Abstract: Handwritten characters are still far from being replaced with the digital form. The occurrence of handwritten text is abundant. With a wide scope, the problem of handwritten letter recognition using computer vision and machine learning techniques has been a well pondered upon topic. The field has undergone phenomenal development, since the emergence of machine learning techniques.
This paper introduces an Offline Kannada Handwritten Text Recognition system using Convolutional Neural Networks (CNNs). The primary objective is to extract text from scanned images, accurately identify Kannada characters, and make them accessible for various applications. This work on a major scale devises to bridge the gap between the state-of-the-art technologies, of deep learning, to automate the solution to handwritten character recognition, using convolutional neural networks.
Convolutional neural networks have been known to have performed extremely well, on the vintage classification problem in the field of computer vision. Using the advantages of the architecture and leveraging on the preprocessing free deep learning techniques, we present a robust, dynamic and swift method to solve the problem of handwritten character recognition, for Kannada language. CNNs, known for their effectiveness in computer vision, are employed to automate the recognition of handwritten Kannada characters.
To address the scarcity of Kannada training data, handwritten samples are collected from various sources, and two recognition methods are proposed, both relying solely on CNNs. The paper briefly mentions the exploration of different datasets, without providing specific accuracy figures.
Keywords: Convolutional Neural Network (CNN), Tesseract, OCR, Handwritten Text Recognition (HTR)
|
DOI:
10.17148/IJARCCE.2024.13542
