edge computing devices with lower computation power.

When optical coherence tomography (OCT) is used for retinal disease diagnosis, it is critical to detect and classify the biomarkers from the OCT B-scans of patients. In this paper, we propose a novel weakly supervised approach that utilizes healthy data and image-level labels for biomarker detection and classification. The proposed approach is based on a hybrid network which integrates adversarial generative network and guided attention into one framework. The framework includes an anomaly detection network and a classification network. The anomaly detection network reconstructs an input image with biomarkers to a reconstructed image and the reconstructed image is compared with the input image to locate the biomarkers. Inspired by the guided attention inference network, we utilize the discriminator trained in the anomaly detection network as a classifier twice to reduce model parameters and obtain a complete attention map with class information to get biomarker classes. Experimental results with a large dataset demonstrate the effectiveness of the proposed detection and classification framework.

It is straightforward to encrypt the outsourced data to protect its confidentiality using symmetric cryptography in cloud storage. How to control and restrict the use of the encryption key in data users’ devices becomes one of the critical issues. In most of existing time-based and policy-based schemes, the key cannot be stored locally in data users’ devices, making the traffic cost linear with the data access times as the key should be retrieved in each data access. In this paper, we propose a times-based scheme with Intel SGX to restrict the times the key can be used in the data user’s device to restrict the times of data access. The basic idea is to compare the current used times with the specified maximal times to determine whether the key can be used or not. To this end, we use a monotonic counter to count the times the key has been used. When the use condition is not satisfied, we destroy the key securely and generate public proof so that (i) the encrypted data cannot be accessed anymore, i.e., the data is deleted assuredly, (ii) the deletion can be verified. In addition, a hash-based integrity check approach is utilized to detect and prevent replay attacks. The experimental results on the implemented prototype show our scheme is feasible in practice.

Stacked auto-encoder is mainly used for image classification and it can extract valid information from data through unsupervised pre-training and supervised fine-tuning. This paper is intended to improve the accuracy of image classification, we constructed a 6-layer stacked convolution neural network (CNN) based on stacked auto-encoders. The constructed CNN can extract effective features for image classification through greedy layer-wise training. In order to make the constructed CNN to have strong robustness to noise, we added a noisy-layer in the pre-training stage. Adding the sparsity constraint can make the training of the CNN more effective, and can also reduce data redundancy. For classification applications, our experiments show that the final classification results of the proposed model is superior to the combination of auto-encoders and the noisy auto-encoders.

In this paper, we propose a cluster-driven anisotropic diffusion (CDAD) filter for speckle reduction in ultrasound images. The proposed filter is based on the multiplicative noise model and is driven by K-means clustering algorithm. Instead of choosing homogeneous sample region with manual selection, the proposed algorithm is able to do it automatically (based on the clustering results). In addition, clustering result is used as a global characteristics descriptor to further improve the performance of noise removal as well as edge enhancement. The proposed filter was implemented and evaluated with real ultrasound images. Experimental results show that the proposed CDAD filter shows improved performance compared with Speckle Reducing Anisotropic Diffusion (SRAD).

A feature-preserving mesh denoising filter is proposed in the paper for 3-D printers. The whole algorithm contains two steps: non-iterative normal filtering and iterative vertex updating. The basic idea of normal filtering is to minimize the angles between face normals in meshes in flat region. The proposed filter was tested and compared with other mesh denoising filters on simulated noisy mesh models as well as real mesh models. The performance of filters were evaluated based on the edge features from the filtered meshes. The proposed filter is very simple to accomplish, and it shows good performance in both noise removal and edge preservation. We also printed the original noisy mesh and the filtered versions using a 3-D printer and visually checked the quality of the filtered meshes obtained by different filters and we found that the meshes filtered by the proposed filter has the best visual quality.

In this paper, we describe three speckle reduction filters and compared their performance in speckle reduction for 3D ultrasound images. Filtering techniques related to those filters include Frost's filter, anisotropic diffusion, Normalized bilateral filtering, and non-local means filter. The qualitative as well quantitative evaluations are used to analyze the performance of four filters.

In this paper, we propose an interactive image retrieval method based on interactive image segmentation and relevance feedback. For testing the performance of the algorithm, we built an image database by web crawlers, and added a background label to each image by histogram analysis. For image retrieval, an interactive image segmentation scheme based on GrabCut has been applied to get the region of interest (ROI), and then we use an automatic labeling method to get the training samples of relevance feedback, and then incorporate the background labels into the similarity measurement to decrease the influence of clutters. The experimental results show that this method can reduce the influence of image background on image retrieval, and optimize the search results by the feedback of users.

In this paper, we investigate advanced image processing technologies to detect cracks for road distress analysis. An algorithm which can detect and segment cracks effectively is proposed. The proposed algorithm is a hybrid crack detection and segmentation algorithm. In the proposed detection and segmentation algorithm, we first use histogram based thresholding method to get the rough locations of the cracks and then mathematics morphology technologies and B-spline based snake model based technology are used to refine the locations of the cracks. We conducted experiments on 10 images with different types of cracks and experimental results show that the proposed technologies can be used for find the cracks effectively.

Human head pose estimation is a hot topic in computer vision field, which can be used in video surveillance, Human Computer Interaction and so on. Active Shape Model is a template matching method, which is suitable for object localization and point based feature extraction. In this paper, we propose an algorithm based on Active Shape Model for head pose estimation. In the proposed algorithm, we firstly use Active Shape Model to estimate 2D face feature points of the target human head, then we adopt Relevant Vector Machine to evaluate head pose based on the extracted feature points. Experiments on CAS-PEAL-R1 dataset show that the proposed algorithm has great potential in estimating head pose with small yaw angle.

In this paper, we investigate the possibility of using limited feature points (shape landmarks) from 3-D human body shapes to recognize the gender of human beings. Several machine learning algorithms and feature extraction algorithms (principal component analysis and linear discriminant analysis) are investigated and analyzed in this paper. Experimental results on a large dataset containing 2484 3-D shape models show that limited feature points (shape landmarks) can be used for gender recognition and can achieve high recognition rate, which provides a fast gender recognition technique. The research provides a potential research direction for gender recognition.

In this paper, we investigate the reduction of speckles in 3-D ultrasound images using a 3-D bilateral filter for cattle follicle segmentation and volume estimation. Adaptive 3-D bilateral filter is developed to reduce the speckles in the ultrasound images effectively. We compared the proposed 3-D bilateral filter with the conventional 3-D bilateral filter and 3-D Gaussian filter using both 3-D synthetic speckled images and real ultrasound images. Quantitative analysis verified the effectiveness of the proposed method.

In this paper, we describe a framework for GPS/INS based Portable Positioning System. The framework includes two main components: receiving terminal and monitoring center. In the receiving terminal, the digital compass and the GPS modules are both connected with an I/O interface in a FPGA to provide an integrated positioning solution. This integrated positioning algorithm can solve the problems arising both in standalone modes and in traditional integrated measurements. In the monitoring center, several improvements have been discussed to ensure runtime efficiency and the robustness of the PPS. The experimental results from two positioning modes validate the effectiveness of the proposed algorithm.

To understand and interpret human motion is a very active research area nowadays because of its importance in sports sciences, health care, and video surveillance. However, classification of human motion patterns is still a challenging topic because of the variations in kinetics and kinematics of human movements. In this paper, we present a novel algorithm for automatic classification of motion trajectories of human upper limbs. The proposed scheme starts from transforming 3-D positions and rotations of the shoulder/elbow/wrist joints into 2-D trajectories. Discriminative features of these 2-D trajectories are, then, extracted using a probabilistic shape-context method. Afterward, these features are classified using a k-means clustering algorithm. Experimental results demonstrate the superiority of the proposed method over the state-of-the-art techniques.

In this paper, a new method for the estimation of 3D human body poses from monocular images is proposed. Histograms of oriented gradients are used as the features for modeling human body poses. Human body poses are represented as 3D limb angles, which can remove the structure information from pose vector. Relevance Vector Machine is used to infer the mapping from image features to body poses. Experiments show that the proposed method is robust to camera views and can lead more accurate results than other pose estimation methods.

In this paper, we investigate mass classification using an improved local binary pattern operator. In the proposed classification algorithm, the improved local binary pattern operator is used to extract the features of masses and is used to determine whether the mass is benign or malignant. For classifier, support vector machine is adopted. 309 images from the DDSM database were used and the experimental results show the effectiveness of the proposed algorithm.

Web application has become one of the main network applications. The security in web application systems is very important. In this paper we present a method for tracking suspicious users based on web data analysis. Based on a browser/server model, internet flow data are stored in the server and outliers considered as the suspicious users are detected with web data analysis. The behaviors of these suspicious users are tracked and those browsed web pages are recorded in database. By replaying the visited web pages, the proposed method is able to monitor the given suspicious users, which can benefit intranet network security.

The five papers in this special issue focus on pattern recognition technologies for anti-terrorism applications.

Gender recognition has important applications in identity recognition, demographic survey, and human-computer interaction systems. In the past, gender recognition was based on 2-D images or videos, which has many limitations and disadvantages, such as low accuracy and sensitivity to the viewpoint of the camera and lighting conditions. In this paper, we investigate gender recognition using 3-D human body shapes. The 3-D human body shapes used for gender recognition were obtained by laser scanning. Different machine-learning algorithms and feature-extraction methods are investigated and analyzed in this paper. Experimental results show that the support vector machine (SVM) is the best classification algorithm, and the features represented using distributions of normals are very effective for gender recognition. Furthermore, Fourier descriptor (FD) is a robust method to analyze the breast regions and has great potential applications in 3-D human-body-shape-based biometrics. The research demonstrates that our shape-based gender recognition has achieved a very high recognition rate. The techniques provide effective ways for gender recognition and overcome some limitations in 2-D technologies.

Particle filter is a popular stochastic tracker for object tracking. In articulated human body pose tracking, lots of work focuses on increasing sampling efficiency by incorporating optimization algorithm into particle filter. In this study, we propose a modified optimization based particle filter algorithm for pose tracking. The new algorithm can maintain the diversity of particle set by using a suppression scheme. Experimental results show that the proposed method can cope with multi-modality and can obtain more accurate estimation than other optimization based particle filter methods.

Human motion tracking and analysis have received increasing attention for motion capture and human behavior recognition, which aim to extract useful information such as position, pose, and velocity of a moving human body from image sequences (video). This paper proposed a new human motion tracking method which searches critical points of generalized gradient vector flow (GGVF) around the skeleton of a human body. We focus on the motion analysis of critical points since it reveals the essential movement of the observed object. Experimental results demonstrated that the proposed method can extract crucial information of the dynamic body motions.

With the wide applications of video cameras in surveillance, video analysis technologies have attracted the attention from the researchers in computer vision field. In video analysis, human behavior recognition and understanding is an important research direction. By recognition and understanding the human behaviors, we can predict and recognize the happening of crimes and help to the police or other agencies to react immediately. In the past, large amount of intensive papers have been published on human behavior understanding in videos. Generally speaking, the procedure of human behavior understanding can be divided into the following stages: human segmentation and tracking, and human behavior recognition. In this paper, we provide a comprehensive survey of the recent development of all these stages. We will also discuss the difficulties in behavior understanding and identify possible future directions.

The widespread networks in campus provide students with rich resources, but they also provide unhealthy information which may have negative effects on students. Filtering systems have been developed to prevent web users from unhealthy web contents. However, the false positive and false negative rates of those tools are still high and thus need to be improved. In this paper, we propose an Internet behavior monitoring method by integrating the BHO plug-in techniques with URL-based filtering technique, and apply this method in the campus network. Designed in the client/server mode, the method has the capabilities of filtering out unhealthy websites according to the given black list, and can record the students' online web activities into XML documents and/or pictures. The recorded contents can be replayed by the campus network administrators. This method assists teachers to keep eyes on students' learning state, and notifies the administrators to react immediately to help campus web users correct their inappropriate behaviors.

Image enhancement technologies have been widely used for improving the quality of the images for screening mammograms. In this paper, we will focus on the enhancement of breast calcifications, which are the deposits of calcium that can be seen on a mammogram of the breast. In the proposed method, the original image and the normalized gradient image of the original image are first decomposed into a multi-level Laplacian pyramids, and then the features in different scales are enhanced level by level based on a contrast measure during the reconstruction stage. Because the importance of different levels is different, different weights are used in different levels. Experiments proved the effectiveness of the proposed algorithm.

Breast cancer is the second-most common and leading cause of cancer death among women. It has become a major health issue in the world over the past 50 years, and its incidence has increased in recent years. Early detection is an effective way to diagnose and manage breast cancer. Computer-aided detection or diagnosis (CAD) systems can play a key role in the early detection of breast cancer and can reduce the death rate among women with breast cancer. The purpose of this paper is to provide an overview of recent advances in the development of CAD systems and related techniques. We begin with a brief introduction to some basic concepts related to breast cancer detection and diagnosis. We then focus on key CAD techniques developed recently for breast cancer, including detection of calcifications, detection of masses, detection of architectural distortion, detection of bilateral asymmetry, image enhancement, and image retrieval.

In this paper, the recurrent neural networks (RNNs) with a generalized activation function class is proposed. In this proposed model, every component of the neuron's activation function belongs to a convex hull which is bounded by two odd symmetric piecewise linear functions that are convex or concave over the real space. All of the convex hulls are composed of generalized activation function classes. The novel activation function class is not only with a more flexible and more specific description of the activation functions than other function classes but it also generalizes some traditional activation function classes. The absolute exponential stability (AEST) of the RNN with a generalized activation function class is studied through three steps. The first step is to demonstrate the global exponential stability (GES) of the equilibrium point of original RNN with a generalized activation function being equivalent to that of RNN under all vertex functions of convex hull. The second step transforms the RNN under every vertex activation function into neural networks under an array of saturated linear activation functions. Because the GES of the equilibrium point of three systems are equivalent, the next stability analysis focuses on the GES of the equilibrium point of RNN system under an array of saturated linear activation functions. The last step is to study both the existence of equilibrium point and the GES of the RNN under saturated linear activation functions using the theory of M-matrix. In the end, a two-neuron RNN with a generalized activation function is constructed to show the effectiveness of our results.

Dimension reduction is critical in many areas of pattern classification and machine learning and many discriminant analysis algorithms have been proposed. In this paper, a Pairwise Covariance-preserving Projection Method (PCPM) is proposed for dimension reduction. PCPM maximizes the class discrimination and also preserves approximately the pairwise class covariances. The optimization involved in PCPM can be solved directly by eigenvalues decomposition. Our theoretical and empirical analysis reveals the relationship between PCPM and Linear Discriminant Analysis (LDA), Sliced Average Variance Estimator (SAVE), Heteroscedastic Discriminant Analysis (HDA) and Covariance preserving Projection Method (CPM). PCPM can utilize class mean and class covariance information at the same time. Furthermore, pairwise weight scheme can be incorporated naturally with the pairwise summarization form. The proposed methods are evaluated by both synthetic and real-world datasets.

Currently, radiologists mainly use their eyes to discern cancer when they screen the mammograms. However, in many cases, cancer is not easily detected by the eyes because of bad imaging conditions. In order to improve the diagnostic rate of cancer, image enhancement technology is often used to enhance the image and aid the radiologists. In this paper, we developed a new image enhancement technology in the wavelet domain for radiologists to screen mammograms. The new image enhancement algorithm has several advantages. First, the image enhancement is based on a contrast measure defined in the wavelet domain which matches the human vision system better. The enhanced images are therefore more suitable for the human eye; second, the image enhancement is carried on in the wavelet domain which saves time if the image is compressed by JPEG2000. The algorithm was tested by an expert and the results are progressive.

In this paper a new algorithm is presented for image enhancement in the discrete cosine transform (DCT) domain. The algorithm is based on a novel contrast measure that is defined for each DCT coefficient. This algorithm can be applied to the enhancement of images compressed with JPEG and it is especially useful when it is applied to enhance the direction contrast of the images. Experimental results show the effectiveness of the proposed algorithm.

An image enhancement algorithm for images compressed using the JPEG standard is presented. The algorithm is based on a contrast measure defined within the discrete cosine transform (DCT) domain. The advantages of the psychophysically motivated algorithm are 1) the algorithm does not affect the compressibility of the original image because it enhances the images in the decompression stage and 2) the approach is characterized by low computational complexity. The proposed algorithm is applicable to any DCT-based image compression standard, such as JPEG, MPEG 2, and H. 261.