A Survey on Handwritten Text Recognition.

A Survey on Handwritten Text Recognition.

1Sanket Kanse, Student, Computer Engg, GSMCOE, Maharashtra, India.

2Sagar Powar, Student, Computer Engg, GSMCOE, Maharashtra, India.

3Prathamesh Sawant, Student, Computer Engg, GSMCOE, Maharashtra, India.

4Jayesh dubale, Student, Computer Engg, GSMCOE, Maharashtra, India.

5Prof. Supriya Kamble, Guide, Computer Engg, GSMCOE, Maharashtra, India.

ABSTRACT
Handwritten Text Recognition (HTR) is the detection of characters from images. HTR is a complex task due to the variability and diversity of handwritten characters in the script. CNNs are a type of deep learning algorithm that can automatically learn features from images and are widely used in image recognition tasks. This paper presents a CNN-based approach for HTR that achieves state-of-theatre performance on a benchmark dataset. The proposed approach involves a pre-processing step to normalize and segment the input images, followed by a CNN architecture that consists of several convolutional layers and fully connected layers. The network is trained using a massive character labelled dataset. The outcomes demonstrate that the suggested method achieves excellent accuracy in recognizing characters and can be applied to real-world applications such as document digitization and text-to-speech conversion.