视频类型分类:使用视觉描述符和多层感知器实时识别卡通

The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005. Pub Date : 2005-07-11 DOI:10.1109/ICACT.2005.246155

R. Glasberg, K. Elazouzi, T. Sikora

{"title":"视频类型分类:使用视觉描述符和多层感知器实时识别卡通","authors":"R. Glasberg, K. Elazouzi, T. Sikora","doi":"10.1109/ICACT.2005.246155","DOIUrl":null,"url":null,"abstract":"We present a new approach for classifying MPEG-video sequences as `cartoon' or `noncartoon' by analyzing specific color, texture and motion features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres like cartoon, commercial, music, news and sports are studied. Such applications have also been discussed in the context of MPEG-7 [T. Sikora et al. (2002)]. In our method the extracted features from the visual descriptors are nonlinear weighted with a sigmoid-function and afterwards combined using a multilayered perceptron to produce a reliable recognition. The results demonstrate a high identification rate based on a large collection of 100 representative video sequences (20 cartoons and 4*20 noncartoons) gathered from free digital TV-broadcasting","PeriodicalId":293442,"journal":{"name":"The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005.","volume":"51 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2005-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Video-genre-classification: recognizing cartoons in real-time using visual-descriptors and a multilayer-percetpron\",\"authors\":\"R. Glasberg, K. Elazouzi, T. Sikora\",\"doi\":\"10.1109/ICACT.2005.246155\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"We present a new approach for classifying MPEG-video sequences as `cartoon' or `noncartoon' by analyzing specific color, texture and motion features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres like cartoon, commercial, music, news and sports are studied. Such applications have also been discussed in the context of MPEG-7 [T. Sikora et al. (2002)]. In our method the extracted features from the visual descriptors are nonlinear weighted with a sigmoid-function and afterwards combined using a multilayered perceptron to produce a reliable recognition. The results demonstrate a high identification rate based on a large collection of 100 representative video sequences (20 cartoons and 4*20 noncartoons) gathered from free digital TV-broadcasting\",\"PeriodicalId\":293442,\"journal\":{\"name\":\"The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005.\",\"volume\":\"51 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2005-07-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005.\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICACT.2005.246155\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005.","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICACT.2005.246155","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}

引用次数: 3

摘要

通过实时分析连续帧的特定颜色、纹理和运动特征，提出了一种将mpeg视频序列分类为“卡通”或“非卡通”的新方法。这是众所周知的视频类型分类问题的一部分，该问题研究了流行的电视广播类型，如卡通、商业、音乐、新闻和体育。这些应用也在MPEG-7 [T]的背景下进行了讨论。Sikora et al.(2002)。在我们的方法中，从视觉描述符中提取的特征用s型函数进行非线性加权，然后使用多层感知器进行组合以产生可靠的识别。结果表明，基于从免费数字电视广播中收集的100个代表性视频序列(20个动画片和4*20个非动画片)的大量集合，具有很高的识别率

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

Video-genre-classification: recognizing cartoons in real-time using visual-descriptors and a multilayer-percetpron

We present a new approach for classifying MPEG-video sequences as `cartoon' or `noncartoon' by analyzing specific color, texture and motion features of consecutive frames in real-time. This is part of the well-known video-genre-classification problem, where popular TV-broadcast genres like cartoon, commercial, music, news and sports are studied. Such applications have also been discussed in the context of MPEG-7 [T. Sikora et al. (2002)]. In our method the extracted features from the visual descriptors are nonlinear weighted with a sigmoid-function and afterwards combined using a multilayered perceptron to produce a reliable recognition. The results demonstrate a high identification rate based on a large collection of 100 representative video sequences (20 cartoons and 4*20 noncartoons) gathered from free digital TV-broadcasting

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

The 7th International Conference on Advanced Communication Technology, 2005, ICACT 2005.

自引率

0.00%

发文量