Refine Search

New Search

Results: 7

(searched for: doi:10.13176/11.245)
Save to Scifeed
Page of 1
Articles per Page
by
Show export options
  Select all
Sagar Shinde, R. B. Waghulade, D. S. Bormane
2017 International Conference on Trends in Electronics and Informatics (ICEI) pp 204-209; https://doi.org/10.1109/icoei.2017.8300916

Abstract:
Identification of handwritten digits, letters, mathematical symbols and complex structure expressions have captured a lot of concentration in the field of pattern recognition. Accuracy has been improved by considering the features like skew, entropy, kurtosis, standard deviation. In segmentation binarization, edge detection, morphological operation has been considered. The equations under various categories have been considered for experiment and achieved significant results. Latency, throughput and accuracy have been improved by using feed forward back propagation neural network with gradient descent with momentum algorithm and adaptive learning.
Published: 22 March 2016
Abstract:
Computer based pattern recognition is a process that involves several sub-processes, including pre-processing, feature extraction, feature selection, and classification. Feature extraction is the estimation of certain attributes of the target patterns. Selection of the right set of features is the most crucial and complex part of building a pattern recognition system. In this work we have combined multiple features extracted using seven different approaches. The novelty of this approach is to achieve better accuracy and reduced computational time for recognition of handwritten characters using Genetic Algorithm which optimizes the number of features along with a simple and adaptive Multi Layer Perceptron classifier. Experiments have been performed using standard database of CEDAR (Centre of Excellence for Document Analysis and Recognition) for English alphabet. The experimental results obtained on this database demonstrate the effectiveness of this system.
Gauri Katiyar, Shabana Mehfuz
2015 Annual IEEE India Conference (INDICON) pp 1-5; https://doi.org/10.1109/indicon.2015.7443398

Abstract:
Selection of classifiers plays a very important role in achieving best possible accuracy of classification. In this proposed work an efficient Support Vector Machine based off-line handwritten character recognition system has been developed. Experiments have been performed using well known standard database acquired from CEDAR, also we propose four different techniques of feature extraction to construct the final feature vector. Experimental results show that the performance of SVM is much better than other techniques reported in literature.
Gauri Katiyar, Shabana Mehfuz
International Conference on Computing, Communication & Automation pp 1155-1159; https://doi.org/10.1109/ccaa.2015.7148550

Abstract:
Statistical techniques for off-line character recognition are not flexible and adaptive enough for new handwriting constraints. Offline handwritten character recognition of English alphabets using a three layered feed forward neural network is presented in this paper. The proposed recognition system describes the evaluation of feed forward neural network by combining four different feature extraction approaches(box approach, diagonal distance approach, mean and gradient operations). The proposed recognition system performs well on the benchmark dataset CEDAR (Centre of Excellence for Document Analysis And Recognition).
Page of 1
Articles per Page
by
Show export options
  Select all
Back to Top Top