Ka‐Hou Chan, S. Im, Vai-Kei Ian, Ka-Man Chan, W. Ke
{"title":"用于文本分类的增强空间变换网络","authors":"Ka‐Hou Chan, S. Im, Vai-Kei Ian, Ka-Man Chan, W. Ke","doi":"10.1145/3406971.3406981","DOIUrl":null,"url":null,"abstract":"This paper introduces a 2D transformation based framework for arbitrary-oriented text detection in natural scene images. We present the localization networks within Spatial Transformer Networks (STN), which are designed to generate proposals with text orientation affine information including translation, scaling and rotation. This information will then be adapted as learning parameters to make the proposals to be fitted into the text regular form in terms of the orientation more accurately. Localization network is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. Compared with any previous text detection systems, this work ensures the relationship between the learning parameters, which can lead to a better approximation for orientation. As a result, this new layer greatly enhances the training accuracy. Moreover, the design and implementation can be easily deployed in the current systems built upon the standard CNNs architecture.","PeriodicalId":111905,"journal":{"name":"Proceedings of the 4th International Conference on Graphics and Signal Processing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2020-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Enhancement Spatial Transformer Networks for Text Classification\",\"authors\":\"Ka‐Hou Chan, S. Im, Vai-Kei Ian, Ka-Man Chan, W. Ke\",\"doi\":\"10.1145/3406971.3406981\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"This paper introduces a 2D transformation based framework for arbitrary-oriented text detection in natural scene images. We present the localization networks within Spatial Transformer Networks (STN), which are designed to generate proposals with text orientation affine information including translation, scaling and rotation. This information will then be adapted as learning parameters to make the proposals to be fitted into the text regular form in terms of the orientation more accurately. Localization network is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. Compared with any previous text detection systems, this work ensures the relationship between the learning parameters, which can lead to a better approximation for orientation. As a result, this new layer greatly enhances the training accuracy. Moreover, the design and implementation can be easily deployed in the current systems built upon the standard CNNs architecture.\",\"PeriodicalId\":111905,\"journal\":{\"name\":\"Proceedings of the 4th International Conference on Graphics and Signal Processing\",\"volume\":\"2 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2020-06-26\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 4th International Conference on Graphics and Signal Processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3406971.3406981\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 4th International Conference on Graphics and Signal Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3406971.3406981","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Enhancement Spatial Transformer Networks for Text Classification
This paper introduces a 2D transformation based framework for arbitrary-oriented text detection in natural scene images. We present the localization networks within Spatial Transformer Networks (STN), which are designed to generate proposals with text orientation affine information including translation, scaling and rotation. This information will then be adapted as learning parameters to make the proposals to be fitted into the text regular form in terms of the orientation more accurately. Localization network is proposed to project arbitrary-oriented proposals to a feature map for a text region classifier. Compared with any previous text detection systems, this work ensures the relationship between the learning parameters, which can lead to a better approximation for orientation. As a result, this new layer greatly enhances the training accuracy. Moreover, the design and implementation can be easily deployed in the current systems built upon the standard CNNs architecture.