DSP-Based Optical Character Recognition System Using Interval Type-2 Neural Fuzzy System

被引：0

作者：

Lee, Ching-Hung ^{[1
]}

Chang, Feng-Yu ^{[2
]}

Lin, Chih-Min ^{[3
,4
]}

机构：

[1] Natl Chung Hsing Univ, Dept Mech Engn, Taichung 402, Taiwan

[2] Yuan Ze Univ, Dept Elect Engn, Taoyuan, Taiwan

[3] Yuan Ze Univ, Coll Elect & Commun Engn, Zhongli City, Taiwan

[4] Obuda Univ, Budapest, Hungary

来源：

INTERNATIONAL JOURNAL OF FUZZY SYSTEMS | 2014年 / 16卷 / 01期

关键词：

Interval type-2 fuzzy neural network; uncertainty; bounds; simultaneous perturbation stochastic; approximation algorithm; optical character recognition; digital signal processors (DSPs); NETWORK; DESIGN; MODEL;

D O I：

暂无

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

The aim of this paper is to solve optical character recognition (OCR) problem using the interval type-2 neural fuzzy system (IT2NFS) with stable learning mechanism and uncertainty bounds operations for computation speedup and implementation on digital signal processors (DSPs). Differ from most of the interval type-2 fuzzy neural networks, the type-reduction of IT2NFS is embedded in the network structure by using uncertainty bounds method such that the time-consuming Karnik-Mendel (KM) algorithm can be avoided. The simultaneous perturbation stochastic approximation (SPSA) algorithm provides the gradient free property which is suitable for training IT2NFS. The classification of 26 English letters on the image under the conditions of rotation, scale, and displacement is described to illustrate the proposed OCR system. The experimental results demonstrate the feasibility of the designed OCR system based on a fixed-point TMS320DM6437 DSP from Texas Instruments.

引用

页码：86 / 96

页数：11

共 27 条

[11] Interval type-2 fuzzy logic systems: Theory and design [J].

Liang, QL ;

Mendel, JM .

IEEE TRANSACTIONS ON FUZZY SYSTEMS, 2000, 8 (05) :535-550

[12] Adaptive Control of Two-Axis Motion Control System Using Interval Type-2 Fuzzy Neural Network [J].

Lin, Faa-Jeng ;

Chou, Po-Huan .

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS, 2009, 56 (01) :178-193

[13]

Lynch C, 2005, IEEE INT CONF FUZZY, P347

[14]

Mani N, 1997, IEEE SYS MAN CYBERN, P2517, DOI 10.1109/ICSMC.1997.635312

[15]

Melgarejo MA, 2004, IEEE INT CONF FUZZY, P977

[16]

Mendel JM, 2001, JOINT 9TH IFSA WORLD CONGRESS AND 20TH NAFIPS INTERNATIONAL CONFERENCE, PROCEEDINGS, VOLS. 1-5, P1647, DOI 10.1109/NAFIPS.2001.943798

[17] A neuro-fuzzy inference engine for Farsi numeral characters recognition [J].

Montazer, Gholam Ali ;

Saremi, Hamed Qahri ;

Khatibi, Vahid .

EXPERT SYSTEMS WITH APPLICATIONS, 2010, 37 (09) :6327-6337

[18] HISTORICAL REVIEW OF OCR RESEARCH-AND-DEVELOPMENT [J].

MORI, S ;

SUEN, CY ;

YAMAMOTO, K .

PROCEEDINGS OF THE IEEE, 1992, 80 (07) :1029-1058

[19] The DSFPN: A new neural network and circuit simulation for optical character recognition [J].

Morns, IP ;

Dlay, SS .

IEEE TRANSACTIONS ON SIGNAL PROCESSING, 2003, 51 (12) :3198-3209

[20] Rotation, scale and translation invariant handwritten Devanagari numeral character recognition using general fuzzy neural network [J].

Patil, P. M. ;

Sontakke, T. R. .

PATTERN RECOGNITION, 2007, 40 (07) :2110-2117

← 1 2 3 →