Intelligent Character Recognition System Using Convolutional Neural Network

S. Suriya, Dhivya S, Balaji M
2020 EAI Endorsed Transactions on Cloud Systems  
Computational Linguistics involves the techniques of Computer Science which play a vital role in recognizing written or printed characters such as numbers or letters to change them into a form that the computer can use it efficiently. Convolutional Neural Network differs from other approaches by extracting the features automatically. The proposed approach is capable of recognizing characters in a variety of challenging conditions using the Convolutional Neural Network, where traditional
more » ... r recognition systems fail, notably in the presence of low resolution, substantial blur, low contrast, and other distortions. Intellectual Character Recognition System is an application that uses Convolutional Neural Network (CNN) to recognize the Tamil character dataset accurately developed by HP Labs India. The novelty of this system is that, it recognizes the characters of the Predominant Tamil language. With the help of suitable datasets consisting of the Tamil Scripts, the model is trained efficiently. This work has produced a training accuracy of 99.16% which is far better compared to the traditional approaches. Equality rate for ணீ = 0.007126562089919851 Equality rate for � = 0.006803545111339915 Equality rate for � = 0.006662225183211193 Equality rate for ண் = 0.006904487917146145 Equality rate for த = 0.0067026023055336845 Equality rate for � = 0.006843922233662407 Equality rate for � = 0.006783356550178669 Equality rate for � = 0.006904487917146145 Equality rate for � = 0.006924676478307391 Equality rate for த் = 0.006944865039468637 Equality rate for ந = 0.006581470938566208 Equality rate for நி = 0.006642036622049947 Equality rate for நீ = 0.006783356550178669 Equality rate for � = 0.006843922233662407 Equality rate for � = 0.006924676478307391 Equality rate for ந் = 0.006884299355984899 Equality rate for ன = 0.00652090525508247 Equality rate for னி = 0.006904487917146145 Equality rate for னீ = 0.006682413744372439 Equality rate for � = 0.006803545111339915 Equality rate for � = 0.006682413744372439 Equality rate for ன் = 0.006823733672501161 Equality rate for ப = 0.006843922233662407 Equality rate for � = 0.006843922233662407 Equality rate for � = 0.0067026023055336845 Equality rate for � = 0.006843922233662407 Equality rate for � = 0.006864110794823653 Equality rate for ம = 0.006843922233662407 Equality rate for ப் = 0.00672279086669493 Equality rate for � = 0.006682413744372439 Equality rate for � = 0.0067026023055336845 Equality rate for � = 0.006763167989017423 Equality rate for � = 0.006884299355984899 Equality rate for ம் = 0.006843922233662407 Equality rate for ய = 0.006803545111339915 Equality rate for � = 0.006783356550178669 Equality rate for � = 0.006783356550178669 Checking equality rate for augmenting After finding the number of images in each label and equality rate, finding the equality rate after data augmenting to increase the efficiency of the system in learning and recognizing the character. Sample Output:
doi:10.4108/eai.16-10-2020.166659 fatcat:rrv3tyk2ezegdhcwsvuvvkgbrq