Recognizing Handprinted Digit Strings: a Hybrid Connectionist/Procedural Approach

We describe an alternative approach to hand-printed word recognition using a hybrid of procedural and connectionist techniques. We utilize two connectionist components: one to concurrently make recognition and segmentation hypotheses, and another to perform reened recognition of segmented characters. Both networks are governed by a procedural controller which incorporates systematic domain knowledge and procedural algorithms to guide recognition. We employ an approach wherein an image is processed over time by a spatiotemporal connectionist network. The scheme ooers several attractive features including shift-invariance and retention of local spatial relationships along the dimension being temporalized, a reduction in the number of free parameters , and the ability to process arbitrarily long images. Recognition results on a set of real-world isolated ZIP code digits are comparable to the best reported to date, with a 96.0% recognition rate and a rate of 99.0% when 9.5% of the images are rejected.

[1]  Lokendra Shastri,et al.  Handprinted digit recognition using spatiotemporal connectionist models , 1992, Proceedings 1992 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[2]  Lokendra Shastri,et al.  Learning Phonetic Features Using Connectionist Networks , 1987, IJCAI.

[3]  Lokendra Shastri,et al.  Character Recognition Using A Modular Spatiotemporal Connectionist Model , 1992 .