Tensor representation learning based image patch analysis for text identification and recognition. Issue 4 (April 2015)

• Record Type: Journal Article
• Authors: Zhong, Guoqiang; Cheriet, Mohamed
• Is Part Of: Pattern recognition. Volume 48:Issue 4(2015:Apr.)
• Page Start: 1207
• Page End: 1220
• Publication Date: 2015-04
• Subjects: Pattern perception -- Periodicals; Perception des structures -- Périodiques; Patroonherkenning; 006.4
• DOI: 10.1016/j.patcog.2014.09.025
• Languages: English
• ISSNs: 0031-3203

Abstract

<abstract abstract-type="author" id="ab0005"> <title id="sect0005">Abstract</title> <sec> <p id="sp0075">In this paper, we introduce a novel framework for text identification and recognition, called tensor representation learning based image patch analysis (TRL-IPA). Unlike most of previous text identification approaches, which can only be applied to binarized images, TRL-IPA can be directly applied to <italic>gray level</italic> and <italic>color</italic> images. TRL-IPA is built on a general formulation of the <italic>convergent tensor representation learning</italic> (CTRL) algorithms. In the implementation of TRL-IPA, image patches are represented in the form of tensors, while low dimensional representations of these tensors are learned via a CTRL algorithm. To identify text regions in new coming document images, a <italic>random forest</italic> classifier is trained in the learned tensor subspace. Moreover, the TRL-IPA framework can be straightforwardly applied to recognition problems, such as handwritten digits recognition. We conducted extensive experiments on <italic>ancient Chinese, Arabic and Cyrillic</italic> document images, to evaluate TRL-IPA on text identification tasks. Experimental results demonstrate its effectiveness and robustness. In addition, recognition results on images of handwritten digits show its advantage over state-of-the-art <italic>vector and tensor representation</italic> based approaches.</p> </sec> </abstract>