Handwritten character recognition using wavelet energy and extreme learning machine
- PDF / 434,694 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 30 Downloads / 234 Views
ORIGINAL ARTICLE
Handwritten character recognition using wavelet energy and extreme learning machine Binu P. Chacko • V. R. Vimal Krishnan G. Raju • P. Babu Anto
•
Received: 14 August 2010 / Accepted: 5 September 2011 / Published online: 28 September 2011 Springer-Verlag 2011
Abstract This paper deals with the recognition of handwritten Malayalam character using wavelet energy feature (WEF) and extreme learning machine (ELM). The wavelet energy (WE) is a new and robust parameter, and is derived using wavelet transform. It can reduce the influences of different types of noise at different levels. WEF can reflect the WE distribution of characters in several directions at different scales. To a non oscillating pattern, the amplitudes of wavelet coefficients increase when the scale of wavelet decomposition increase. WE of different decomposition levels have different powers to discriminate the character images. These features constitute patterns of handwritten characters for classification. The traditional learning algorithms of the different classifiers are far slower than required. So we have used an extremely fast leaning algorithm called ELM for single hidden layer feed forward networks (SLFN), which randomly chooses the input weights and analytically determines the output weights of SLFN. This algorithm learns much faster than traditional popular learning algorithms for feed forward neural networks. This feature vector, classifier combination gave good recognition accuracy at level 6 of the wavelet decomposition. Keywords Character recognition Feature extraction Wavelet energy Extreme learning machine
B. P. Chacko (&) V. R. Vimal Krishnan G. Raju P. Babu Anto Department of Information Technology, Kannur University, Kannur, India e-mail: [email protected]
1 Introduction Handwriting recognition has been a popular area of research since few decades under the purview of image processing and pattern recognition [1]. A major goal of pattern recognition research is to create human perception capabilities in artificial systems. The task of automatically reading handwriting with close to human performance is still an open problem and the central issue of an active field of research [2]. This may be due to the large degree of variability of human writing. Handwritten character recognition (HCR) systems have to address issues such as infinite variety of character shapes, similarity between characters, and distorted and broken characters [3]. The system having intelligence in recognizing the natural handwriting for all possible scripts around the world is the need of the current era. As a first step of document understanding, a digital image of the document to be analyzed needs to be captured by a scanner or digital camera. Then the segmented characters are subject to a number of preprocessing steps that aim at reducing the variability in the appearance of handwriting [2]. The basic problem is to assign the digitized character to its symbolic class. A pattern recognition algorithm is used to extract shap
Data Loading...
