New Banknote Number Recognition Algorithm Based on Support Vector Machine

Author

Shan Gai ; Guowei Yang ; Sheng Zhang ; Minghua Wan

Author_Institution

Sch. of Inf. Eng., Nanchang Hangkong Univ., Nanchang, China

fYear

2013

Firstpage

176

Lastpage

180

Abstract

Detecting the banknote serial number is an important task in business transaction. In this paper, we propose a new banknote number recognition method. The preprocessing of each banknote image is used to locate position of the banknote number image. Each number image is divided into non-overlapping partitions and the average gray value of each partition is used as feature vector for recognition. The optimal kernel function is obtained by the semi-definite programming (SDP). The experimental results show that the proposed method outperforms MASK, BP, HMM, Single SVM classifiers.

Keywords

feature extraction; financial data processing; mathematical programming; object recognition; support vector machines; BP; HMM; MASK; SDP; banknote image preprocessing; banknote number recognition algorithm; banknote serial number detection; business transaction; feature vector; nonoverlapping partitions; optimal kernel function; semidefinite programming; single SVM classifiers; support vector machine; Educational institutions; Equations; Hidden Markov models; Kernel; Mathematical model; Support vector machines; Training; Multiple Kernel Learning; Semi-definite programming; Support Vector Machine; banknote Number recognition;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ACPR), 2013 2nd IAPR Asian Conference on

Conference_Location

Naha

Type

conf

DOI

10.1109/ACPR.2013.115

Filename

6778305