Robust outdoor text detection using text intensity and shape features Export

@inproceedings{citeulike:4455780, abstract = {Recognizing texts from camera images is a known hard problem because of the difficulties in text segmentation from the varied and complicated backgrounds. In this paper, we propose an algorithm that employs two novel filters and a basic component-based text detection framework. The framework uses the Niblack algorithm to threshold images and groups components into regions with commonly used geometry features. The intensity filter considers the overlap between the intensity histogram of a component and that of its adjoining area. For non-text regions, we have found that this overlap is large, and so we can prune out components with large values of this measure. The shape filter, on the other hand, deletes regions whose constituent components come from a same object, as most words consist of different characters. The proposed method is evaluated with the text locating database with 249 images used in the ICDAR2003 robust reading competition. The result shows that the algorithm is robust to both indoor images and outdoor images, even for the images of complex background, which usually is a hard factor to overcome for traditional component-based algorithms. In terms of performance statistics, we tested the algorithm on the ICDAR 2003 challenge experiment, and the algorithm achieves 66\% precision rate (p), 46\% recall rate (r), and 54\% the combined rate ( f ), which is the best reported in the literature on this dataset.}, author = {Liu, Zongyi and Sarkar, S.}, booktitle = {Pattern Recognition, 2008. ICPR 2008. 19th International Conference on}, citeulike-article-id = {4455780}, citeulike-linkout-0 = {http://dx.doi.org/10.1109/ICPR.2008.4761432}, citeulike-linkout-1 = {http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=4761432}, comment = {* Using local histogram similarity to separate text (comparing overlap between histogram of connected component with histogram of bounding box)}, doi = {10.1109/ICPR.2008.4761432}, journal = {Pattern Recognition, 2008. ICPR 2008. 19th International Conference on}, keywords = {ocr, text-localization}, pages = {1--4}, posted-at = {2009-05-03 22:58:24}, priority = {2}, title = {Robust outdoor text detection using text intensity and shape features}, url = {http://dx.doi.org/10.1109/ICPR.2008.4761432}, year = {2008} }

TY - CONF ID - citeulike:4455780 L3 - citeulike-article-id:4455780 N2 - Recognizing texts from camera images is a known hard problem because of the difficulties in text segmentation from the varied and complicated backgrounds. In this paper, we propose an algorithm that employs two novel filters and a basic component-based text detection framework. The framework uses the Niblack algorithm to threshold images and groups components into regions with commonly used geometry features. The intensity filter considers the overlap between the intensity histogram of a component and that of its adjoining area. For non-text regions, we have found that this overlap is large, and so we can prune out components with large values of this measure. The shape filter, on the other hand, deletes regions whose constituent components come from a same object, as most words consist of different characters. The proposed method is evaluated with the text locating database with 249 images used in the ICDAR2003 robust reading competition. The result shows that the algorithm is robust to both indoor images and outdoor images, even for the images of complex background, which usually is a hard factor to overcome for traditional component-based algorithms. In terms of performance statistics, we tested the algorithm on the ICDAR 2003 challenge experiment, and the algorithm achieves 66% precision rate (p), 46% recall rate (r), and 54% the combined rate ( f ), which is the best reported in the literature on this dataset. JF - Pattern Recognition, 2008. ICPR 2008. 19th International Conference on EP - 4 TI - Robust outdoor text detection using text intensity and shape features T2 - Pattern Recognition, 2008. ICPR 2008. 19th International Conference on SP - 1 KW - ocr KW - text-localization N1 - * Using local histogram similarity to separate text (comparing overlap between histogram of connected component with histogram of bounding box) AU - Liu, Zongyi AU - Sarkar, S PY - 2008/// UR - http://dx.doi.org/10.1109/ICPR.2008.4761432 ER -