Lexical Search Approach for Character-String Recognition

Koga, Masashi; Mine, Ryuji; Suzuki, Hiroshi; Fujisawa, Hiromichi

doi:10.1007/3-540-48172-9_10

Cited by 16 publications

(6 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…First of all, tracking the thinned curve in certain step to arrive a certain pixel Q from the endpoint P , the angle between the line PQ and , tan (5) So if the step length is 4 / , the normalized direction values of 8-pixel neighborhood of the pixel P is respectively 0, 1, 2, 3, 4, 5, 6, 7.…”

Section: A Thinningmentioning

confidence: 99%

“…Commonly identification of numbers and letters is based on template matching OCR algorithm or artificial neural network OCR algorithm. Characters are often measured by contour, grid, projection and other statistical characteristic features [2][3][4][5][6][7][8]. For these applications, there are two main problems, the poor ability to distinguish between similar characters and the slow recognition speed caused by the increase of feature dimensions.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Extraction and Recognition Alphabetic and Digital Characters on Industrial Containers

Bingxia

et al. 2009

2009 International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

A method of extraction and recognition alphabetic and digital characters on industrial containers on automatic production line is proposed. A thinned image is viewed as a graph. In the procession of image recognition of industrial containers, the number of endpoint is considered as integrate features of those 10 digital and 26 capital English alphabetic character images, which can be used for character coarse classification. Features of some key points are viewed as the major specific features, and then the characters on industrial containers can be recognized, and the external contour of character is used to discriminate similar characters. The experiment results shows that the proposed approach is practical and effective.

show abstract

Section: A Thinningmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Extraction and Recognition Alphabetic and Digital Characters on Industrial Containers

Bingxia

et al. 2009

2009 International Conference on Computational Intelligence and Security

View full text Add to dashboard Cite

show abstract

“…To cope with the difficulty in character segmentation, the lexically directed approach is adopted as shown in Fig. 10 [4,5]. The figure shows how the problem of non-uniform character size and spacing is approached.…”

Section: ) Size Matching 2) Line-segment Matching 3) Fix Area Word Mmentioning

confidence: 99%

<title>Form type identification for banking applications and its implementation issues</title>

et al. 2003

View full text Add to dashboard Cite

This paper presents a new type ATM called image-ATM and an image workflow system developed for banking applications. The system including the image-ATM captures the paper forms brought by the clients at the very front-end, identifies the type of forms, and recognizes the data on the form automatically. The image-ATM can accept over 400 different kinds of forms. The system is presently in operation at some of the Japanese major banks. They could reduce considerable human workforce for their branch offices by introducing the image workflow system and by centralizing the back-office work at a few operation centers. Technically, form recognition, especially form type identification, was one of the keys for this success. This paper discusses a method for form type identification and its technical issues.

show abstract

“…Such methods do not sufficiently incorporate character shape information. On the other hand, over-segmentationbased methods attempt to split character patterns at their true boundaries and label the split character patterns [39][40][41][42][43][44][45][46]. Character patterns may also be split within them, but they are merged later.…”

Section: Introductionmentioning

confidence: 99%