HDNcfm: Handwritten Digit Recognition System Using No Combination of Feature Maps

Sudeep Tanwar, Drashti Dobariya, Dhwani Prajapati


Convolutional Neural Network (CNN) has proved its significance as a robust method for classification of various image based applications such as face recognition and handwritten digit recognition. Traditional neural netwotk’s input feature maps are convolved along with the kernal, which aids in increasing the performance of the system. However, the problem of some feature lost arise in traditional neural network while combining the feature maps, and also the application does not tend to do well at a large scale networks. Hence, to address these issues, in this paper, we proposed, HDNcfm: Handwritten Digit Recognition System using Combination of Feature Maps, which tend to converge faster than Combination of Feature Map(CFM) method, and also upgrade its performance. In this method as the input features doesn’t combined, the number of input feature and output feature can be same and therefore, this method can also be applied for relatively smaller dataset. Performance of the proposed approach has been evaluated using the parameters such as-convergence rate, and error rate. Results obtained clearly show the superior performance of the proposed scheme as compared to the traditional neural network based schemes.


Handwritten Digit Recognition; NCFM; CNNs; Multilayer Perceptron model; Artificial neural network.

Full Text:


DOI: https://doi.org/10.26483/ijarcs.v8i5.3415


  • There are currently no refbacks.

Copyright (c) 2017 International Journal of Advanced Research in Computer Science