Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal JOIV : International Journal on Informatics Visualization
George, Dena Nadir
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Robust and Automatic Algorithm for Palmprint ROI Extraction Yousif, Noor A.; Qassir, Samar Amil; George, Dena Nadir
JOIV : International Journal on Informatics Visualization Vol 9, No 1 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.1.2801

Abstract

The ridges, creases, wrinkles, and minutiae on the palmprint region of interest (ROI) are important features. These features are employed to confirm or identify an individual. One inevitable issue in the realization of palmprint recognition systems is the extraction procedure of this region under unrestricted environments. The variety in palm sizes, postures, lighting conditions, and backgrounds, however, certainly presents a significant issue. Finding and extracting the palm's area of interest (ROI) will be our main goal. This research introduces a robust automated algorithm based on square construction and each YCbCr color space features. After reading the image of the colored hand, this algorithm goes through two stages. Firstly, convert to the YCbCr color space. This stage guarantees precise locating of the hand region in addition to deleting irrelevant information from the image. Secondly, determining ROI is based on applying three steps: locating three key references, utilizing these key references to construct the main line, and finally, constructing the ROI square. The total color hand images (230) were used to test and evaluate the newly introduced algorithm; 30 were collected from the internet; and 200 were chosen from the Birjand University Mobile Palmprint Database (BMPD). The hand images include two orientations, left and right, varying sizes and backgrounds, uneven illumination, shadows, and some hand images have items on the finger(s). The experimental findings demonstrate that the introduced algorithm effectively attained 100% and 99.565% sensitivity and accuracy, respectively.
Co-Authors Qassir, Samar Amil Yousif, Noor A.