Owing to the complexity of finger vein patterns in shape and spatial dependence, the existing methods suffer from an inability to obtain accurate and stable finger vein features. This paper, so as to compensate this defect, proposes an end-to-end model to extract vein textures through integrating the fully convolutional neural network (FCN) with conditional random field (CRF). Firstly, to reduce missing pixels during ROI extraction, the method of sliding window summation is employed to filter and adjusted with self-built tools. In addition, the traditional baselines are endowed with different weights to automatically assign labels. Secondly, the deformable convolution network, through replacing the plain counterparts in the standard U-Net mode, can capture the complex venous structural features by adaptively adjusting the receptive fields according to veins’ scales and shapes. Moreover, the above features can be further mined and accumulated by combining the recurrent neural network (RNN) and the residual network (ResNet). With the steps mentioned above, the fully convolutional neural network is constructed. Finally, the CRF with Gaussian pairwise potential conducts mean-field approximate inference as the RNN, and then is embedded as a part of the FCN, so that the model can fully integrate CRF with FCNs, which provides the possibility to involve the usual back-propagation algorithm in training the whole deep network end-to-end. The proposed models in this paper were tested on three public finger vein datasets SDUMLA, MMCBNU and HKPU with experimental results to certify their superior performance on finger-vein verification tasks compared with other equivalent models including U-Net.

There would be the differences in spectra, scale and resolution between the Remote Sensing datasets of the source and target domains, which would lead to the degradation of the cross-domain segmentation performance of the model. Image transfer faced two problems in the process of domain-adaptive learning: overly focusing on style features while ignoring semantic information, leading to biased transformation results, and easily overlooking the true transfer characteristics of remote sensing images, resulting in unstable model training. To address these issues, we proposes a novel dual-space generative adversarial domain adaptation segmentation framework, DS-DWTGAN, to minimize the differences between the source domain and the target domain. DS-DWTGAN aims to mitigate the distinctions between the source and target domains, thereby rectifying the imbalances in style and semantic representation.The framework introduces a network branch leveraging wavelet transform to capture comprehensive frequency domain and semantic information. It aims to preserve semantic details within the frequency domain space, mitigating image conversion deviations. Furthermore, our proposed method integrates output adaptation and data enhancement training strategies to reinforce the acquisition of domain-invariant features. This approach effectively diminishes noise interference during the migration process, bolsters model stability, and elevates the model’s adaptability to remote sensing images within different domains. Experimental validation was conducted on the publicly available Potsdam and Vaihingen datasets. The findings reveal that in the PotsdamIRRG to Vaihingen task, the proposed method attains outstanding performance with mIoU and mF1 values reaching 56.04% and 67.28%, respectively. Notably, these metrics surpass the corresponding values achieved by state-of-the-art (SOTA) methods, registering an increase of 2.81% and 2.08%. In comparison to alternative approaches, our proposed framework exhibits superior efficacy in the domain of unsupervised semantic segmentation for UAV remote sensing images.

Melanoma is a highly malignant skin tumor. Accurate segmentation of skin lesions from dermoscopy images is pivotal for computer-aided diagnosis of melanoma. However, blurred lesion boundaries, variable lesion shapes, and other interference factors pose a challenge in this regard. This work proposes a novel framework called CFF-Net (Cross Feature Fusion Network) for supervised skin lesion segmentation. The encoder of the network includes dual branches, where the CNNs branch aims to extract rich local features while MLPs branch is used to establish both the global-spatial-dependencies and global-channel-dependencies for precise delineation of skin lesions. Besides, a feature-interaction module between two branches is designed for strengthening the feature representation by allowing dynamic exchange of spatial and channel information, so as to retain more spatial details and inhibit irrelevant noise. Moreover, an auxiliary prediction task is introduced to learn the global geometric information, highlighting the boundary of the skin lesion. Comprehensive experiments using four publicly available skin lesion datasets (i.e., ISIC 2018, ISIC 2017, ISIC 2016, and PH2) indicated that CFF-Net outperformed the state-of-the-art models. In particular, CFF-Net greatly increased the average Jaccard Index score from 79.71% to 81.86% in ISIC 2018, from 78.03% to 80.21% in ISIC 2017, from 82.58% to 85.38% in ISIC 2016, and from 84.18% to 89.71% in PH2 compared with U-Net. Ablation studies demonstrated the effectiveness of each proposed component. Cross-validation experiments in ISIC 2018 and PH2 datasets verified the generalizability of CFF-Net under different skin lesion data distributions. Finally, comparison experiments using three public datasets demonstrated the superior performance of our model. The proposed CFF-Net performed well in four public skin lesion datasets, especially for challenging cases with blurred edges of skin lesions and low contrast between skin lesions and background. CFF-Net can be employed for other segmentation tasks with better prediction and more accurate delineation of boundaries.

Facial beauty prediction (FBP), as a frontier topic in the domain of artificial intelligence regarding anthropology, has witnessed some good results as deep learning technology progressively develops. However, it is still limited by the complexity of the deep structure network in need of a large number of parameters and high dimensions, easily leading to a great consumption of time. To solve this problem, this paper proposes a fast training FBP method based on local feature fusion and broad learning system (BLS). Firstly, two-dimensional principal component analysis (2DPCA) is employed to reduce the dimension of the local texture image so as to lessen its redundancy. Secondly, local feature fusion method is adopted to extract more advanced features through avoiding the effects from unstable illumination, individual differences, and various postures. Finally, extensional feature eigenvectors are input to the broad learning network to train an efficient FBP model, which effectively shortens operational time and improve its preciseness. Extensive experiments with the proposed method on large scale Asian female beauty database (LSAFBD) can be conducted within 13.33s while sustaining an accuracy of 58.97%, impressively outstripping other state-of-the-art methods in training speed.

Breast cancer detection largely relies on imaging characteristics and the ability of clinicians to easily and quickly identify potential lesions. Magnetic resonance imaging (MRI) of breast tumors has recently shown great promise for enabling the automatic identification of breast tumors. Nevertheless, state-of-the-art MRI-based algorithms utilizing deep learning techniques are still limited in their ability to accurately separate tumor and healthy tissue. Therefore, in the current work, we propose an automatic and accurate two-stage U-Net-based segmentation framework for breast tumor detection using dynamic contrast-enhanced MRI (DCE-MRI). This framework was evaluated using T2-weighted MRI data from 160 breast tumor cases, and its performance was compared with that of the standard U-Net model. In the first stage of the proposed framework, a refined U-Net model was utilized to automatically delineate a breast region of interest (ROI) from the surrounding healthy tissue. Importantly, this automatic segmentation step reduced the impact of the background chest tissue on breast tumors’ identification. For the second stage, we employed an improved U-Net model that combined a dense residual module based on dilated convolution with a recurrent attention module. This model was used to accurately and automatically segment the tumor tissue from healthy tissue in the breast ROI derived in the previous step. Overall, compared to the U-Net model, the proposed technique exhibited increases in the Dice similarity coefficient, Jaccard similarity, positive predictive value, sensitivity, and Hausdorff distance of 3%, 3%, 3%, 2%, and 16.2, respectively. The proposed model may in the future aid in the clinical diagnosis of breast cancer lesions and help guide individualized patient treatment.

As for that there is only one training sample in single sample per person(SSPP) face recognition(FR), deep learning(DL) method is very difficult to be used. To overcome this problem, the paper proposes a series of methods to make it possible to be used in SSPP FR. Firstly, an expanding sample method is proposed to increase training sample. Secondly, a learned Deep Convolutional Neural Network(DCNN) model which is trained with amounts of face images and can represent face very well is brought in. Then, these expanding samples are used to fine-tune the DCNN model. Thirdly, the fine-tuned DCNN model is used to perform experiment. Experiments demonstrate that a better performance is obtained by using the fine-tuned DCNN model.