Search

Accurate segmentation of skin lesion regions is a key step in clinical diagnosis and analysis. Aiming at the poor segmentation effect of the existing networks in skin lesion regions due to the presence of variable size, irregular shape, fuzzy boundaries and obscured lesion regions, a multi-scale and boundary fusion network (MSBF-Net) for skin lesion region segmentation is proposed by improving the original structure based on the U-Net. Specifically, firstly, a split pooling (SplitPool) module is proposed, which effectively solves the problem of spatial information loss while reducing the image resolution. Secondly, a full-scale feature fusion (FSFF) module is proposed, which effectively solves the problem that the previous methods only fuse the deep features to the shallow features, while ignoring the contribution of the detail information in the more shallow features to the network segmentation decision. Meanwhile, the original jump connections of U-Net are redesigned to provide richer contextual information for the decoder. Finally, sub-paths for enhancing the network’s ability to learn boundary features are proposed, and the boundary fusion (BF) module is introduced to fuse the prediction results of the main paths and sub-paths, which effectively solves the problems of irregular shape and boundary ambiguity of the lesion region. Dice and JI reach 90.12% and 83.61% on the ISIC2018 dataset, which are 1.13 percentage points and 1.62 percentage points higher than the baseline network, respectively; Dice and JI reach 94.72% and 90.18% on the PH2 dataset, which are 1.49 percentage points and 2.17 percentage points higher than the baseline network, respectively. Experimental results show that MSBF-Net significantly improves the accuracy of skin lesion region segmentation and exceeds the existing state-of-the-art methods in several indices, further validating the effectiveness of the method.

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Current research on image tampering localization focuses on finding region features that distinguish manipulated pixels from non-manipulated pixels. As tampering with a specific area of a given image inevitably leaves cues in the boundary between the tampered region and its surroundings, how to utilize sufficient region and boundary features also matters for image manipulation localization. In this paper, we propose a unified network (called RB-Net), which is a two-branch network (i.e., region module and boundary module) to learn region and boundary features separately. Then the fusion module is implemented to integrate the region features from the region module and the edge features from the boundary module, respectively. Particularly, to identify unnatural boundary traces, we propose edge gate components deployed on different layers of the region module to activate manipulated boundary information from the rich region features. Quantitative and qualitative experiments on four benchmark datasets demonstrate that RB-Net can accurately locate the tampered regions and achieve the best results relative to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) can provide high-resolution and large-scale maritime monitoring, which is beneficial to ship detection. However, ship-detection performance is significantly affected by the complexity of environments, such as uneven scattering of ship targets, the existence of speckle noise, ship side lobes, etc. In this paper, we present a novel anomaly-based detection method for ships using feature learning for superpixel (SP) processing cells. First, the multi-feature extraction of the SP cell is carried out, and to improve the discriminating ability for ship targets and clutter, we use the boundary feature described by the Haar-like descriptor, the saliency texture feature described by the non-uniform local binary pattern (LBP), and the intensity attention contrast feature to construct a three-dimensional (3D) feature space. Besides the feature extraction, the target classifier or determination is another key step in ship-detection processing, and therefore, the improved clutter-only feature-learning (COFL) strategy with false-alarm control is designed. In detection performance analyses, the public datasets HRSID and LS-SSDD-v1.0 are used to verify the method's effectiveness. Many experimental results show that the proposed method can significantly improve the detection performance of ship targets, and has a high detection rate and low false-alarm rate in complex background and multi-target marine environments. [ABSTRACT FROM AUTHOR]

We address the 3D shape assembly of multiple geometric pieces without overlaps, a scenario often encountered in 3D shape design, field archeology, and robotics. Existing methods depend on strong assumptions on the number of shape pieces and coherent geometry or semantics of shape pieces. Despite raising attention to 3D registration with complex or low overlapping patterns, few methods consider shape assembly with rare overlaps. To address this problem, we present a novel framework inspired by solving puzzles, named PuzzleNet, which conducts multi-task learning by leveraging both 3D alignment and boundary information. Specifically, we design an end-to-end neural network based on a point cloud transformer with two-way branches for estimating rigid transformation and predicting boundaries simultaneously. The framework is then naturally extended to reassemble multiple pieces into a full shape by using an iterative greedy approach based on the distance between each pair of candidate-matched pieces. To train and evaluate PuzzleNet, we construct two datasets, named DublinPuzzle and ModelPuzzle, based on a real-world urban scan dataset (DublinCity) and a synthetic CAD dataset (ModelNet40) respectively. Experiments demonstrate our effectiveness in solving 3D shape assembly for multiple pieces with arbitrary geometry and inconsistent semantics. Our method surpasses state-of-the-art algorithms by more than 10 times in rotation metrics and four times in translation metrics. [ABSTRACT FROM AUTHOR]

Camouflaged object detection aims to accurately identify objects blending into the background. However, existing methods often struggle, especially with small object or multiple objects, due to their reliance on singular strategies. To address this, we introduce a novel Search and Recovery Network (SRNet) using a bionic approach and auxiliary features. SRNet comprises three key modules: the Region Search Module (RSM), Boundary Recovery Module (BRM), and Camouflaged Object Predictor (COP). The RSM mimics predator behavior to locate potential object regions, enhancing object location detection. The BRM refines texture features and recovers object boundaries. The COP fuse multilevel features to predict final segmentation maps. Experimental results on three benchmark datasets show SRNet's superiority over SOTA models, particularly with small and multiple objects. Notably, SRNet achieves performance improvements without significantly increasing model parameters. Moreover, the method exhibits promising performance in downstream tasks such as defect detection, polyp segmentation and military camouflage detection. • We propose a Search and Recovery Network using a bionic strategy for accurate camouflage object detection with minimal model parameters. • We propose a Region Search Module that simulates predator-prey interactions to distinguish global and local features. • We propose a boundary recovery module that integrates boundary and contextual features with improved attention mechanisms. • We propose a Camouflaged Object Predictor that aggregates boundary recovery results from multiple BRMs. • We tested our method on downstream tasks, showing strong generalization with accurate segmentation. [ABSTRACT FROM AUTHOR]

Synthetic aperture radar (SAR) can provide high-resolution and large-scale maritime monitoring, which is beneficial to ship detection. However, ship-detection performance is significantly affected by the complexity of environments, such as uneven scattering of ship targets, the existence of speckle noise, ship side lobes, etc. In this paper, we present a novel anomaly-based detection method for ships using feature learning for superpixel (SP) processing cells. First, the multi-feature extraction of the SP cell is carried out, and to improve the discriminating ability for ship targets and clutter, we use the boundary feature described by the Haar-like descriptor, the saliency texture feature described by the non-uniform local binary pattern (LBP), and the intensity attention contrast feature to construct a three-dimensional (3D) feature space. Besides the feature extraction, the target classifier or determination is another key step in ship-detection processing, and therefore, the improved clutter-only feature-learning (COFL) strategy with false-alarm control is designed. In detection performance analyses, the public datasets HRSID and LS-SSDD-v1.0 are used to verify the method’s effectiveness. Many experimental results show that the proposed method can significantly improve the detection performance of ship targets, and has a high detection rate and low false-alarm rate in complex background and multi-target marine environments.

Object detection is of great importance for remote sensing image interpretation work and has received significant attention. However, small weak object detection has always been a challenge. The main reason is that the critical information of these objects, such as textures and boundaries, is suppressed by the background and cannot effectively express their own characteristics. To address this issue, we introduce a novel texture and boundary-aware network (TBNet) in this paper. Firstly, we propose a texture-aware enhancement module (TAEM) to explore the texture details within the images. TAEM captures pixel correlations to perceive the distribution of texture in the objects. Secondly, a boundary-aware fusion module (BAFM) is introduced to emphasize spatial positions. BAFM can extract the edge information to guide the prediction of small weak objects. Finally, a task-decoupled RCNN (TD-RCNN) is designed to separate classification and regression tasks. TD-RCNN achieves fine-grained detection, avoiding compromises between subtasks. Comprehensive experiments on four public datasets, DIOR NWPU VHR-10, RSOD, and AI-TOD, demonstrate that TBNet achieves state-of-the-art performance compared to competitors. The model is also evaluated on UAVOD-10, which collects numerous small weak objects. TBNet achieves state-of-the-art results while significantly outperforming competitors, proving its ability to detect small weak objects. • TBNet is designed to detect small and weak objects in complex remote sensing images. • The network enhances object representations by exploring texture and boundary features. • TD-RCNN avoids feature coupling from shared classification and localization. • Results show the model detects remote-sensing objects effectively, especially weak ones. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Image & Graphics is the property of Editorial Office of Journal of Image & Graphics and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Saliency detection is a significant mechanism for image processing tasks. In this paper, we proposed an improved two-stage method that was based on image boundary feature and smoothness energy function. Firstly, we use the color contrast and image boundary feature to obtain the initial prior map and boundary based prior map respectively. Then, we combine the initial prior map and boundary based prior map to generate the improved coarse saliency map. Finally, the smoothness energy function is utilized to refine the coarse saliency map. Experiment on two public datasets demonstrates that our method has a good performance than the state-off-the-art methods. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective: Feature extraction of breast tumors is very important in the breast tumor detection (benign and malignant) in ultrasound image. The traditional quantitative description of breast tumors has some shortcomings, such as inaccuracy. A simple and accurate feature extraction method has been studied., Methods: In this paper, a new method of boundary feature extraction was proposed. Firstly, the shape histogram of ultrasound breast tumors was constructed. Secondly, the relevant boundary feature factors were calculated from a local point of view, including sum of maximum curvature, sum of maximum curvature and peak, sum of maximum curvature and standard deviation. Based on the boundary features, shape features and texture features, the linear support vector machine classifiers for benign and malignant breast tumor recognition was constructed., Results: The accuracy of boundary features in the benign and malignant breast tumors classification was 82.69%. The accuracy of shape features was 73.08%. The accuracy of texture features was 63.46%. The classification accuracy of the three fusion features was 86.54%., Conclusions: The classification accuracy of boundary features was higher than that of texture features and shape features. The classification method based on multi-features has the highest accuracy and it describes the benign and malignant tumors from different angles. The research results have practical value.