TY - GEN
T1 - Parallel Equilibrium Difference Local Binary Pattern Using GPU
AU - Yadav, Uday
AU - Sheelvant, Abhishek G.
AU - Ashwath Rao, B.
AU - Gopalakrishna Kini, N.
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
PY - 2025
Y1 - 2025
N2 - In the realm of computer vision and image processing, local pattern descriptors play a crucial role in extracting discriminative features for various applications. The Equilibrium Difference Local Binary Pattern (ED-LBP) is a recently proposed method that combines color information with local binary patterns, enhancing its robustness and discriminative power. However, the computational demands of ED-LBP is significantly high due to additional mathematical constraints, especially when processing high-resolution images. In this paper, the implementation of ED-LBP is parallelized to improve computational efficiency and enable real-time processing of large-scale image datasets. Our approach leverages the power of Graphics Processing Units (GPUs), resulting in a significant reduction in feature extraction time without compromising the accuracy of the ED-LBP algorithm.
AB - In the realm of computer vision and image processing, local pattern descriptors play a crucial role in extracting discriminative features for various applications. The Equilibrium Difference Local Binary Pattern (ED-LBP) is a recently proposed method that combines color information with local binary patterns, enhancing its robustness and discriminative power. However, the computational demands of ED-LBP is significantly high due to additional mathematical constraints, especially when processing high-resolution images. In this paper, the implementation of ED-LBP is parallelized to improve computational efficiency and enable real-time processing of large-scale image datasets. Our approach leverages the power of Graphics Processing Units (GPUs), resulting in a significant reduction in feature extraction time without compromising the accuracy of the ED-LBP algorithm.
UR - https://www.scopus.com/pages/publications/105011255887
UR - https://www.scopus.com/pages/publications/105011255887#tab=citedBy
U2 - 10.1007/978-981-96-2700-4_7
DO - 10.1007/978-981-96-2700-4_7
M3 - Conference contribution
AN - SCOPUS:105011255887
SN - 9789819626991
T3 - Lecture Notes in Networks and Systems
SP - 83
EP - 92
BT - 5th Congress on Intelligent Systems, CIS 2024
A2 - Kumar, Sandeep
A2 - Mary Anita, E.A.
A2 - Kim, Joong Hoon
A2 - Nagar, Atulya
PB - Springer Science and Business Media Deutschland GmbH
T2 - 5th Congress on Intelligent Systems, CIS 2024
Y2 - 4 September 2024 through 5 September 2024
ER -