Junpeng Wu^1,2,*, Zhenpeng Liu², Xingfan Jiang², Xinguang Tao², Ye Zhang³

CMC-Computers, Materials & Continua, Vol.78, No.1, pp. 677-694, 2024, DOI:10.32604/cmc.2023.045759

Abstract The current existing problem of deep learning framework for the detection and segmentation of electrical equipment is dominantly related to low precision. Because of the reliable, safe and easy-to-operate technology provided by deep learning-based video surveillance for unmanned inspection of electrical equipment, this paper uses the bottleneck attention module (BAM) attention mechanism to improve the Solov2 model and proposes a new electrical equipment segmentation mode. Firstly, the BAM attention mechanism is integrated into the feature extraction network to adaptively learn the correlation between feature channels, thereby improving the expression ability of the feature map; secondly, the weighted sum of CrossEntropy… More >

Linlin Zhu, Yu Han, Xiaoqi Xi, Zhicun Zhang, Mengnan Liu, Lei Li, Siyu Tan, Bin Yan^*

CMC-Computers, Materials & Continua, Vol.77, No.3, pp. 3367-3386, 2023, DOI:10.32604/cmc.2023.045878

Abstract Deep learning techniques have significantly improved image restoration tasks in recent years. As a crucial component of deep learning, the loss function plays a key role in network optimization and performance enhancement. However, the currently prevalent loss functions assign equal weight to each pixel point during loss calculation, which hampers the ability to reflect the roles of different pixel points and fails to exploit the image’s characteristics fully. To address this issue, this study proposes an asymmetric loss function based on the image and data characteristics of the image recovery task. This novel loss function can adjust the weight of… More >

Wei Wang¹, Xinyao Tang^2,*, Kai Zhou¹, Chunhui Zhao¹, Changfa Liu³

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 1911-1928, 2023, DOI:10.32604/cmc.2023.043233

Abstract Data Matrix (DM) codes have been widely used in industrial production. The reading of DM code usually includes positioning and decoding. Accurate positioning is a prerequisite for successful decoding. Traditional image processing methods have poor adaptability to pollution and complex backgrounds. Although deep learning-based methods can automatically extract features, the bounding boxes cannot entirely fit the contour of the code. Further image processing methods are required for precise positioning, which will reduce efficiency. Because of the above problems, a CenterNet-based DM code key point detection network is proposed, which can directly obtain the four key points of the DM code.… More >

Lisang Liu¹, Chengyang Ke^1,*, He Lin²

CMC-Computers, Materials & Continua, Vol.77, No.2, pp. 2443-2461, 2023, DOI:10.32604/cmc.2023.042582

Abstract Aiming at the problems of inaccurate edge segmentation, the hole phenomenon of segmenting large-scale targets, and the slow segmentation speed of printed circuit boards (PCB) in the image segmentation process, a PCB image segmentation model Mobile-Deep based on DeepLabv3+ semantic segmentation framework is proposed. Firstly, the DeepLabv3+ feature extraction network is replaced by the lightweight model MobileNetv2, which effectively reduces the number of model parameters; secondly, for the problem of positive and negative sample imbalance, a new loss function is composed of Focal Loss combined with Dice Loss to solve the category imbalance and improve the model discriminative ability; in… More >

Fufang Li, Manlin Luo^*, Ming Hu, Guobin Wang, Yan Chen

Computer Systems Science and Engineering, Vol.47, No.3, pp. 2835-2850, 2023, DOI:10.32604/csse.2023.039765

Abstract Liver cancer has the second highest incidence rate among all types of malignant tumors, and currently, its diagnosis heavily depends on doctors’ manual labeling of CT scan images, a process that is time-consuming and susceptible to subjective errors. To address the aforementioned issues, we propose an automatic segmentation model for liver and tumors called Res2Swin Unet, which is based on the Unet architecture. The model combines Attention-Res2 and Swin Transformer modules for liver and tumor segmentation, respectively. Attention-Res2 merges multiple feature map parts with an Attention gate via skip connections, while Swin Transformer captures long-range dependencies and models the input… More >

Wenran Jia¹, Simin Ma¹, Peng Geng¹, Yan Sun^2,*

CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3393-3411, 2023, DOI:10.32604/cmc.2023.040091

Abstract Retinal vessel segmentation in fundus images plays an essential role in the screening, diagnosis, and treatment of many diseases. The acquired fundus images generally have the following problems: uneven illumination, high noise, and complex structure. It makes vessel segmentation very challenging. Previous methods of retinal vascular segmentation mainly use convolutional neural networks on U Network (U-Net) models, and they have many limitations and shortcomings, such as the loss of microvascular details at the end of the vessels. We address the limitations of convolution by introducing the transformer into retinal vessel segmentation. Therefore, we propose a hybrid method for retinal vessel… More >

Sayyid Kamran Hussain¹, Ali Haider Khan^2,*, Malek Alrashidi³, Sajid Iqbal⁴, Qazi Mudassar Ilyas⁴, Kamran Shah⁵

CMC-Computers, Materials & Continua, Vol.76, No.3, pp. 3763-3781, 2023, DOI:10.32604/cmc.2023.041722

Abstract As ocular computer-aided diagnostic (CAD) tools become more widely accessible, many researchers are developing deep learning (DL) methods to aid in ocular disease (OHD) diagnosis. Common eye diseases like cataracts (CATR), glaucoma (GLU), and age-related macular degeneration (AMD) are the focus of this study, which uses DL to examine their identification. Data imbalance and outliers are widespread in fundus images, which can make it difficult to apply many DL algorithms to accomplish this analytical assignment. The creation of effcient and reliable DL algorithms is seen to be the key to further enhancing detection performance. Using the analysis of images of… More >

Xuefei Chen¹, Wenhui Tan², Qiulan Wu^1,*, Feng Zhang¹, Xiumei Guo¹, Zixin Zhu¹

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 3143-3157, 2023, DOI:10.32604/iasc.2023.040903

Abstract In order to improve the accuracy and efficiency of Lentinula edodes logs contamination identification, an improved YOLOv5s contamination identification model for Lentinula edodes logs (YOLOv5s-CGGS) is proposed in this paper. Firstly, a CA (coordinate attention) mechanism is introduced in the feature extraction network of YOLOv5s to improve the identifiability of Lentinula edodes logs contamination and the accuracy of target localization. Then, the CIoU (Complete-IOU) loss function is replaced by an SIoU (SCYLLA-IoU) loss function to improve the model’s convergence speed and inference accuracy. Finally, the GSConv and GhostConv modules are used to improve and optimize the feature fusion network to… More >

Xu Yao^1,2, Chengjian Qiu¹, Yuqing Song¹, Zhe Liu^1,*

Intelligent Automation & Soft Computing, Vol.37, No.3, pp. 2583-2594, 2023, DOI:10.32604/iasc.2023.037205

Abstract As the pancreas only occupies a small region in the whole abdominal computed tomography (CT) scans and has high variability in shape, location and size, deep neural networks in automatic pancreas segmentation task can be easily confused by the complex and variable background. To alleviate these issues, this paper proposes a novel pancreas segmentation optimization based on the coarse-to-fine structure, in which the coarse stage is responsible for increasing the proportion of the target region in the input image through the minimum bounding box, and the fine is for improving the accuracy of pancreas segmentation by enhancing the data diversity… More >

Runlian Zhang^1,*, Rui Shu¹, Yongzhuang Wei¹, Hailong Zhang², Xiaonian Wu¹

CMC-Computers, Materials & Continua, Vol.76, No.2, pp. 1911-1927, 2023, DOI:10.32604/cmc.2023.041187

Abstract S-boxes can be the core component of block ciphers, and how to efficiently generate S-boxes with strong cryptographic properties appears to be an important task in the design of block ciphers. In this work, an optimized model based on the generative adversarial network (GAN) is proposed to generate 8-bit S-boxes. The central idea of this optimized model is to use loss function constraints for GAN. More specially, the Advanced Encryption Standard (AES) S-box is used to construct the sample dataset via the affine equivalence property. Then, three models are respectively built and cross-trained to generate 8-bit S-boxes based on three… More >