Recognition of Handwritten Digits Using Support Vector Machine and Neural Networks

Computer Science and Engineering

Optical Character Recognition (OCR) is the method of classification of optical patterns contained in an exceedingly digital image. The character recognition is achieved through segmentation, feature extraction, and classification. one of all the foremost used tools for optical character recognition may well be a tesseract. During this project we try to create an alternate of tesseract which is our own model ready to} recognize different handwritten digits which don't seem to be printed but written manually and since tesseract is solely able to recognize printed digits, it'll be a valuable feature for several developers. We use the Support Vector Machine during this process. Support Vector Machine could also be a classification tool at home with recognizing handwritten digits. We also use a Neural network for Data analysis and classification of knowledge. In particular, handwritten digit recognition has been applied to acknowledge amounts written on checks for banks and zip codes on envelopes for postal services. The handwritten digit recognition system may be divided into four stages, Data acquisition, Pre-processing, Feature extraction and Classification. Support Vector Machines, within the machine learning theory, are used for classification and analysis. they've supervised learning models with associated learning algorithms that analyze data and recognize patterns. As per the requirement of the information into consideration, the Support Vector Machines are modeled to classify. Support Vector and naive Bayes, both don't require the maximum amount of computation power compared to deep learning which makes it possible for the developers to deploy the model natively instead of running it in a server container.

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