Open AccessMulti-Feature based Handwritten Script Identification at word level
Author(s) -
Suryakanth Baburao Ummapure*,
G. G. Rajput
Publication year - 2019
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.b7772.129219
Subject(s) - scale invariant feature transform , artificial intelligence , pattern recognition (psychology) , computer science , feature (linguistics) , support vector machine , identification (biology) , word (group theory) , image (mathematics) , rotation (mathematics) , feature extraction , computer vision , mathematics , philosophy , linguistics , botany , geometry , biology
SIFT and LBP are two popular techniques used for obtaining “feature description" of the object. SIFT identifies key points that are locations with distinct image information and robust to scaling and rotation whereas, LBP transforms an image into an array of integer labels describing small scale appearance of the image. In this paper, we present an efficient method wherein “feature description” of handwritten document images at word level are computed using SIFT and LBP. Identification of script type is done using KNN and SVM classifiers. Experimental results show that the performance of SVM is better over KNN. Further, the proposed method is compared with other methods in the literature to demonstrate the efficacy of the proposed method.