Automatic Extraction of Two Regions of Creases from Palmprint Images for Biometric Identification

Abstract

Palmprint has become one of the biometric modalities that can be used for personal identification. This modality contains critical identification features such as minutiae, ridges, wrinkles, and creases. In this research, feature from creases will be our focus. Feature from creases is a special salient feature of palmprint. It is worth noting that currently, the creases-based identification is still not common. In this research, we proposed a method to extract crease features from two regions. The first region of interest (ROI) is in the hypothenar region, whereas another ROI is in the interdigital region. To speed up the extraction, most of the processes involved are based on the processing of the image that has been a downsampled image by using a factor of 10. The method involved segmentations through thresholding, morphological operations, and the usage of the Hough line transform. Based on 101 palmprint input images, experimental results show that the proposed method successfully extracts the ROIs from both regions. The method has achieved an average sensitivity, specificity, and accuracy of 0.8159, 0.9975, and 0.9951, respectively.

Image-Based Measurement of Hand Parameters for Burn and Scald Treatments

“…Therefore, we must obtain the position, posture, and edge information of the hand to eliminate the measurement error. Automatic tracking and the identification of hand images have received significant attention in recent years [15,16]. The automatic edge tracking method of a hand is described in the following steps.…”

Quality Assessment Methods to Evaluate the Performance of Edge Detection Algorithms for Digital Image: A Systematic Literature Review

“…I N some computer vision applications, image segmentation is required to identify objects and analyze images automatically or help humans find the region of interest [1]- [3]. Edge detection is one of the significant branches available for image segmentation.…”

Improving GPR Imaging of the Buried Water Utility Infrastructure by Integrating the Multidimensional Nonlinear Data Decomposition Technique into the Edge Detection

“…A variety of data processing techniques have been proposed to improve the accuracy of GPR imaging [2][3][4][5][6]. Edge detection is a technique formerly used by computer engineers in the analysis of images to outline the essential information of the data [7][8][9]. In the years since the edge detection technique was proposed in the 1970s [10,11], it was once considered only an alternative image segmentation technique, but now it has become a major field of study within image processing.…”