A machine-learning approach for analyzing document layout structures with two reading orders
學年 97
學期 1
出版(發表)日期 2008-10-01
作品名稱 A machine-learning approach for analyzing document layout structures with two reading orders
作品名稱(其他語言)
著者 Wu, Chung-Chih; Chou, Chien-Hsing; Chang, Fu
單位 淡江大學電機工程學系
出版者 Kidlington: Pergamon
著錄名稱、卷期、頁數 Pattern Recognition 41(10), pp.3200-3213
摘要 The purpose of document layout analysis is to locate textlines and text regions in document images mostly via a series of split-or-merge operations. Before applying such an operation, however, it is necessary to examine the context to decide whether the place chosen for the operation is appropriate. We thus view document layout analysis as a matter of solving a series of binary decision problems, such as whether to apply, or not to apply, a split-or-merge operation to a chosen place. To solve these problems, we use support vector machines to learn whether or not to apply the previously mentioned operations from training documents in which all textlines and text regions have been located and their identifies labeled. The proposed approach is very effective for analyzing documents that allow both horizontal and vertical reading orders. When applied to a test data set composed of eight types of layout structure, the approach's accuracy rates for identifying textlines and text regions are 98.83% and 96.72%, respectively.
關鍵字 Binary decision;Document layout analysis;Reading order;Support vector machine;Taboo box;Textline;Text region
語言 en
ISSN 0031-3203
期刊性質 國外
收錄於
產學合作
通訊作者 Chang, Fu
審稿制度
國別 GBR
公開徵稿
出版型式 ,紙本
相關連結

機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/92967 )

機構典藏連結