Kai Chen, Cheng-Lin Liu, Mathias Seuret, M. Liwicki, J. Hennebert, R. Ingold
{"title":"基于无监督特征学习的超像素分类历史文档图像页面分割","authors":"Kai Chen, Cheng-Lin Liu, Mathias Seuret, M. Liwicki, J. Hennebert, R. Ingold","doi":"10.1109/DAS.2016.13","DOIUrl":null,"url":null,"abstract":"In this paper, we present an efficient page segmentation method for historical document images. Many existing methods either rely on hand-crafted features or perform rather slow as they treat the problem as a pixel-level assignment problem. In order to create a feasible method for real applications, we propose to use superpixels as basic units of segmentation, and features are learned directly from pixels. An image is first oversegmented into superpixels with the simple linear iterative clustering (SLIC) algorithm. Then, each superpixel is represented by the features of its central pixel. The features are learned from pixel intensity values with stacked convolutional autoencoders in an unsupervised manner. A support vector machine (SVM) classifier is used to classify superpixels into four classes: periphery, background, text block, and decoration. Finally, the segmentation results are refined by a connected component based smoothing procedure. Experiments on three public datasets demonstrate that compared to our previous method, the proposed method is much faster and achieves comparable segmentation results. Additionally, much fewer pixels are used for classifier training.","PeriodicalId":197359,"journal":{"name":"2016 12th IAPR Workshop on Document Analysis Systems (DAS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2016-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"29","resultStr":"{\"title\":\"Page Segmentation for Historical Document Images Based on Superpixel Classification with Unsupervised Feature Learning\",\"authors\":\"Kai Chen, Cheng-Lin Liu, Mathias Seuret, M. Liwicki, J. Hennebert, R. Ingold\",\"doi\":\"10.1109/DAS.2016.13\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this paper, we present an efficient page segmentation method for historical document images. Many existing methods either rely on hand-crafted features or perform rather slow as they treat the problem as a pixel-level assignment problem. In order to create a feasible method for real applications, we propose to use superpixels as basic units of segmentation, and features are learned directly from pixels. An image is first oversegmented into superpixels with the simple linear iterative clustering (SLIC) algorithm. Then, each superpixel is represented by the features of its central pixel. The features are learned from pixel intensity values with stacked convolutional autoencoders in an unsupervised manner. A support vector machine (SVM) classifier is used to classify superpixels into four classes: periphery, background, text block, and decoration. Finally, the segmentation results are refined by a connected component based smoothing procedure. Experiments on three public datasets demonstrate that compared to our previous method, the proposed method is much faster and achieves comparable segmentation results. Additionally, much fewer pixels are used for classifier training.\",\"PeriodicalId\":197359,\"journal\":{\"name\":\"2016 12th IAPR Workshop on Document Analysis Systems (DAS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2016-04-11\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"29\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2016 12th IAPR Workshop on Document Analysis Systems (DAS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/DAS.2016.13\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2016 12th IAPR Workshop on Document Analysis Systems (DAS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DAS.2016.13","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Page Segmentation for Historical Document Images Based on Superpixel Classification with Unsupervised Feature Learning
In this paper, we present an efficient page segmentation method for historical document images. Many existing methods either rely on hand-crafted features or perform rather slow as they treat the problem as a pixel-level assignment problem. In order to create a feasible method for real applications, we propose to use superpixels as basic units of segmentation, and features are learned directly from pixels. An image is first oversegmented into superpixels with the simple linear iterative clustering (SLIC) algorithm. Then, each superpixel is represented by the features of its central pixel. The features are learned from pixel intensity values with stacked convolutional autoencoders in an unsupervised manner. A support vector machine (SVM) classifier is used to classify superpixels into four classes: periphery, background, text block, and decoration. Finally, the segmentation results are refined by a connected component based smoothing procedure. Experiments on three public datasets demonstrate that compared to our previous method, the proposed method is much faster and achieves comparable segmentation results. Additionally, much fewer pixels are used for classifier training.