Characterizing Global Hand-Crafted Feature Descriptors for Sketch-Based Image Retrie

Sketch-based Image Retrieval (SBIR) is an essential method of searching objects by drawing them in two-dimensional (2-D). The SBIR problem was that the image inside the dataset did not match the pair due to its modality difference. The main objective of this research is to compare which descriptor i...

Full description

Saved in:

Bibliographic Details
Published in:	2021 6th IEEE International Conference on Recent Advances and Innovations in Engineering (ICRAIE) Vol. 6; pp. 1 - 4
Main Authors:	Abbas, Mohd Hussaini, Che Ani, Adi Izhar, Abd Samat, Ahmad Asri, Hazim, Muhamad Amirul, Abdul Kader, Mohamed Mydin M., Setumin, Samsul, Hamidi, Mohd
Format:	Conference Proceeding
Language:	English
Published:	IEEE 01-12-2021
Subjects:	Conferences Feature extraction Gabor and LBP Histograms HOG Image retrieval SBIR Technological innovation Training Two dimensional displays
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Sketch-based Image Retrieval (SBIR) is an essential method of searching objects by drawing them in two-dimensional (2-D). The SBIR problem was that the image inside the dataset did not match the pair due to its modality difference. The main objective of this research is to compare which descriptor is better adapted to the SBIR. Histogram of Oriented Gradient (HOG), Gabor, and Local Binary Pattern (LBP) are selected for the study. Each sample will be divided into distance measures with features vector that corresponds to the training dataset will be compared the performance in order to study the best adapted to SBIR. Histogram of Oriented Gradient (HOG) is identified as the best descriptor for SBIR. HOG has shown a better performance than Gabor and LBP since the method shows the highest percent of distance matrices accuracy.
DOI:	10.1109/ICRAIE52900.2021.9703823