Proceedings of the 6th International Conference on Advances in Image Processing最新文献_第3页

Transformer Network with Self-Supervised Learning for Stenosis Detection in CT Angiography 基于自监督学习的变压器网络在CT血管造影中的狭窄检测

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577147

Yonglin Bian, Danni Ai, Tao Han, Lu Lin, Jian Yang

{"title":"Transformer Network with Self-Supervised Learning for Stenosis Detection in CT Angiography","authors":"Yonglin Bian, Danni Ai, Tao Han, Lu Lin, Jian Yang","doi":"10.1145/3577117.3577147","DOIUrl":"https://doi.org/10.1145/3577117.3577147","url":null,"abstract":"Coronary artery stenosis is a common coronary artery disease (CAD) that may pose high risk to the life of patients. However, the poor imaging quality at lesions causes difficulties for automatic detection of stenosis in cardiac CT angiography. Previous supervised learning methods improve the robustness of detection by introducing networks with strong context modeling capabilities such as RNN and Transformer, yet requiring large-scale dataset for a high performance. In this paper, we propose a novel self-supervised Transformer network for stenosis detection in multi-planar reformatted (MPR) images reconstructed with the centerlines of the coronary arteries. A Transformer with cross-shaped attention, which can capture the global information of coronary branches efficiently in the MPR images, is introduced into the proposed network. Moreover, an auxiliary self-supervised learning task that encourages the Transformer network to learn spatial relations within an image is introduced. Extensive experiments are conducted on a dataset of 78 patients annotated by experienced radiologists. The results illustrate that the proposed method achieved better results in F1 (0.79) than other state-of-the-art methods.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129393611","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Lightweight 3D Segmentation Network for Abdominal Liver in CT Image 腹部肝脏CT图像的轻量级三维分割网络

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577139

Ju-ping Zhao, Tianlin Zhang, Ling Gao, Wenbo Wan, Jian Wang

{"title":"A Lightweight 3D Segmentation Network for Abdominal Liver in CT Image","authors":"Ju-ping Zhao, Tianlin Zhang, Ling Gao, Wenbo Wan, Jian Wang","doi":"10.1145/3577117.3577139","DOIUrl":"https://doi.org/10.1145/3577117.3577139","url":null,"abstract":"Abnormal liver function is linked to a variety of disorders. Precise and quick automatic liver segmentation can help clinicians make better diagnosis and treatment decisions. With the development of computer vision and deep learning approaches, there are more solutions for biomedical image segmentation tasks. In recent years, the U-Net architecture is by far the most widely used backbone architecture for biomedical image segmentation. Deep convolutional neural networks-based semantic segmentation has achieved sufficient accuracy. However, the scale of high-precision networks is growing, requiring an increasing amount of storage and computational resources. Furthermore, the deep neural network's operating time is lengthy, making it difficult to satisfy practical needs. As a result, the lightweight convolutional neural network design is used to the semantic segmentation task. As a consequence, in this article, a lightweight convolutional neural network is proposed to solve the aforementioned problems in the task of biomedical image segmentation. 3D U-Net is used as the backbone architecture and a modification of the Ghost module from GhostNet is introduced to boost up the effectiveness and the learning efficiency. The experimental results demonstrate that the proposed network improved the segmentation performance with fewer network parameters and requiring less floating-point computation.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"219 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121853556","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-Carrier Information Hiding Algorithm Based on GHM Multiwavelet Transform and Singular Value Decomposition 基于GHM多小波变换和奇异值分解的多载波信息隐藏算法

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577118

Shuai Ren, Qiuyu Feng, Meng Wang

{"title":"Multi-Carrier Information Hiding Algorithm Based on GHM Multiwavelet Transform and Singular Value Decomposition","authors":"Shuai Ren, Qiuyu Feng, Meng Wang","doi":"10.1145/3577117.3577118","DOIUrl":"https://doi.org/10.1145/3577117.3577118","url":null,"abstract":"Aiming at the problem that the single-carrier information hiding algorithm is limited by the number of carriers, and its capacity and security cannot be further broken through, a digital image multi-carrier information hiding algorithm based on Geronimo Hardin Massopus (GHM) and singular value decomposition (SVD) is proposed. Firstly, the digital image is classified based on the color histogram and LDP fusion characteristics of the digital image. Secondly, the GHM multiwavelet transform is applied and the information hiding area is selected according to the energy characteristics. Finally, while ensuring the correlation between images, the carrier image is slightly modified in combination with the stability of singular value to embed secret information. By applying GHM multiwavelet transform to the carrier image, the data is embedded in the subgraph with relatively low energy weight, which effectively improves the concealment and anti-analysis of the algorithm. Using the unique stability and rotation invariance of image singular value, it is slightly modified to embed secret information in the carrier image, reduce the embedding distortion and improve the robustness of the proposed algorithm. Experimental analysis shows that compared with the comparison algorithm, the advantage of the algorithm is that the invisibility PSNR value is increased by 27.05% and 9.46% on average. When facing the high-intensity composite attack of 30% shear, JPEG2000 compression and 33° counterclockwise rotation at the same time, the PSNR can reach 39.3274dB, and its invisibility and robustness have been significantly improved.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126519659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

The One-stop Intelligent Environmental Protection Community based on Image Processing Techniques 基于图像处理技术的一站式智能环保社区

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577122

Xinya Shu, Zihao Wang, Mingyang Cao, Yanqing Wang

{"title":"The One-stop Intelligent Environmental Protection Community based on Image Processing Techniques ","authors":"Xinya Shu, Zihao Wang, Mingyang Cao, Yanqing Wang","doi":"10.1145/3577117.3577122","DOIUrl":"https://doi.org/10.1145/3577117.3577122","url":null,"abstract":"In view of the spread of COVID-19 epidemic and many problems existing in the community, such as potential safety hazards, diluted interpersonal relationships, and out-of-place management, a system of one-stop intelligent environmental protection communities based on the Internet was proposed. It not only improves the ability of community staff, provides great convenience for residents and community workers, cares for vulnerable groups, and promotes a happy and harmonious neighborhood life, but also scores residents and staff while monitoring the community environment for safety with the technology application of thermal imaging recognition, PaddleHub-based face and mask recognition. This new system design is easy to implement at low cost and has a simple structure with many functions. The technologies for face and mask recognition proposed in this paper are based on PaddleHub. Experiments on MaskedFace-Net provided by Haute-Alsace University and the pretrained parameters loaded by PaddleHub showed that the accuracy rate with mask recognition was 94.3290 percent using this method.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117335037","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Spatial Pyramid Dynamic Graph Convolution Assisted Two-Stage U-Net for Retinal Layer and Optic Disc Segmentation in OCT Images 空间金字塔动态图卷积辅助两阶段U-Net在OCT图像视网膜层和视盘分割中的应用

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577141

Junying Zeng, Yingbo Wang, Weibin Luo, Yucong Chen, Chuanbo Qin, Yajin Gu, Huiming Tian, Yunxiong Chen

引用次数: 0

Intelligent monitoring drowning early warning system 智能监测溺水预警系统

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577120

Wei Wang, Zihao Wang, Qiantu Wang, Yanqing Wang

引用次数: 0

Knowledge Graph Tracing and Query System Based on Blockchain 基于区块链的知识图谱跟踪与查询系统

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577131

Chiyu Zhang, Yujia Liu, Zhiyi Zhang, Yanqing Wang

引用次数: 0

Image Comparison Research of Smart Electricity Meter 智能电表的图像对比研究

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577132

Yuan Ma, Zhuoliang Zhao, Ming Chen, Jia-zhong Guo, Senlin Lan, Yu-Nan Wang

{"title":"Image Comparison Research of Smart Electricity Meter","authors":"Yuan Ma, Zhuoliang Zhao, Ming Chen, Jia-zhong Guo, Senlin Lan, Yu-Nan Wang","doi":"10.1145/3577117.3577132","DOIUrl":"https://doi.org/10.1145/3577117.3577132","url":null,"abstract":"The standardization of the installation and operation and maintenance of the smart meter box is particularly important to ensure the reliable and safe operation and maintenance of the smart power system. The smart meter box is generally maintained by manual inspection, which requires experienced power professionals to judge the meter box. Status anomalies often lead to false negatives. With the development of fifth-generation mobile communication, machine learning and other technologies, operation and maintenance personnel can take on-site photos of the meter box through mobile devices and upload them to the cloud. The photos of regular inspections can be compared through the image analysis method based on machine learning to automatically determine whether the meter box is damaged. In this paper, target detection, image perspective transformation and adaptive local affine matching algorithm are combined. First, target detection is used to identify and locate the areas in the smart meter box that need to be compared, and the detected objects are cut into opposite subsections. Image, then transform the target to be determined through image perspective transformation, remove the area that does not need to be matched, and then use the adaptive local affine matching algorithm to calculate the similarity between each feature point according to the local features of the image. The accuracy of the image comparison process.","PeriodicalId":309874,"journal":{"name":"Proceedings of the 6th International Conference on Advances in Image Processing","volume":"229 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121978974","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Design and Implementation of a Dual-Modal Ranging System Using Joint Calibration method 基于联合标定方法的双峰测距系统设计与实现

Proceedings of the 6th International Conference on Advances in Image Processing Pub Date : 2022-11-18 DOI: 10.1145/3577117.3577119

Mingyu Gao, Qingfeng Jiang, Da Xu, Yi Chen, Junfan Wang, Huipin Lin

引用次数: 0