The design of HMM-based banknote recognition system

Author

Shan, Gai ; Peng, Liu ; Jiafeng, Liu ; Xianglong, Tang

Author_Institution

Sch. of Comput. Sci. & Technol., Harbin Inst. of Technol., Harbin, China

Volume

4

fYear

2009

fDate

20-22 Nov. 2009

Firstpage

106

Lastpage

110

Abstract

The banknote recognition system based on hidden Markov models (HMM) is proposed. It is based on the empirical risk minimization (ERM) principle. Image preprocessing includes brightness equalization and tilt correction. In order to satisfy the high speed and reliability of the banknote processing system, the grid segmentation is used for features extraction. Analyze the experimental data and determine the number of states, iterations, and Gaussian components. The proposed banknote recognition system can be applied to classify any kinds of banknotes. More than 16,000 RMB samples are sampled by CIS (Contact Image Sensor) with 25 dpi. Experimental results show that the proposed method obtained higher recognition rate than ANN and SVM.

Keywords

bank data processing; feature extraction; hidden Markov models; image segmentation; Contact Image Sensor; Gaussian components; banknote recognition system; brightness equalization; empirical risk minimization; feature extraction; grid segmentation; hidden Markov models; image preprocessing; tilt correction; Brightness; Computational Intelligence Society; Data analysis; Feature extraction; Hidden Markov models; Image segmentation; Image sensors; Risk management; Support vector machine classification; Support vector machines; Banknote Recognition; ERM; Features Extraction; HMM;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Computing and Intelligent Systems, 2009. ICIS 2009. IEEE International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-4244-4754-1

Electronic_ISBN

978-1-4244-4738-1

Type

conf

DOI

10.1109/ICICISYS.2009.5357719

Filename

5357719