Application of Natured-Inspired Technique to Odia Handwritten Numeral Recognition

Application of Natured-Inspired Technique to Odia Handwritten Numeral Recognition

Puspalata Pujari (Guru Ghasidas Vishwavidyalaya, India) and Babita Majhi (Guru Ghasidas Vishwavidyalaya, India)
DOI: 10.4018/978-1-5225-2857-9.ch019
OnDemand PDF Download:


In this chapter an effort has been made to develop a hybrid system using functional link artificial neural network (FLANN) and differential evolution (DE) for effective recognition of Odia handwritten numerals. The S-transform (ST) is chosen for feature extraction from handwritten numerals and these are further reduced by using principal component analysis (PCA). After reduction of feature the reduced features are applied to FLANN model for recognition of each numeral. Further differential evolution algorithm (DE) is used for the optimization of weights of FLANN classifier. For performance comparison, genetic algorithm (GA) and particle swarm optimization (PSO) based FLANN models (FLANN_GA and FLANN_PSO) are also designed and simulated under similar condition. The efficiency of proposed DE based FLANN (FLANN_DE) method is assessed through simulation with standard dataset consisting of 4000 handwritten Odia numerals. The results of three models are compared and it is observed that the FLANN_DE model provides the best result as compared to other models.
Chapter Preview


Over the last ten decades optical character recognition (OCR) is the most demanding area which comes under the field of pattern recognition, artificial intelligence and machine vision. There are varieties of applications of handwritten character such as postal pin code verification, passport verification, digital library system, document processing, forgery detection in banks and many more. OCR is the translation of handwritten and printed images of character into editable character. The challenging task lies in the recognition of optically processed characters. In off-line recognition method characters are recognized later, after their creation. But the characters are recognized immediately after their creation in an on-line method. OCR can recognize both printed and handwritten characters, but the efficiency of recognition precisely depends on the constraints associated with the characters. More constrained the character is, greater is the efficiency of the OCR system. It is very difficult to develop OCR system for totally unconstrained handwritten characters. Recognition of handwritten characters and numerals is more complex task than the printed character. Many variations are observed in handwritten character due to the style of writing, added noise, missing part, devices and medias used for image acquisition. These may be due to different size, stroke and slant of the image. Therefore there is a requirement to develop robust system which can recognize effectively any handwritten characters. This chapter develops a recognition model for offline handwritten Odia numerals using FLANN as classifier and a bio-inspired technique such as differential evolution (DE) for the weight optimization of the FLANN model. Preprocessing is the first step of OCR followed by feature extraction and classification. Before developing the recognition model preprocessing and feature extraction tasks are performed. The numeral images are preprocessed first. Then feature based recognition method is applied to measure and extract significant features from the numerals image. Then a hybrid system is developed by using FLANN classifier where the weights of FLANN classifier are optimized with DE algorithm. The features are compared to the prototypes developed in training phase. The description which provides the closest match provides the recognition. For feature extraction the recently developed S-transform (M. Hariharan, 2014) is applied which retains the significant features of the pattern. These features being more in dimensions are then reduced by applying principal component analysis (PCA). For the classification task FLANN model is used, the weights of which are adjusted by minimizing the squared error value using the DE algorithm.

Key Terms in this Chapter

S-Transform (ST): ST is a time frequency analysis method for the extraction of important features from the characters. It combines the features of short time fourier transform (STFT) and wavelet transform (WT).

Differential Evolution (DE): DE is a bio inspired techniques which optimizes a problem by iteratively modifying each candidate solutions.

Functional Link Artificial Neural Network (FLANN): FLANN is a higher order neural network with low computational complexity. It has no hidden layers. The input vector of FLANN is functionally expanded to get non-linear solutions.

OCR: Optical character recognition is the recognition of scanned images of hand written or printed characters.

Complete Chapter List

Search this Book: