Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems最新文献_第2页

An Investigation about Optical Millimeter-wave Generation Technology 光毫米波产生技术研究

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416113

Xinyu Liu

引用次数: 1

Electric Vehicle Battery Swapping Station Design 电动汽车换电池站设计

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416105

Honghao Lu

引用次数: 0

A Deep Two-Stage Scheme for Polycrystalline Micro-Crack Detection 多晶微裂纹检测的深度两阶段方案

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416119

Sirui Chen, Shuo Shan, Liping Xie, Haikun Wei, Jinxia Zhang

{"title":"A Deep Two-Stage Scheme for Polycrystalline Micro-Crack Detection","authors":"Sirui Chen, Shuo Shan, Liping Xie, Haikun Wei, Jinxia Zhang","doi":"10.1145/3415048.3416119","DOIUrl":"https://doi.org/10.1145/3415048.3416119","url":null,"abstract":"Solar cell efficiency is one of the most concerned issues during the photovoltaic power generation. The existed micro-crack detection approaches mainly rely on manual work with the detection efficiency is low. Besides, there lacks exploration in algorithms for separating the region of damage without much workforce. In this paper, we propose a two-stage deep scheme, especially for the polycrystalline micro-crack detection method. A region of interest (ROI) proposal method based on the canny feature and the wavelet feature for micro-crack is raised. The computational efficiency and detection accuracy are greatly improved. Firstly, we split the original electroluminescent image (EL image) by its grid line and cut them into fixed-size squares. Then the ROI proposal method is applied to extract candidate boxes as the inputs of the second stage. At the second stage, a modified convolution neural network based on the candidate boxes is supervised by binary labels. Our experimental results demonstrate that our polycrystalline micro-crack detection scheme outperforms other traditional frameworks. This work is the first attempt to solve engineering problems about micro-crack by deep learning techniques in photovoltaic systems, without many high-quality labels and computing power.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122912309","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: 2

Detection and Recognition of Skin Cancer in Dermatoscopy Images 皮肤镜图像中皮肤癌的检测与识别

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416111

Ying Qian, Shuo Zhao

{"title":"Detection and Recognition of Skin Cancer in Dermatoscopy Images","authors":"Ying Qian, Shuo Zhao","doi":"10.1145/3415048.3416111","DOIUrl":"https://doi.org/10.1145/3415048.3416111","url":null,"abstract":"Melanoma and basal-cell carcinoma (BCC) are the two most common skin cancers, the death rate of melanoma is very high. If melanoma can be diagnosed early, the survival rate of patients will be greatly improved. But nevus and melanoma have similar appearances and symptoms. In order to reduce the cost for doctors to diagnose skin cancer, we proposed a computer-aided diagnostic system (CAD) that detects and identifies melanoma, nevus, and BCC in dermoscopy images. Firstly, use the hair removal algorithm, Gaussian filter and Wiener filter to remove the noise; Secondly, use the otsu to obtain the lesion area; then extract the texture and color features from the lesion area and use multiset discriminant correlation analysis (MDCA) to fuse the extracted features; finally, skin cancer is classified into melanoma, nevus, and BCC by KNN classification. Our aim is to select suitable features, test the effectiveness of MDCA, and compare the classification results with the methods in recent years. The improved algorithm was tested on the ISIC dataset, which included 469 images of melanoma, 127 images of basal cell carcinoma and 412 images of nevus. Compared with the methods in recent years, the selected features in this study combine with the MDCA method can improve the accuracy rate by 10.34%.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128822170","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: 3

Fault Diagnosis of Remainders Inside PIGA Based on Pattern Recognition Algorithm 基于模式识别算法的PIGA内部余数故障诊断

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416117

Lan Yue, Hu Zhou, R. Duan

引用次数: 2

Multi-Exposure Image Fusion Method Based on Independent Component Analysis 基于独立分量分析的多曝光图像融合方法

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416099

Ying Huang, K. Yao

{"title":"Multi-Exposure Image Fusion Method Based on Independent Component Analysis","authors":"Ying Huang, K. Yao","doi":"10.1145/3415048.3416099","DOIUrl":"https://doi.org/10.1145/3415048.3416099","url":null,"abstract":"Aiming at the problems that some detailed information cannot be effectively retained and the color is distorted in MEF (multi-exposure image fusion), this paper proposes a MEF method combining with signal decomposition. In this method, the process of decomposing signals using ICA (independent component analysis) is added to the HybridHDR algorithm. The key to MEF is the fusion of the luminance channel, so different fusion methods are used for the luminance channel and the chrominance channel. Because the details under different brightness conditions are different, this paper expands the images of different brightness into a set of one-dimensional signals, and uses ICA to perform signal decomposition, so that more details are extracted and retained in the final resulting image. Then combine HybridHDR and ICA to further extract the details in the multiple-exposure image, thereby improving the quality of the fused image. Experimental results show that the proposed method can improve the overall quality of the final fusion result, and in some scenes, it has more prominent detail retention ability than other existing methods, while still maintaining the color of the original exposure image.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129830112","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: 3

A Multilevel Fire Detection Platform Based on Multi-Source Heterogeneous Information Fusion 基于多源异构信息融合的多层次火灾探测平台

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416120

Bicheng Hua, Kanjian Zhang, Haikun Wei, Jinxia Zhang, Liping Xie

引用次数: 1

Accurate Iris Segmentation for at-a-distance Acquired Iris/Face Images under Less Constrained Environment 非约束环境下近距离虹膜/人脸图像的精确分割

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3415049

Chun-Wei Tan, Stella Tabora Domingo

{"title":"Accurate Iris Segmentation for at-a-distance Acquired Iris/Face Images under Less Constrained Environment","authors":"Chun-Wei Tan, Stella Tabora Domingo","doi":"10.1145/3415048.3415049","DOIUrl":"https://doi.org/10.1145/3415048.3415049","url":null,"abstract":"Iris recognition for at-a-distance acquired iris images under less constrained environment has shown to be challenging due to highly imaging variations such as reflections, motion blur, occlusions etc. This poses challenges for conventional gradient-based iris segmentation methods which are essentially developed to work on high quality iris images acquired in a controlled environment. In this work, we propose an effective encoder-decoder Deep Convolutional Neural Network which can be trained end-to-end to perform iris segmentation for distantly acquired iris/face images. More specifically, the proposed approach is motivated by the recent state-of-the-art semantic segmentation approach -- DeepLabv3/3+. The encoder module adapts the ResNet-50 as base network and extended with additional blocks constructed using multi-grid atrous convolution, and Atrous Spatial Pyramid Pooling to capture multi-scale features, which can better accommodate the segmentation of iris at different scales. To facilitate recovering of the spatial information, refinement module is introduced in the decoder module. We demonstrate the effectiveness of the proposed approach on two public datasets, i.e., UBIRIS.v2 and FRGC, which achieves average improvement of 37.42% and 48.9%, respectively. The trained model is made publicly available at https://gitlab.com/cwtan501/iris_segmentation to encourage reproducible of the reported results.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"67 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114114986","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: 1

Research on Image Enhancement Algorithm Base on Convolutional Neural Network in Scotopic Vision Environment 暗域视觉环境下基于卷积神经网络的图像增强算法研究

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416109

Ying Zhao, Lingyun Gao, Lijuan Xiang, Qin Zhang, Zhiqiang Zhao

{"title":"Research on Image Enhancement Algorithm Base on Convolutional Neural Network in Scotopic Vision Environment","authors":"Ying Zhao, Lingyun Gao, Lijuan Xiang, Qin Zhang, Zhiqiang Zhao","doi":"10.1145/3415048.3416109","DOIUrl":"https://doi.org/10.1145/3415048.3416109","url":null,"abstract":"The limitation of human visual contrast resolution makes it impossible that people to clearly distinguish the image information obtained in the scotopic vision environment. In view of the low brightness, unclear content and low contrast of the image obtained in the scotopic vision environment, an image enhancement algorithm based on convolutional neural network is proposed. First, the image data sets required for experimental training are captured by image acquisition equipment. Secondly, using the algorithm principle of the GAN network, to construct a convolutional neural network model, and the obtained image is input into an image generation network can get an enhanced image, where the input image includes an image in a scotopic vision environment and its brightness channel image, the image generation network is structured by an autoencoder network, and then according to the characteristics of the image to constructed different loss functions. Theoretical analysis and experimental results show that the enhancement effect of traditional image enhancement algorithm on these images is very limited, while image enhancement using convolutional neural network can ensure the accuracy of the algorithm and achieve a good effect. The method in this paper obviously improves the scotopic vision environment image visual effect, make the image clearer, meets the requirements of people to the naked eye to watch.","PeriodicalId":122511,"journal":{"name":"Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123505164","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: 2

Non-reference Image Quality Assessment for Contrast Distortion Based on Pixel Statistics and Color 基于像素统计和颜色的对比度失真非参考图像质量评估

Proceedings of the 2020 International Conference on Pattern Recognition and Intelligent Systems Pub Date : 2020-07-30 DOI: 10.1145/3415048.3416106

Ying Huang, Bai‐Cheng Li, Meilan Jiang

引用次数: 0