Address block location on envelopes using Gabor filters: supervised method

The authors have implemented a texture-based supervised segmentation method to identify potential destination address blocks in envelope images. Texture features are computed by using a set of even symmetric Gabor filters. A one-layer neural network classifier is used to classify pixels into text and non-text categories using four texture features. The authors also present a simple heuristic to select the correct destination address block from among several candidates identified. The method works well on several envelope images.<<ETX>>

[1]  Azriel Rosenfeld,et al.  Address location on envelopes , 1987, Pattern Recognit..

[2]  Graham Leedham,et al.  Preprocessing and presorting of envelope images for automatic sorting using OCR , 1990, Pattern Recognit..

[3]  Sargur N. Srihari,et al.  Object recognition in visually complex environments: an architecture for locating address blocks on mail pieces , 1988, [1988 Proceedings] 9th International Conference on Pattern Recognition.

[4]  Alan C. Bovik,et al.  Experiments in segmenting texton patterns using localized spatial filters , 1989, Pattern Recognit..

[5]  Anders Krogh,et al.  Introduction to the theory of neural computation , 1994, The advanced book program.

[6]  Anil K. Jain,et al.  Address block location on envelopes using Gabor filters , 1992, Pattern Recognit..

[7]  Anil K. Jain,et al.  Unsupervised texture segmentation using Gabor filters , 1990, 1990 IEEE International Conference on Systems, Man, and Cybernetics Conference Proceedings.

[8]  Sargur N. Srihari,et al.  Recognizing Address Blocks on Mail Pieces: Specialized Tools and Problem-Solving Architecture , 1987, AI Mag..