Wyniki wyszukiwania - BazTech

1

Palmprint Recognition Using Gabor-Based Scale Orientation

Kusban Muhammad

International Journal of Electronics and Telecommunications

|

2022

|

Vol. 68. No. 3

641--646

EN

Various methods are used to obtain a superior palmprint recognition system. After selecting a palmprint image filter, using Gabor orientation scale pairs is an option to support the refinement of the verification process. Many researchers use the [8×5] pair for the value of the Gabor orientation scale in the field of palmprint recognition. However, from the experiments conducted, other Gabor pairs have more impact on system improvement. The problem is to get the most suitable value pairs for palmprint applications, so in this study, a comparison of seven kinds of Gabor pairs is carried out. This Gabor pair being compared applies using original images, PCA dimension reduction, and the Euclidean method. From the research that has been done, the pair of Gabor orientation scale [8×7] or image expansion of 56 will have the most significant impact compared to other pairs. Suppose the result of this Gabor pair is [8×7] by using other improvement systems, namely the 3W filter instead of the original image, KPCA to replace the PCA, and the cosine method in the matching method. In that case, it will increase the verification value by 99.611%. The trial value obtained can be an alternative method of choice for improving palmprint recognition.

2

Weighted multimodal biometric recognition algorithm based on histogram of contourlet oriented gradient feature description

Zhang Xinman, Cheng Dongxu, Xu Xuebin

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

381–-384

EN

Although the unimodal biometric recognition (such as face and palmprint) has higher convenience, its security is also relatively weak. The recognition accuracy is easy affected by many factors such as ambient light and recognition distance etc. To address this issue, we present a weighted multimodal biometric recognition algorithm with face and palmprint based on histogram of contourlet oriented gradient (HCOG) feature description. We employ the nonsubsampled contour transform (NSCT) to decompose the face and palmprint images, and the HOG method is adopted to extract the feature, which is named as HCOG feature. Then the dimension reduction process is applied on the HCOG feature and a novel weight value computation method is proposed to accomplish the multimodal biometric fusion recognition. Extensive experiments illustrate that our proposed weighted fusion recognition can achieve excellent recognition accuracy rates and outmatches the unimodal biometric recognition methods.

3

Palmprint recognition based on convolutional neural network-Alexnet

Gong Weiyong, Zhang Xinman, Deng Bohua, Xu Xuebin

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

313–-316

EN

In the classic algorithm, palmprint recognition requires extraction of palmprint features before classification and recognition, which will affect the recognition rate. To solve this problem, this paper uses the convolutional neural network (CNN) structure Alexnet to realize palmprint recognition. First, according to the characteristics of the geometric shape of palmprint, the ROI area of palmprint was cut out. Then the ROI area after processing is taken as input layer of convolutional neural network. Next the PRelu activation function is used to train the network to select the best learning rate and super parameters. Finally, the palmprint was classified and identified. The method was applied to PolyU Multi-Spectral Palmprint Image Database and PolyU 2D+3D Palmprint Database, and the recognition rate of a single spectrum was up to 99.99%.

4

Fast near-infrared palmprint recognition using nonnegative matrix factorization extreme learning machine

Xu X., Zhang X., Lu L., Deng W., Zuo K

Optica Applicata

|

2014

|

Vol. 44, nr 2

285--298

EN

Support vector machine and artificial neural network are widely used in classification applications. Extreme learning machine (ELM) is a novel and efficient learning algorithm based on the generalized single hidden layer feed forward networks, which performs well in classification applications. The research results have shown the superiority of ELM with the existing classical algorithms: support vector machine (SVM) and back propagation neural network. In this study, we firstly propose a novel nonnegative matrix factorization extreme learning machine (NMFELM) to improve the performance of standard ELM method. Then we propose a novel near-infrared palmprint recognition approach based on NMFELM classifier. As the test data, we use the near-infrared palmprint database provided by Hong Kong Polytechnic University. The experimental results demonstrate that the proposed NMFELM method outperforms the standard ELM- and SVM-based methods.