A Survey on Feature Extraction Methods for Handwritten Digits Recognition
Ishani Patel, Virag Jagtap, Ompriya Kale · International Journal of Computer Applications · 2014
Hand written digit recognition is highly nonlinear problem.Recognition of handwritten numerals plays an active role in day to day life now days.Office automation, e-governors and many other areas, reading printed or handwritten documents and convert them to digital media is very crucial and time consuming task.So the system should be designed in such a way that it should be capable of reading handwritten numerals and provide appropriate response as humans do.However, handwritten digits are varying from person to person because each one has their own style of writing, means the same digit or character/word written by different writer will be different even in different languages.This paper presents survey on handwritten digit recognition systems with recent techniques, with three well known classifiers namely MLP, SVM and k-NN used for classification.This paper presents comparative analysis that describes recent methods and helps to find future scope.