A new courtesy amount recognition module of a Check Reading System

Author(s):  
Wu Ding ◽  
Ching Y. Suen ◽  
Adam Krzyzak
Keyword(s):  
Author(s):  
Françoise Fogelman Soulié ◽  
Dorothée Gureghian Gastinel ◽  
Jérôme Loncelle ◽  
Erik Marcadé ◽  
Jérôme Gallinari
Keyword(s):  

Author(s):  
S. Knerr ◽  
V. Anisimov ◽  
O. Baret ◽  
N. Gorski ◽  
D. Price ◽  
...  

We developed a check reading system, termed INTERCHEQUE, which recognizes both the legal (LAR) and the courtesy amount (CAR) on bank checks. The version presented here is designed for the recognition of French, omni-bank, omni-scriptor, handwritten bank checks, and meets industrial requirements, such as high processing speed, robustness, and extremely low error rates. We give an overview of our recognition system and discuss some of the pattern recognition techniques used. We also describe an installation which processes of the order of 70,000 checks per day. Results on a data base of about 170,000 checks show a recognition rate of about 75% for an error rate of the order of 1/10,000 checks.


Author(s):  
Gregory Dzuba ◽  
Alexander Filatov ◽  
Dmitry Gershuny ◽  
Igor Kil ◽  
Vadim Nikitin

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.


Author(s):  
N. Mori ◽  
T. Oikawa ◽  
Y. Harada ◽  
J. Miyahara ◽  
T. Matsuo

The Imaging Plate (IP) is a new type imaging device, which was developed for diagnostic x ray imaging. We have reported that usage of the IP for a TEM has many merits; those are high sensitivity, wide dynamic range, and good linearity. However in the previous report the reading system was prototype drum-type-scanner, and IP was also experimentally made, which phosphor layer was 50μm thick with no protective layer. So special care was needed to handle them, and they were used only to make sure the basic characteristics. In this article we report the result of newly developed reading, printing system and high resolution IP for practical use. We mainly discuss the characteristics of the IP here. (Precise performance concerned with the reader and other system are reported in the other article.)Fig.1 shows the schematic cross section of the IP. The IP consists of three parts; protective layer, phosphor layer and support.


Author(s):  
Karen Emmorey

Recent neuroimaging and electrophysiological studies reveal how the reading system successfully adapts when phonological codes are relatively coarse-grained due to reduced auditory input during development. New evidence suggests that the optimal end-state for the reading system may differ for deaf versus hearing adults and indicates that certain neural patterns that are maladaptive for hearing readers may be beneficial for deaf readers. This chapter focuses on deaf adults who are signers and have achieved reading success. Although the left-hemisphere-dominant reading circuit is largely similar in both deaf and hearing individuals, skilled deaf readers exhibit a more bilateral neural response to written words and sentences than their hearing peers, as measured by event-related potentials and functional magnetic resonance imaging. Skilled deaf readers may also rely more on neural regions involved in semantic processing than hearing readers do. Overall, emerging evidence indicates that the neural markers for reading skill may differ for deaf and hearing adults.


2017 ◽  
Vol 27 ◽  
pp. 45-57 ◽  
Author(s):  
Johanna Liebig ◽  
Eva Froehlich ◽  
Carmen Morawetz ◽  
Mario Braun ◽  
Arthur M. Jacobs ◽  
...  
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document