Handwriting Recognition using KNN classification algorithm

Computer Science Enginering

Building an effective methodology to detect hand-written characters from images with less error rate is the great task. Our aim is to make such an algorithm that will be able to generate error free recognition of hand written text from the given input image which will be a hand written character, and will help in document digitizing. OCR has always been an intensive research topic for more than 4 decades, it is probably one of the most time consuming, as well as labor intensive work of inputting the data through keyboard .This paper discusses about mechanical or electronic conversion of scanned images, text which contain graphics ,image captured by camera ,scanned images and the recognition of images where characters may be broken or corrupted .The optical character recognition is the desktop based application developed using Python 3.0 and .We should gain > 97.82% accuracy when applied on different data sets, during pre-processing we will use different techniques to remove noise from the background of the image. We will convert the labelled data into grey scaled images and train the classifier and generalize it using the validation set to reduce any kind of validation error. Finally, we will test the module using the test_data and see the outcome of the algorithm. We display the images as well using the matplot library provided by Python.

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.