Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering最新文献

筛选

英文中文

A Self-service Visual Acuity Test Program Using Gesture Recognition 使用手势识别的自助视觉敏锐度测试程序

Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering Pub Date : 2021-11-12 DOI: 10.1145/3502871.3502891

Li Dong, Qianying Cai, Rongchao Peng

{"title":"A Self-service Visual Acuity Test Program Using Gesture Recognition","authors":"Li Dong, Qianying Cai, Rongchao Peng","doi":"10.1145/3502871.3502891","DOIUrl":"https://doi.org/10.1145/3502871.3502891","url":null,"abstract":"The visual acuity test is a common method to examine the visual function of the eyes, which is important for early detection and intervention of ophthalmic diseases such as myopia. However, the conventional visual test needs an examiner, often a doctor in hospital, to point at “E” characters in the visual chart for the examinee to recognize, which is unsuitable for home environment. Therefore, we designed a self-service visual test program for a single person to use alone at home. The program utilizes the computer screen to randomly display a visual icon and the built-in camera to capture the examinee's gestures. The gesture images are then processed in OpenCV. After skin color detection, inter-frame difference and centroid calculation, the change of the hand centroid is recognized as the direction of the hand movement, and the result of “match / mismatch” is determined, which is used to “zoom out / in” the visual icon in the next trial. After several trials, the final visual level is evaluated for the examinee. This program ran well in our lap-top computers and successfully recognized the gestures, with an average success rate of 75%. We think it is useful for self-service visual test in home environment.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125382899","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

Learning-based k-Space Weighted Image Contrast (L-KWIC) for Golden Angle Radial Dynamic MRI 基于学习的黄金角径向动态MRI k空间加权图像对比度(L-KWIC)

Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering Pub Date : 2021-11-12 DOI: 10.1145/3502871.3502875

Zhijun Wang, H. She, Yiping P. Du

引用次数: 0

Fine-Grained Classification of Colposcopic Images with Multi-Modality 多模态阴道镜图像的细粒度分类

Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering Pub Date : 2021-11-12 DOI: 10.1145/3502871.3502877

Yiming Wang, Yi Chen, Jialiang Lu, Song Li, Dan‐dan Wu

{"title":"Fine-Grained Classification of Colposcopic Images with Multi-Modality","authors":"Yiming Wang, Yi Chen, Jialiang Lu, Song Li, Dan‐dan Wu","doi":"10.1145/3502871.3502877","DOIUrl":"https://doi.org/10.1145/3502871.3502877","url":null,"abstract":"Computer aided diagnosis (CAD) has gained popularity in medical image processing over the last decade. As with image based manual diagnosis, CAD system should base its results on specific lesions. In the case of colposcopic images, two modalities are collected for diagnosis, namely Lugol’s Iodine (LI) and Acetic Acid (A). In practice, classification performance may suffer from barely distinguishable lesions in mono-modality. To tackle this problem, we present in this paper a framework with fine-grained strategy and further boost its performance with multi-modality. Specifically, our proposed framework consists of two branches, Local Lesion Branch and Global Branch, to implement a fine-grained strategy. Local Lesion Branch indicates existence and severity of lesion in different modalities on patch level. Global Branch extracts features on whole image level, and uses our proposed Cross Stage Modality Fusion (CSMF) Blocks to enable feature exchange and fusion between two modalities. Features from two branches are then concatenated for final prediction. We conduct experiments on clinical dataset of colposcopic images. The result shows that our method achieves an accuracy of 83.39%, outperforming mono-modal baseline model by over 7.24%.","PeriodicalId":253757,"journal":{"name":"Proceedings of the 2021 8th International Conference on Biomedical and Bioinformatics Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126128260","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

首页上一页