Alexander Filatov

Graph-based handwritten digit string recognition

The article presents a handwritten digit string recognition algorithm based on matching input subgraphs with prototype symbol graphs. The article defines a set of acceptable graph transformations corresponding to typical variations of the handwritten symbols. The search for a match between the input subgraph and prototype graph is conducted using this set of transformations. This approach allows us to solve the problems of structure recognition methods caused by a high variability of handwritten symbol topology. The article presents experimental results of the handwritten digit string recognition system.

Check Amount Recognition Based on the Cross Validation of Courtesy and Legal Amount Fields

Check amount recognition is one of the most promising commercial applications of handwriting recognition. This paper is devoted to the description of the check reading system developed to recognize amounts on American personal checks. Special attention is paid to a reliable procedure developed to reject doubtful answers. For this purpose the legal (worded) amount on a personal check is recognized along with the courtesy (digit) amount. For both courtesy and legal amount fields, a brief description of all recognition stages beginning with field extraction and ending with the recognition itself are presented. We also present the explanation of problems existing at each stage and their possible solutions. The numeral recognizer used to read the amounts written in figures is described. This recognizer is based on the procedure of matching input subgraphs to graphs of symbol prototypes. Main principles of the handwriting recognizer used to read amounts written in words are explained. The recognizer is based on the idea of describing the handwriting with the most stable handwriting elements. The concept of the optimal confidence level of the recognition answer is introduced. It is shown that the conditional probability of the answer correctness is an optimal confidence level function. The algorithms of the optimal confidence level estimation for some special cases are described. The sophisticated algorithm of cross validation between legal and courtesy amount recognition results based on the optimal confidence level approach is proposed. Experimental results on real checks are presented. The recognition rate at 1% error rate is 67%. The recognition rate without reject is 85%. Significant improvement is achieved due to legal amount processing in spite of a relatively low recognition rate for this field.

Handwritten ZIP code recognition

The encoding of delivery point code (DPC) for a handwritten address is one of the most complex problems of the US mail delivery automation. This paper describes a real-time system intended to recognize the 5-digit ZIP code part of DPC. To increase the system performance the results of ZIP code recognition are cross-validated with those of city and state name recognition. The main principles of the handwritten word recognizer which provide the core of the system are explained. The system throughput is 40,000 address blocks per hour. Experimental results on live mail pieces are presented. The ZIP code recognition rate is 73% with 1% error rate.

The AddressScriptTM Recognition System for Handwritten Envelopes

This paper presents AddressScript - a system for handwritten postal address recognition for US mail. Key aspects of AddressScript technology, such as system control flow, cursive handwriting recognition, and postal database are described. Special attention is paid to the powerful character recognizer and the intensive usage of context, which becomes available during the recognition process. The algorithm of confidence level calculation is presented. Laboratory test results on a blind test set of 50,000 images of live hand-written mail pieces demonstrate a 64% finalization rate for error rates below USPS restrictions.