A survey on handwritten character recognition

Handwritten Character Recognition (HCR) stands as a pivotal domain within computer vision, finding extensive applications in document digitization and signature verification. This survey paper aims to present a comprehensive overview of character recognition techniques. We explore fundamental princi...

Full description

Saved in:
Bibliographic Details
Main Authors: Patil, Shubham, Kokate, Shantanu, Mane, Vijay, Gandhe, S. T.
Format: Conference Proceeding
Language:English
Subjects:
Algorithms
Artificial neural networks
Character recognition
Computer vision
Digitization
Handwriting recognition
Handwritten signature verification
Markov chains
Support vector machines
User interfaces
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Handwritten Character Recognition (HCR) stands as a pivotal domain within computer vision, finding extensive applications in document digitization and signature verification. This survey paper aims to present a comprehensive overview of character recognition techniques. We explore fundamental principles, preprocessing strategies, feature extraction methods, classification algorithms, evaluation metrics, and contemporary challenges that define HCR. As we navigate through the evolution of character recognition, this survey serves as an inclusive guide, providing insights and direction for researchers and practitioners in the intricate realm of handwritten character recognition. In the context of character recognition, this paper briefly compares various methods such as Support Vector Machines (SVM), Convolutional Neural Networks (CNN), k-Nearest Neighbors (KNN), and Hidden Markov Models (HMM). These techniques play a crucial role in enhancing character recognition accuracy, making them suitable for diverse applications ranging from digitizing historical manuscripts to modern handwriting-based user interfaces. By addressing the strengths and limitations of each method, researchers and practitioners can make informed decisions based on the specific requirements of their applications. In conclusion, this survey paper aims to contribute to the collective understanding of character recognition. It serves as a valuable resource for those engaged in advancing the field of handwritten character recognition, providing a roadmap for navigating its complexities and pushing the boundaries of its applications.
ISSN:0094-243X
1551-7616
DOI:10.1063/5.0230177