Automatic text location in complex color images using local color quantization

An efficient text location method in complex color images is proposed. To deal with characters on complex background colors, local color quantization is done separately for each color instead of all colors. A candidate text line is extracted merging connected components and confirmed using heuristics based on color profile. I tested the proposed method on complex book cover images and it is shown to be successful in extracting texts in complex color images.

[1]  Tim Ritchings,et al.  Representation and classification of complex-shaped printed regions using white tiles , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[2]  Anil K. Jain,et al.  Locating text in complex color images , 1995, Pattern Recognit..

[3]  Anil K. Jain,et al.  Automatic text location in images and video frames , 1998, Proceedings. Fourteenth International Conference on Pattern Recognition (Cat. No.98EX170).

[4]  Hang Joon Kim,et al.  Automatic recognition of a car license plate using color image processing , 1994, Proceedings of 1st International Conference on Image Processing.

[5]  Tim Ritchings,et al.  Flexible page segmentation using the background , 1994, Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5).

[6]  Masaharu Ozaki.  Column segmentation by white space pattern matching , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[7]  Luc Vincent,et al.  Ground-truthing and benchmarking document page segmentation , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[8]  Luc M. Vincent,et al.  Benchmarking page segmentation algorithms , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[9]  C. Viard-Gaudin,et al.  A background based adaptive page segmentation algorithm , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[10]  Hae-Kwang Kim,et al.  Efficient Automatic Text Location Method and Content-Based Indexing and Structuring of Video Database , 1996, J. Vis. Commun. Image Represent..