The Extract Region of Interest in High-Resolution Palmprint using 2D Image Histogram Entropy Function

Abstract

The segmentation of high-resolution palmprint is has been challenged and the research in this filed is still limited because of variations in location and distortion of these images. To achieve superior recognition result, accurate segmentation of a region of interest is very crucial. Therefore, in this paper, a novel palmprint extraction method has been presented using a 2D image histogram entropy function and mathematical dilation. The proposed method has two phases. The first phase is the binarization image where the histogram of the image will be determined after applying a median filter to remove noise and then calculating the 2D image histogram entropy function. Finally, the maximum entropy that will be the adaptive threshold value to build a binary palmprint image will be selected. The second phase is to extract the ROI, apply a dilation method on the binary image, then dividing the dilate image into four regions and finding four reference points depending on the white percentage and finally the ROI will be extracted. The publically available high-resolution palmprint THUPALMLAB has been used for testing. The result indicates a high percentage of accuracy up to 93%. The findings strongly indicate that the proposed method was able to extract the palm's ROI more consistently. These ROIs will be used in the recognition system instead of whole palmprints and hence assists in improving the performance of a traditional palmprint system. High-resolution palmprint images are highly used in the forensic application.

Human Recognition based on Multi-instance Ear Scheme

“…Second, removing noise while preserving the edge details of the ear image with the median filter [33]. Then, using the Entropy function, the grayscale image is transformed into a binary image [1]. Finding the edges is supported by binary images.…”

“…The edges can be used to calculate an outer line. The edges of the ear image are calculated using the dilation morphology [1]. The steps for ear ROI extraction are summarized in Fig.…”

“…Colleagues consider fingerprints and iris to be more exact in biometric examination than the face, yet the face has different characteristics like being effectively gotten in genuine circumstances without client communication. Be that as it may, the face without anyone else isn't as adaptable as it ought to be because of brightening and demeanor changes [1]. On the other hand, ear recognition is a sort of new biometrics, the hypothesis and examination of ear recognition excite additional consideration from homegrown and unfamiliar researchers.…”

Multimodal Recognition System Based on High-Resolution Palmprints

“…Therefore, it is difficult to extract ROIs. However, we adopted the ROI method that was reported in [37], which includes two phases, namely, the binarization phase and the ROI extraction phase. The binarization phase is comprised of three steps: first, noise removal using a median filter; second, 2D palmprint image histogram calculation; and third, binarization of the palmprint image by calculating the 2D histogram entropy and selecting the maximum entropy as a threshold value.…”

“…Based on the method that was introduced in [37] and described in the preprocessing section, the palmprint ROIs have been extracted. Figure 6 summarizes the steps for extracting the palmprint ROIs.…”