作者: Syed Saqib Bukhari , Faisal Shafait , Thomas M. Breuel
DOI: 10.1007/978-3-642-29364-1_10
关键词: Artificial intelligence 、 Content area 、 Page frame 、 Document image processing 、 Process (computing) 、 Noise removal 、 Digitization 、 Computer vision 、 Computer science 、 Noise (video) 、 Preprocessor
摘要: Camera-captured document images usually contain two main types of marginal noise: textual noise (coming from neighboring pages) and non-textual (resulting the page surrounding and/or binarization process). These degrade performance preprocessing (dewarping) camera-captured subsequent digitization/recognition processes. Page frame detection is one newly investigated areas in image processing, which used to remove border identify actual content area images. In this paper, we present a new technique for We use text non-text contents information find evaluate our algorithm on DFKI-I (CBDAR 2007 Dewarping Contest) dataset. Experimental results show effectiveness method comparison other state-of-the-art approaches.