International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Call for Papers | Fully Refereed | Open Access | Double Blind Peer Reviewed

ISSN: 2319-7064


Downloads: 123

Research Paper | Computer Science Engineering | Volume 3 Issue 8, August 2014 | Pages: 561 - 566 | India


Recognition of Word using different Feature Extraction Methods

Kavita Babalad, Laxmidevi Noolvi, Dr. Jharna Majumdar

Abstract: Word Recognition is one of the most interesting and challenging research areas in the field of image processing. In this paper, we are presenting a printed Word Recognition method, where we segment each character from the word. For segmented character each invariant features like line segments, different types of line segments, normalized horizontal and vertical line, crossing, distances and moment of inertia are been extracted. The clustering methods are used for recognition. The recognized word is spelled out by the system.

Keywords: Pre-processing, Segmentation, Feature Extraction, Recognition and Clustering method

How to Cite?: Kavita Babalad, Laxmidevi Noolvi, Dr. Jharna Majumdar, "Recognition of Word using different Feature Extraction Methods", Volume 3 Issue 8, August 2014, International Journal of Science and Research (IJSR), Pages: 561-566, https://www.ijsr.net/getabstract.php?paperid=2015293, DOI: https://dx.doi.org/10.21275/2015293

Download Citation: APA | MLA | BibTeX | EndNote | RefMan

Share This Research

Help this article reach readers, researchers and professionals.

Share activity is measured for research-engagement analytics. Only verified, unique public shares can support award tie-breaking.

Confirm Your Share

Enter your details so IJSR can confirm this sharing activity.

Your details are used to validate this share and protect the award process from duplicate or false activity.

Download Article PDF


Rate This Article!

Top

Confirm Your Share

Enter your details so IJSR can confirm this sharing activity.

Your details are used to validate this share and protect the award process from duplicate or false activity.