Academia.eduAcademia.edu

Figure 10 – uploaded by Khamis A . Zidan

See full PDFdownloadDownload figure
Figure 13. Sample HOG descriptors. Each cell of the patch shows the orientation of the gradients Following image(see figure 13) shows the gradient directions for a sample image patch: The above stated steps therefore normalize the block- cells whose joint histograms establish the HOG feature vector of the complete image. Scaling and rotation do not affect the algorithm because only the key points are used for scale-space extrema detection [44]. Following image(see figure 13) shows the eradient directions for a sample image patch: Thus, HOG descriptor primarily comprises of features about histograms of slopes of object edges of an image. HOG feature descriptor can be defined by the equation [45]:

Figure 13 Sample HOG descriptors. Each cell of the patch shows the orientation of the gradients Following image(see figure 13) shows the gradient directions for a sample image patch: The above stated steps therefore normalize the block- cells whose joint histograms establish the HOG feature vector of the complete image. Scaling and rotation do not affect the algorithm because only the key points are used for scale-space extrema detection [44]. Following image(see figure 13) shows the eradient directions for a sample image patch: Thus, HOG descriptor primarily comprises of features about histograms of slopes of object edges of an image. HOG feature descriptor can be defined by the equation [45]:

Related Figures (24)

Finger vein comes under the category of intrinsic features, and is therefore hard to replicate and alter. In a trans-illumination manner, near-infrared (NIR) light (700-900 nm) is used to capture finger veins [10]. For personal verification, systems based on veins generally use diverse anatomic features like finger vein, hand vein, foot vein or palm vein. The most recommended is finger vein because it has the smallest imaging tool and has larger number of veins as compared to palm and hand [6]. Additionally, even for the identical twins, vein pattern for every finger is unique and exists only for humans as long as they are alive [11]. More importantly, during lifetime, a finger vein pattern does not alter [5]. Finger vein recognition is viewed as one of the most challenging tasks because of low image contrast, uneven- illumination and variations in temperature. Finger vein identification systems are also secure against spoof
Finger vein comes under the category of intrinsic features, and is therefore hard to replicate and alter. In a trans-illumination manner, near-infrared (NIR) light (700-900 nm) is used to capture finger veins [10]. For personal verification, systems based on veins generally use diverse anatomic features like finger vein, hand vein, foot vein or palm vein. The most recommended is finger vein because it has the smallest imaging tool and has larger number of veins as compared to palm and hand [6]. Additionally, even for the identical twins, vein pattern for every finger is unique and exists only for humans as long as they are alive [11]. More importantly, during lifetime, a finger vein pattern does not alter [5]. Finger vein recognition is viewed as one of the most challenging tasks because of low image contrast, uneven- illumination and variations in temperature. Finger vein identification systems are also secure against spoof
Figure 2. SDUMLA-HMT database- sample data In compilation of images, a number of people who take part is one hundred and six (106). The format of images of vein is .bmp. Of each person, images of both two hands were taken. Data of three fingers were
Figure 2. SDUMLA-HMT database- sample data In compilation of images, a number of people who take part is one hundred and six (106). The format of images of vein is .bmp. Of each person, images of both two hands were taken. Data of three fingers were
Figure 4.(a)Database image,(b)Mask obtained ,(c)Cropped finger. Boundary of the finger is detected by computation of the masking value in y dimension for each value along the x dimension. This masking value has a point of maximization which is actually the boundary of the finger in y direction [21].The database image is then cropped by keeping the portion of only those rows which are fully white on the correspoinding mask(see figure 4).
Figure 4.(a)Database image,(b)Mask obtained ,(c)Cropped finger. Boundary of the finger is detected by computation of the masking value in y dimension for each value along the x dimension. This masking value has a point of maximization which is actually the boundary of the finger in y direction [21].The database image is then cropped by keeping the portion of only those rows which are fully white on the correspoinding mask(see figure 4).
Figure 7.(a) Image before Histogram equalization , (b)Image histogram
Figure 7.(a) Image before Histogram equalization , (b)Image histogram
Figure 8.(a)Image After Cumulative Histogram equalization ,(b) Image Histogram The image as shown in figure 8(a) shows the results after cumulative histogram equalization. In comparison to figure 8(b) it is flat.
Figure 8.(a)Image After Cumulative Histogram equalization ,(b) Image Histogram The image as shown in figure 8(a) shows the results after cumulative histogram equalization. In comparison to figure 8(b) it is flat.
3.1.4 Median filtering nl Median filtering is a non-linear process. To remove the impulsive and salt-and-pepper noise, median filtering is done on the image. For each pixel, a window is used to select neighboring pixels. For the pixels within this window, the median intensity value is computed and that median value is assigned to the pixel on which the operation was being performed. For each pixel of the image, this process is repeated [33]. It smoothly removes noise and preserves the edge-information. Strength of median filter depends upon window size [34]. For the experiments of this research, we used window size of 3x3(see figure 10).
3.1.4 Median filtering nl Median filtering is a non-linear process. To remove the impulsive and salt-and-pepper noise, median filtering is done on the image. For each pixel, a window is used to select neighboring pixels. For the pixels within this window, the median intensity value is computed and that median value is assigned to the pixel on which the operation was being performed. For each pixel of the image, this process is repeated [33]. It smoothly removes noise and preserves the edge-information. Strength of median filter depends upon window size [34]. For the experiments of this research, we used window size of 3x3(see figure 10).
Up till here we have discussed a method to bring out the unique shape of each finger vein pattern. We will call it Proposed method 1. We also carried out experimentation with changed orders of these enhancement steps and computed results. It was found that a rearrangement of these steps yielded slightly blurred images, but there was a distinct pattern in those images for each class and such images were giving marginally improved results as compared to Proposed method 1. We will call it Proposed method 2. A comparison of both these approaches is given in table 1, for person 103 (middle finger of left hand): In tough visual situation, Histogram of Oriented Gradient (HOG) feature extraction is extensively used due t its ability to do well in those situations [37].
Up till here we have discussed a method to bring out the unique shape of each finger vein pattern. We will call it Proposed method 1. We also carried out experimentation with changed orders of these enhancement steps and computed results. It was found that a rearrangement of these steps yielded slightly blurred images, but there was a distinct pattern in those images for each class and such images were giving marginally improved results as compared to Proposed method 1. We will call it Proposed method 2. A comparison of both these approaches is given in table 1, for person 103 (middle finger of left hand): In tough visual situation, Histogram of Oriented Gradient (HOG) feature extraction is extensively used due t its ability to do well in those situations [37].
Figure 14. (a) Sample image (b) Visualization of gradients. Each block (red outline) contains four cells (white outline) (c) Process of generating HOG feature vector [45]
Figure 14. (a) Sample image (b) Visualization of gradients. Each block (red outline) contains four cells (white outline) (c) Process of generating HOG feature vector [45]
Figure 15. K-tree decomposition structure [48].
Figure 15. K-tree decomposition structure [48].
Table 3 . Average computational time per step for method 2 Table 2. Average computational time per step for method 1 An extensive evaluation of the algorithm was performed. Every possible combination of finger type and hand type was tested for each feature extraction method and also for each classifier. It was found that the middle finger is the most discriminative of all for the considered dataset of 106 persons. For the experimental results mentioned below, each finger of each hand is considered a separate category, even if it is of the same person(see figure 17). The computational time for each stage of the two proposed enhancement methods is presented in table 2 and 3
Table 3 . Average computational time per step for method 2 Table 2. Average computational time per step for method 1 An extensive evaluation of the algorithm was performed. Every possible combination of finger type and hand type was tested for each feature extraction method and also for each classifier. It was found that the middle finger is the most discriminative of all for the considered dataset of 106 persons. For the experimental results mentioned below, each finger of each hand is considered a separate category, even if it is of the same person(see figure 17). The computational time for each stage of the two proposed enhancement methods is presented in table 2 and 3
The process of learning data representations with many levels of abstraction through a set of computation< models based on numerous processing layers is called “Deep Learning” (see figure 16) [54] [55] 5.2 Deep Neural Networks
The process of learning data representations with many levels of abstraction through a set of computation< models based on numerous processing layers is called “Deep Learning” (see figure 16) [54] [55] 5.2 Deep Neural Networks
Table 4. Results of KNN with right hand, middle GR a
Table 4. Results of KNN with right hand, middle GR a
Table 5. Results of DNN with right hand, middle BE tise eae
Table 5. Results of DNN with right hand, middle BE tise eae
Results of recognition and verification for middle finger of right hand, left hand and both hands are summarized in the tables below. For KNN, results are given with HOG, HC and with combined feature vector of HOG and HC. For DNN, dimensions of combined HOG and HC were first reduced (to be equal to 75) using Generalized Discriminant Analysis (GDA) [56] before giving them for classification. Reason for this is that data samples per class were limited and DNN is known to work best on extensive data whose feature length is not more than the total available samples(see tables 4,5,6,7,8,9).
Results of recognition and verification for middle finger of right hand, left hand and both hands are summarized in the tables below. For KNN, results are given with HOG, HC and with combined feature vector of HOG and HC. For DNN, dimensions of combined HOG and HC were first reduced (to be equal to 75) using Generalized Discriminant Analysis (GDA) [56] before giving them for classification. Reason for this is that data samples per class were limited and DNN is known to work best on extensive data whose feature length is not more than the total available samples(see tables 4,5,6,7,8,9).
Table 8. Results of KNN with both right and left hand, middle finger Table 6. Results of KNN with left hand, middle finger
Table 8. Results of KNN with both right and left hand, middle finger Table 6. Results of KNN with left hand, middle finger
7. Conclusion and future work Table 10. Results with all fingers of both hands with stratified 6 fold cross validation In this paper, we introduce two novel methods of finger vein enhancement for recognition and verification purposes. An extensive evaluation of results is done with KNN and also with DNN. KNN proved to be much more accurate in its predictions on test data. Using stratified 6- fold analysis on all fingers of all hands in the SDUMLA database, a maximum accuracy of 97.6415% was achieved with an EER of 0.0037. based on the analysis of the 106 persons present in the dataset, it was found that the most discriminative finger is the middle finger of right hand which gives above 99% accuracy. For future work, the parameters of DNN can be optimized using some optimization methods [58] Furthermore, in this research we fed to DNN, feature vectors after reducing their dimensions to 75 using LNINA a, a ee, ee ey , ee, es ee fh ee: ee S| ee. ee Sy J 2.1.2.2 Le.
7. Conclusion and future work Table 10. Results with all fingers of both hands with stratified 6 fold cross validation In this paper, we introduce two novel methods of finger vein enhancement for recognition and verification purposes. An extensive evaluation of results is done with KNN and also with DNN. KNN proved to be much more accurate in its predictions on test data. Using stratified 6- fold analysis on all fingers of all hands in the SDUMLA database, a maximum accuracy of 97.6415% was achieved with an EER of 0.0037. based on the analysis of the 106 persons present in the dataset, it was found that the most discriminative finger is the middle finger of right hand which gives above 99% accuracy. For future work, the parameters of DNN can be optimized using some optimization methods [58] Furthermore, in this research we fed to DNN, feature vectors after reducing their dimensions to 75 using LNINA a, a ee, ee ey , ee, es ee fh ee: ee S| ee. ee Sy J 2.1.2.2 Le.
Related topics:
Computer ScienceArtificial IntelligenceHistogram Equalization
580 California St., Suite 400
San Francisco, CA, 94104
© 2025 Academia. All rights reserved