Hybridization of Texture Features
for Identification of Bi-Lingual Scripts
from Camera Images at Wordlevel
Satishkumar Mallappa, B. V. Dhandra, and Gururaj Mukarambi
Abstract In this paper, hybrid texture features are proposed for identification of
scripts of bi-lingual camera images for a combination of 10 Indian scripts with Roman
scripts. Initially, the input gray-scale picture is changed over into an LBP image, then
GLCM and HOG features are extracted from the LBP image named as LBGLCM
and LBHOG. These two feature sets are combined to form a potential feature set
and are submitted to KNN and SVM classifiers for identification of scripts from the
bilingual camera images. In all 77,000-word images from 11 scripts each contributing
7000-word images. The experimental results have shown the identification accuracy
as 71.83 and 71.62% for LBGLCM, 79.21 and 91.09% for LBHOG, and 84.48 and
95.59% for combined features called CF, respectively for KNN and SVM.
Keywords LBP · LBGLCM · LBHOG · GLCM · HOG · KNN · SVM
1 Introduction
In the present situation there is a significant improvement in internal storage, the
performance of the processors, and high resolution handheld mobile devices such
as smartphones; have emerged new ways of capturing and processing images in
general and document images in particular. With these handheld mobile devices,
users can easily capture the images of hard documents, too fragile documents, text
present in the scene, signboards, text on monuments, business boards, digital boards,
historical documents, text written on leaves, carved on stones and so on. Along with
S. Mallappa ( )
Department of P.G.Studies and Research in Computer Science, Gulbarga University, Gulbarga,
India
e-mail: satishkumar697.compsc@gug.ac.in
B. V. Dhandra
Department of Statistics, Christ (Deemed to Be University), Bengaluru, India
G. Mukarambi
School of Computer Science, Department of Computer Science, Central University of Karnataka,
Gulbarga, India
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2023 1
R. J. Kannan et al. (eds.), Computer Vision and Machine Intelligence Paradigms
for SDGs, Lecture Notes in Electrical Engineering 967,
https://doi.org/10.1007/978-981-19-7169-3_11