Optical Character Recognition, Using K-Nearest Neighbors

TL;DR

This paper proposes an OCR method using K-nearest neighbors that achieves over 90% accuracy with quick training and runtime, addressing the ongoing challenge of recognizing handwritten text.

Contribution

The paper introduces a K-nearest neighbors based OCR approach with high accuracy and efficient processing, contributing a simple yet effective solution to handwritten text recognition.

Findings

Achieved over 90% recognition accuracy.

Short training and runtime performance.

Effective for handwritten text recognition.

Abstract

The problem of optical character recognition, OCR, has been widely discussed in the literature. Having a hand-written text, the program aims at recognizing the text. Even though there are several approaches to this issue, it is still an open problem. In this paper we would like to propose an approach that uses K-nearest neighbors algorithm, and has the accuracy of more than 90%. The training and run time is also very short.