• Selected
• Entire List

Abstract:
In the US and many other countries, bank checks are preprinted with the account number and the check number in MICB ink and format; as such, these two numeric fields can be easily read and processed using automated techniques. However, the amount field on a filled -in check is usually read by human eyes, and involves significant time and cost, especially when one considers that about 68 billion checks are processed per annum in the US alone.

The system described in this paper uses the scanned image of a bank check to "read" the check. There are four main stages in the system that focus on: the detection of courtesy amount block within the image; the segmentation of string into characters; the recognition of isolated characters; and the post processing process that ensures correct recognition.

The detection of courtesy amounts is performed using heuristic rules. These rules are applied after processing the image to translate the set of gray pixels into groups of pixels, which are considered as strings. The segmentation of the courtesy amount is the most difficult part of the process because of the largely unconstrained nature of handwritten amounts on checks. The proposed segmentation has been implemented as a recursive process that interacts with the recognition module. The recognition of the isolated characters is based on an array of neural networks that has been demonstrated to be very accurate and computationally efficient. Finally, the post-processing module is used to minimize the incidence of incorrect readings by verifying that the sequence of numbers, periods, and commas matches the correct syntax for the recognized value of the check. Several of the algorithms included in the system are generalizable and can also be applied to address other applications involving reading of handwritten inputs.

Automated Check Reading, Automated Reading of Handwritten Information, Knowledge Acquisition

Abstract:
While reading handwritten text accurately is a difficult task for computers, the conversion of handwritten papers into digital format is necessary for automatic processing. Since most bank checks are handwritten, the number of checks is very high, and manual processing involves significant expenses, many banks are interested in systems that can read check automatically. This paper presents several approaches to improve the accuracy of neural networks used to read unconstrained numerals in the courtesy amount field of bank checks.

Optical Character Recognition, Neural Networks, Document Imaging, Check Processing, Unconstrained Handwritten Numerals

Abstract:
In spite of the rapid advances in computers and communication technologies, a number of large-scale applications continue to rely heavily on the use of paper as the dominant medium, either in an intra-organizational or an inter-organizational environment. One major example of this category of paper intensive applications is the check processing application. In a number of countries, the value of each check is read by human eyes before the check is physically transported, in stages, from the point it was presented to the location of the branch of the bank which issued the blank check to the concerned account holder. This process of manual reading of each check involves significant time and cost. In this paper, a new approach is proposed to read the numerical amount field on the check; this field is also called the courtesy amount field. In the case of check processing, the segmentation of unconstrained strings into individual digits is a challenging task because one needs to accommodate special cases involving: connected or overlapping digits, broken digits, and digits physically connected to a piece of stroke that belongs to a neighboring digit. The system described in this paper involves three stages: the segmentation of the string into a series of individual characters; the normalization of each isolated character; and the recognition of each character based on a neural network classifier.

Abstract:
In spite of rapid evolution of electronic techniques, a number of large-scale applications continue to rely on the use of paper as the dominant medium. This is especially true for processing of bank checks. This paper examines the issue of reading the numerical amount field. In the case of checks, the segmentation of unconstrained strings into individual digits is a challenging task because of connected and overlapping digits, broken digits, and digits that are physically connected to pieces of strokes from neighboring digits. The proposed architecture involves four stages: segmentation of the string into individual digits, normalization, recognition of each character using a neural network classifier, and syntactic verification. Overall, this paper highlights the importance of employing a hybrid architecture that incorporates multiple approaches to provide high recognition rates.

Handwritten checks; Reading of unconstrained handwritten material; neural network

Abstract:
In recent years, a number of large-scale applications continue to rely heavily on the use of paper as the dominant medium, either on intra-organization basis or on inter-organization basis, including paper intensive applications in the check processing application. In many countries, the value of each check is read by human eyes before the check is physically transported, in stages, from the point it was presented to the location of the branch of the bank which issued the blank check to the concerned account holder. Such process of manual reading of each check involves significant time and cost. In this research, a new approach is introduced to read the numerical amount field on the check; also known as the courtesy amount field. In the case of check processing, the segmentation of unconstrained strings into individual digits is a challenging task because one needs to accommodate special cases involving: connected or overlapping digits, broken digits, and digits physically connected to a piece of stroke that belongs to a neighboring digit. The system described in this paper involves three stages: segmentation, normalization, and the recognition of each character using a neural network classifier, with results better than many other methods in the literarature.

Character recognition, bank check recognition, segmentation, courtesy amount, scanning, preprocessing, accuracy rate, post processing, feedback, architecture