2023 International Conference on Computer Graphics and Image Processing (CGIP)最新文献

Application of 3D Animation and Virtual Reality Technology in Digital Preservation of Religious Cultural Heritage 三维动画与虚拟现实技术在宗教文化遗产数字化保护中的应用

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00019

Chen Zhang

{"title":"Application of 3D Animation and Virtual Reality Technology in Digital Preservation of Religious Cultural Heritage","authors":"Chen Zhang","doi":"10.1109/CGIP58526.2023.00019","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00019","url":null,"abstract":"The continuous development of digital technology has provided new opportunities and means for preserving these treasures. The digital preservation of religious cultural heritage using 3D animation and virtual reality technology has become more effective and efficient in achieving this goal. In this context, this paper proposes a new digital preservation platform for religious cultural heritage, which is designed based on 3D animation and virtual reality technology. The platform offers an interactive and immersive experience to visitors, allowing them to explore and learn about the religious cultural heritage in a more engaging way. Moreover, the platform offers multiple benefits, such as easy accessibility, long-term preservation, and accurate representation of the heritage. Overall, the proposed platform is expected to enhance the digital preservation of religious cultural heritage and promote a deeper understanding and appreciation of these treasures among people. This paper emphasizes the importance of adopting new technologies and innovative approaches to address the challenges associated with the preservation of religious cultural heritage.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129988160","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

Oversampling Facial Motion Features Using the Variational Autoencoder to Estimate Oro-facial Dysfunction Severity 用变分自编码器对面部运动特征进行过采样以估计面部功能障碍的严重程度

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00013

Trassandra Jewelle Ipapo, Charlize Del Rosario, R. Alampay, P. Abu

{"title":"Oversampling Facial Motion Features Using the Variational Autoencoder to Estimate Oro-facial Dysfunction Severity","authors":"Trassandra Jewelle Ipapo, Charlize Del Rosario, R. Alampay, P. Abu","doi":"10.1109/CGIP58526.2023.00013","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00013","url":null,"abstract":"Class imbalance, which negatively affects classification model performance, is a common problem with machine learning. Various oversampling methods have been developed as potential solutions to compensate for imbalanced data. SMOTE is one of the more common methods employed. However, deep generative models such as the variational autoencoder are showing promise as alternatives to traditional oversampling methods. This study investigated the potential of variational autoencoders in learning the distribution of the minority class and producing new observations of facial motion features extracted from an imbalanced medical dataset as well as to see the effects of oversampling before and after the train-test split. The effectiveness of the variational autoencoder was compared to SMOTE in increasing ordinal classification performance across the metrics of accuracy, accuracy±1, inter-rater reliability, specificity, and sensitivity with no oversampling serving as the baseline. The results show that the variational autoencoder has potential as an oversampling method for facial motion features in the context of oro-facial dysfunction estimation. Oversampling prior to the train-test split was also shown to improve classification performance.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134457653","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

Using Monocular Depth Estimation for Distance Estimation in a Moving Vehicle 基于单目深度估计的移动车辆距离估计

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00012

Lanz Benedict N. De Guzman, Aaron Raymond See

{"title":"Using Monocular Depth Estimation for Distance Estimation in a Moving Vehicle","authors":"Lanz Benedict N. De Guzman, Aaron Raymond See","doi":"10.1109/CGIP58526.2023.00012","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00012","url":null,"abstract":"Accompanying the increase in demand for autonomous systems and robotic solutions is the increase in the relevance of various depth estimation technologies. Monocular Depth Estimation (MDE) is used to predict distances by generating depth maps using only a single RGB camera. However, without out-of-the-box calibration or ground truth reference for generated depth values from MDE models its use case in practical applications is limited. This research introduces a method of actualizing generated depth map values for different applications. The proposed system involves the utilization of machine vision using YOLO for object detection, followed by the computation of the lens optic algorithms to calculate the distance. Results demonstrated a real-time environment detection and depth estimation solution with more than 90% accuracy for measuring object depth in static environments. Furthermore, the system was also successfully tested in a moving vehicle to provide an estimated distance of surrounding vehicles. In the future, further tests will be done to improve the accuracy and calculation speed for use in car safety.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123944914","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

Research on Digital Image Information Security and Encryption Technology 数字图像信息安全与加密技术研究

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00023

Fengcong Guo

{"title":"Research on Digital Image Information Security and Encryption Technology","authors":"Fengcong Guo","doi":"10.1109/CGIP58526.2023.00023","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00023","url":null,"abstract":"The development mode of digital and Internet communication has contributed to the phenomenon of taking digital image as the information transmission carrier. Therefore, the transmission network and sending and receiving equipment of digital images are extremely easy to receive external intrusion and attacks, causing information leakage and other information security accidents. On the basis of the digital image features, the digital graphic encryption method and the defects of single feature encryption, further study the chaotic encryption technique of multiple angle encryption. Constructing a modified tesseract transform using chaotic sequence and mirror transform to dislocate the image, and performing a cyclic dissimilarity between the gray values of each pixel point and chaotic sequence to achieve diffusion and confusion between pixel points increases the complexity of the key and increases the number of keys. It makes the time required to crack increase. The algorithm design is simple and easy to implement, and the experimental simulation results conclude that the algorithm has the advantages of easy implementation, sensitivity to the perturbation of the initial conditions of the system, and large key space compared with the traditional chaotic encryption algorithm.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"10 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129112546","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 Development of the Korat Boxing Digital Museum with 3D Animation Using Inertial Motion Capture Techniques for Preserving the Ancient Martial Arts 利用惯性动作捕捉技术保存古代武术的三维动画Korat拳击数字博物馆的开发

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00018

Thawatphong Phithak, Kunlachat Thainchanam, Sorachai Kamollimsakul

{"title":"The Development of the Korat Boxing Digital Museum with 3D Animation Using Inertial Motion Capture Techniques for Preserving the Ancient Martial Arts","authors":"Thawatphong Phithak, Kunlachat Thainchanam, Sorachai Kamollimsakul","doi":"10.1109/CGIP58526.2023.00018","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00018","url":null,"abstract":"Korat Boxing or Muay Korat is a unique ancient martial art that originated in Nakhon Ratchasima, Thailand. Up to this point, there has been limited concrete effort to conserve knowledge of Muay Korat. Since knowledge of Muay Korat has mainly been transmitted person to person the general public has limited access or awareness. It is believed that knowledge of this distinct martial art is worth preserving before it becomes irretrievable. This research aims to 1) study and consolidate knowledge of Muay Korat in the form of digital media and 2) design and develop 3D animation of Muay Korat for a digital museum. The researcher used a inertial motion capture machine to record the movements of boxing teachers to create realistic 3D animations of Muay Korat moves, a total of 47 moves. After that, a digital museum was designed and developed which can be accessed via www.muaykorat.info. The digital museum was evaluated for usability testing, using a 5-point Likert scale questionnaire with 6 aspects. The questionnaire was completed by 70 people interested in sports. The results gave excellent scores for 3 aspects, including content and language use ${{(bar X = 4}}{text{.65)}}$; text ${{(bar X = 4}}{text{.65)}}$; and the animation and multimedia presentation ${{(bar X = 4}}{text{.56)}}$. The assessment result for all aspects ${{(bar X = 4}}{text{.53)}}$ implies that the usability of the Korat Boxing Digital Museum is very good. This result is consistent with the overall satisfaction assessment also being very good ${{(bar X = 4}}{text{.51)}}$. In addition, an assessment of the media exposure to digital museum users revealed that Korat Boxing Digital Museum could enhance knowledge and understanding about Korat Boxing at the highest level.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126478156","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 of Traffic Visual Communication Design Systems Using Moving Images 基于动态图像的交通视觉传达设计系统设计

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/cgip58526.2023.00015

Zao Sun

引用次数: 0

Review of Image guided radiotherapy 影像引导放射治疗综述

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00024

Wenxuan Li

引用次数: 0

Sponsors 赞助商

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/cgip58526.2023.00008

引用次数: 0

Laptop Appearance Defect Detection Based on Improved YOLOv5 Algorithm 基于改进YOLOv5算法的笔记本电脑外观缺陷检测

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00011

Zhenyu Yang, Xiaohui Yan, Liang Yu, Huijuan Zhu

{"title":"Laptop Appearance Defect Detection Based on Improved YOLOv5 Algorithm","authors":"Zhenyu Yang, Xiaohui Yan, Liang Yu, Huijuan Zhu","doi":"10.1109/CGIP58526.2023.00011","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00011","url":null,"abstract":"During the production of the shell of laptop and during the installation of the laptop its surface may be damaged by external factors. Therefore, its surface quality inspection is an essential and important part of the entire production process. At this stage, the detection of laptop appearance defects within the industry mainly relies on manual inspection, but manual inspection methods are inefficient and costly. In order to reduce the cost of manual labor, realize the intelligence of industrial production as well as improve the efficiency of inspection, in this paper, the YOLOv5 algorithm was used to create a deep learning model to investigate an effective method for detecting scratches defects on the appearance of laptops. In order to speed up the operation of the algorithm and improve the accuracy of the defect detection, the C3 module is used, and the activation function of the Conv module was modified, and the SiLU activation function was used instead of the Hardswish activation function; the experimental results show that the deep learning model trained with the improved YOLOv5 algorithm has a better performance for detecting the scratch defects on the appearance of laptops, not only accelerates the training speed of the model but also achieves an accuracy of 95.0% and a recall of 88%.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126595792","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

Saliency Network with Pyramidal Attention for Crack Detection 基于金字塔关注的裂纹检测显著性网络

2023 International Conference on Computer Graphics and Image Processing (CGIP) Pub Date : 2023-01-01 DOI: 10.1109/CGIP58526.2023.00017

Wenhao Guo, Xing Zhang, Fanyi Meng, Yi Li, Tian Lin, Dejin Zhang, Qingquan Li

{"title":"Saliency Network with Pyramidal Attention for Crack Detection","authors":"Wenhao Guo, Xing Zhang, Fanyi Meng, Yi Li, Tian Lin, Dejin Zhang, Qingquan Li","doi":"10.1109/CGIP58526.2023.00017","DOIUrl":"https://doi.org/10.1109/CGIP58526.2023.00017","url":null,"abstract":"Road crack is a common road disease and can endanger the safety of vehicular traffic. To solve the problem of the low accuracy of traditional deep neural networks in detecting crack images with more complex background and interference, this paper proposes a crack detection network (GLPANet) based on human visual cognitive mechanism. We construct three key modules for extracting crack image features extraction, namely Global Correspondence Modelling (GCM), Local Correspondence Modelling (LCM), and Pyramidal Attention Network (PANet). Specifically, GCM directly fuses all internal features outside through three-dimensional (3D) convolution, LCM also uses 3D convolution to decouple multi-image relationships into multiple local pairs (LP) of image correspondences. PANet learns the spatial geometry of cracks through a network of pyramidal attention mechanisms to create associations between crack features, in the PASCAL VOC dataset, PANet achieved a mean IoU of 77.92%, an 11.5% improvement over FCN-R101. In the crack dataset, with the mean absolute error (MAE) of 0.0172, GLPANet outperforms the state-of-the-art competitors. GLPANet network can improve the accuracy of fracture detection in complex and disturbed backgrounds.","PeriodicalId":286064,"journal":{"name":"2023 International Conference on Computer Graphics and Image Processing (CGIP)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125069778","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