2022 7th International Conference on Image, Vision and Computing (ICIVC)最新文献

{"title":"IBR-Yolov5: Illegal Building Recognition with UAV Image Based on Improved YOLOv5","authors":"Yang Liu, Yong-Ju Yu, Ruiwei Gao, Yuwei Wang, Yufeng Lin, Weiye Wang","doi":"10.1109/ICIVC55077.2022.9886827","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886827","url":null,"abstract":"The urban illegal buildings have seriously disrupted the urban land planning and development space, even having serious security risks. How accurately and comprehensively identifying the illegal buildings is very important for their management and planning. The traditional method of identifying illegal buildings is inefficient and high consumption. Learning-based methods can improve efficiency and save resources but a high miss rate. In response to the above problem, this paper proposes an illegal building recognition method based on UAV (Unmanned Aerial Vehicle) images: IBR-Yolov5 (Illegal Building Recognition with UAV Image Based on Improved YOLOv5). IBR-Yolov5 appends SPP (Spatial Pyramid Pooling) based on stochastic pooling to the Backbone module. Meanwhile, CBAM(Convolutional Block Attention Module) is used to highlight the main features and suppress irrelevant features, which can ultimately improve the detection accuracy of IBR-Yolov5. In addition, IBR-Yolov5 combined with BiFPN (Bidirectional Feature Pyramid Network) can fuse features extracted by different layers of networks to reduce feature loss. Experimental results show that the miss detection rate of the proposed improved model is lower in comparison with the original YOLOv5, and detection precision has been improved.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115380752","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}

{"title":"CAU: A Consensus Model of Augmented Unlabeled Data for Medical Image Segmentation","authors":"Wenli Cheng, Jiajia Jiao","doi":"10.1109/ICIVC55077.2022.9886218","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886218","url":null,"abstract":"Medical image segmentation plays an important role in medical diagnosis and treatment. However, medical image data are more expensive and time-consuming to obtain than ordinary image data. In this paper, we propose a novel semi-supervised method named CAU for medical image segmentation, which can easily use Convolutional Neural Networks (CNNs) to segment 2D images. The network learns through a combination of common supervision losses for labeled data and losses for unlabeled data. Specifically, we augment the unlabeled data strongly and weakly and send them to the student model and the teacher model respectively. We take full advantage of unlabeled data learning through a novel combination of minimizing the difference between network predictions for different data augmentation processing scenarios and using an unsupervised loss of min-entropy on the outputs of the two networks. In order to improve the regularization effect, we use the teacher-student model to optimize the teacher model by averaging the student model weights. Experiments show that our method in labeled data experiments with 5%, 10%,35% and 50% labeled data on Automated Cardiac Diagnosis Challeng(ACDC) dataset exceeds the fully supervised algorithm using the same amount of data and the existing popular semi-supervised learning algorithms 1.922% ~ 4.451%(Dice),0.841 ~ 5.031(Asd) and 0.06 ~ 1.116(HD95), respectively, and the Dice index exceeds the fully supervised algorithm 0.019% with 50% labeled data, which verifies its effectiveness in medical image segmentation.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"499 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123156647","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}

{"title":"Primate Recognition System Design Based on Deep Learning Model VGG16","authors":"Chen Ziyue, Gao Yuanyuan","doi":"10.1109/ICIVC55077.2022.9886310","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886310","url":null,"abstract":"The study of primate recognition is of great significance to the survival of primates. Nowadays, animal classification system plays an indispensable role in primate classification and species research. China has a vast territory, there are a variety of rare primates, such as: golden monkey, white-headed langurs, macaques, etc., the primate recognition system mentioned in this paper provides convenience for the classification and recognition of primates. Artificial visual recognition not only has a high error rate, but also fails to recognize primate photos that have lost most of their details. Primate recognition systems can also accurately recognize and classify images that have lost most of their details. This paper is based on VGG16 deep learning network development, detailed neural network training and call process, and neural network recognition accuracy and loss function are analyzed, and use PyQt5 and QT Designer for visual interface design, to better realize human-computer interaction. The design is completed and the system is tested and the results are analyzed.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"65 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122977402","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}

{"title":"Microwave Breast Imaging Based on Deep Learning","authors":"Lichun Wang, Zerui Hai, Ya Lu, Kunkun Wang, Qian Wang, Xiaoling Zhou, Zhaoxia Zhang","doi":"10.1109/ICIVC55077.2022.9886729","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886729","url":null,"abstract":"In order to address the problems of high computing cost and inability to real-time imaging in the traditional iterative methods of microwave breast imaging, a composite autoencoder network is proposed in this paper. It reconstructs the images from the scattered field arrays obtained by illuminating the breast dielectric constant images with antennas. The composite autoencoder network consists of two networks, the first being an autoencoder that mainly compresses high-resolution breast permittivity images into 256×3 vectors. The second neural network maps the scattered field arrays to compressed features 256×3, which are upsampled to high- resolution images. In this paper, a number of realistic breast phantoms are used to obtain a two-dimensional breast permittivity image dataset by slicing 3-D phantoms with a thickness of 2 mm. The proposed network can achieve real-time imaging compared to the improved traditional iterative method.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123018980","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}

{"title":"Textile Defect Detection Algorithm Based on Unsupervised Learning","authors":"Daitao Wang, Wenjing Yu, Peiyin Lian, Mingjun Zhang","doi":"10.1109/ICIVC55077.2022.9887216","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9887216","url":null,"abstract":"In order to solve the problem of lack of sample data and high cost of dataset due to the large number of abnormal samples and high-precision marking data required by current deep learning algorithms in textile defect detection, a pixel-level real-time defect detection scheme based on autoencoder and morphology was proposed in this paper. Algorithm is innovation in that can carry on the network training by unsupervised learning, as opposed to supervised learning needs a large number of high-precision marking abnormal samples, the algorithm relies on the dataset is only normal sample data, and no need to tag samples. In addition to reducing the production cost of large dataset, textile defects of various sizes can be detected in real-time at the pixel level. The algorithm steps are described as follows: First, the normal textile image is input into the network for encoding and decoding, and the underlying feature information of textile image is learned and reconstructed into a new image. Secondly, the encoding and decoding stages were combined horizontally to obtain better fitting effect. By subtracting the input image from the reconstructed image, the difference matrix of the input image and the reconstructed image was obtained to obtain the range of the defect area. Finally, Dilate, Median Filtering and Edge Detection are used to amplify and denoise the features of the defect region to obtain the final accurate defect region. The experimental results show that the scheme can effectively detect textile defects in real-time at pixel-level only when normal samples are used as dataset. Compared with supervised learning based algorithms such as RCNN and YOLO, this scheme only needs normal samples as dataset to carry out network training, which greatly reduces the cost of making dataset. Besides, Accuracy and F1-score can both reach over 0.95 in 4 different textile datasets, and its FPS is 36.2. Meet the requirements of real-time detection. The code and models will be made publicly available at https://github.com/hanknewbird/anomaly-detection.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129505504","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}

{"title":"An Algorithm for Detecting the Discontinuous Areas in Interferometric Phase Images","authors":"H. Hongxing, Yu Ronghuan, Hu Huaquan, Guo Jing","doi":"10.1109/ICIVC55077.2022.9887265","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9887265","url":null,"abstract":"Interferometric measurements have been widely used in medical diagnosing and geographic mapping. The detection of discontinuous areas in interferometric phase images is very significant for subsequent processing (such as denoising, unwrapping, and so on). In this paper, the Wrapped Laplace Transform is proposed to adapt the edge detection methods to the characteristics of the interferometric phase image. Thresholding is committed to the transformation results to generate the preliminary detection results of the discontinuous area. Then the detected discontinuous areas are restored by dilation and erosion. The experimental results show that the proposed algorithm in this paper can effectively detect discontinuous areas in the interference phase image, while avoiding the effects of interference fringes.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128554330","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}

{"title":"Identification of Papilionidae Species in Yunnan Province Based on Deep Learning","authors":"Min Fan, Ying Lu, Q. Xu, Han-Qing Zhang, Jumei Chang, Weijie Deng","doi":"10.1109/ICIVC55077.2022.9886389","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886389","url":null,"abstract":"Yunnan is known as the \"Hometown of Butterflies\" in China. The colorful and morphological diversity of the Papilioidae in Yunnan province is the subject of insect ecology and evolution research. At the same time, the Yunnan Papilio has great ornamental value. It is of great significance to accurately identify the species of Papilionidae in Yunnan Province. At present, Yunnan Papilio has not been classified in the related research on butterfly identification using deep learning methods, and there is a situation that the sample data set between species is small and the number is unbalanced, which may cause the model to fail to learn the morphological characteristics of butterflies. In response to the above problems, this study established a data set consisting of 12,956 original images of papilionidae from Yunnan Province, including two subfamilies, 12 genera and 80 species. Five deep learning network models (VGG-19, ResNet-34, ResNet-50, ResNet-101 and DenseNet-121) were explored from the perspective of prediction accuracy and loss value by transfer learning method. And modeling effects of SGD, Adam, Adamax and RMsprop optimization algorithms. The final data set adopts balanced sampling and 11 data enhancement methods for data fusion to expand the data set to 16,000 images. The ResNet-50 network structure optimized by Adamax algorithm is selected to achieve the optimal effect. The experimental results show that the recognition accuracy of ResNet-50 in the constructed model reaches 87.47%. The study provides a basis for constructing a visual recognition model of Papilioidae in Yunnan and applying it to the mobile terminal, and provides a fast and efficient new method for species identification of Papillidae in Yunnan. (Abstract)","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129139552","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}

{"title":"Near-Infrared Image Colorization with Weighted UNet++ and Auxiliary Color Enhancement GAN","authors":"Sicong Zhou, S. Kamata","doi":"10.1109/ICIVC55077.2022.9887040","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9887040","url":null,"abstract":"We propose a novel GAN-based method for near-infrared image colorization. This method innovatively rebalances the color of the colorization image by importing a luminance channel and a feature weight-driven color generator. We set the weighted UNet++ structure in the generator for colorization results with the detail of focal objects. A color enhancement network composed of a deeper luminance network and a colorimetric network is used for global color balance to improve the color quality of the generated color images. Our network is trained and evaluated on two datasets. According to the FID, SSIM and PSNR results, our network performs well, with good recovery effects for both overall color and detailed color and outperforming the current state-of-the-art methods.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129226261","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}

{"title":"Light-Field Depth Estimation Using RNN and CRF","authors":"Zhan Shi, Shengnan Zheng, Xiaohua Huang, Mengxi Xu, Lei Han","doi":"10.1109/ICIVC55077.2022.9886991","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886991","url":null,"abstract":"Convolutional Neural Networks (CNNs) have recently been successfully applied to depth estimation from light field. Different from those CNN-based methods, we utilize the sequence characteristics of Epipolar Plane Images (EPIs) and introduce a novel light-field depth estimation method based on the Recurrent Neural Network (RNN). Our network builds upon two-stages architectures, involving a local depth estimation and a depth refinement part. In the first part, we regard an EPI patch as a vector sequence which is fed into the RNN to obtain a local depth value. Then, guided by the theory of Conditional Random Field (CRF), we globally optimize the depth map in the second part. Our network was trained in the disparity truth values provided by the synthetic light-field dataset. Experimental results show that our method allows to estimate high-quality disparity results.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123911384","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}

{"title":"Review of Human Violence Recognition Algorithms","authors":"Youshan Zhang, Shaozhe Guo, Yong Li","doi":"10.1109/ICIVC55077.2022.9886081","DOIUrl":"https://doi.org/10.1109/ICIVC55077.2022.9886081","url":null,"abstract":"Violent behavior recognition is a specific research direction of human behavior recognition. Published reviews mainly focuses on the development of deep learning in the field of behavior recognition, and the attention to violent behavior recognition is low. According to the different methods used, this paper analyzes various algorithms from the perspective of violence recognition based on manual descriptor and deep learning, and introduces the commonly used datasets. Finally, the characteristics of different models and algorithms are summarized, and discuss potential problems and future work in the field of violence recognition.","PeriodicalId":227073,"journal":{"name":"2022 7th International Conference on Image, Vision and Computing (ICIVC)","volume":"423 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124216972","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}