Dynamic weighted discrimination power analysis in DCT domain for face and palmprint recognition

Leng, Lu; Zhang, Jiashu; Xu, Jing; Khan, Muhammad Khurram; Alghathbar, Khaled

doi:10.1109/ictc.2010.5674791

Cited by 123 publications

(60 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sparse random matrix for random projection used in this paper is generated according to [13]. Since face and palmprint are two popular biometrics for identity authentication [14][15], the experimental results on ORL face database, Yale face database and PolyU palmprint database confirm the performance and effectiveness of (2D) 2 RP and its variations. The comparisons among the methods are discussed and analyzed extensively.…”

Section: Introductionsupporting

confidence: 62%

Two-Directional Two-Dimensional Random Projection and Its Variations for Face and Palmprint Recognition

Leng

Zhang

Chen

et al. 2011

Computational Science and Its Applications - ICCSA 2011

Self Cite

View full text Add to dashboard Cite

Abstract. 2DRP (two-dimensional random projection) is two-dimensional extension of one-dimensional RP (random projection) to keep biometric images from being reshaped to vectors before RP for recognition. We propose a novel method called (2D) 2 RP (two-directional two-dimensional random projection) for feature extraction of biometrics. (2D) 2 RP directly projects the image matrix from high-dimensional space to low-dimensional space to extract optimal projective vectors at row-direction and column-direction. (2D) 2 RP, similar to RP, can also avoid the problems of singularity, SSS (small sample size) and overfitting; furthermore it has much less storage and computational cost than RP. Besides, the variations of (2D) 2 RP combined with 2DPCA and 2DLDA are developed. Experimental results and comparison discussion among (2D) 2 RP and its variations on face and palmprint databases confirm the performance and effectiveness of (2D) 2 RP and its variations.

show abstract

Section: Introductionsupporting

confidence: 62%

Two-Directional Two-Dimensional Random Projection and Its Variations for Face and Palmprint Recognition

Leng

Zhang

Chen

et al. 2011

Computational Science and Its Applications - ICCSA 2011

Self Cite

View full text Add to dashboard Cite

show abstract

“…Geometric methods, 14,15 statistical methods, [16][17][18] subspace methods, 19,20 and texture coding methods [21][22][23] are widely used methods for extracting palmprint features. Geometric methods, 14,15 statistical methods, [16][17][18] subspace methods, 19,20 and texture coding methods [21][22][23] are widely used methods for extracting palmprint features.…”

Section: Figure 1 Palmprint Featuresmentioning

confidence: 99%

“…and extract the ROI. Geometric methods, 14,15 statistical methods, [16][17][18] subspace methods, 19,20 and texture coding methods [21][22][23] are widely used methods for extracting palmprint features. In this paper, bottom-hat filtering approach is implemented to extract the characters from the palmprint images because this method only can solve requirements of identification compared to previously represented methods.…”

Section: Figure 1 Palmprint Featuresmentioning

confidence: 99%

Highly secure palmprint based biometric template using fuzzy vault

Venkatapathy

Chitra²

2018

Concurrency and Computation

View full text Add to dashboard Cite

Biometric cryptosystem is an integrated system of cryptography with biometric features which is considered to be a promising component of template security. This paper presents a novel method for biometric cryptosystem based on fuzzy vault using palmprint features. Initially, pre-processing is performed to remove noise in palmprint enrolled image and to pre-align image automatically.Bottom-hat filtering is employed for the feature extraction from the palmprint images. A polynomial is evaluated from the secret key and this polynomial is used to generate projections from palmprint features. Fuzzy vault is created by combining projected points with randomly generated dummy or chaff points. During decoding process, matching scores are calculated by comparing the query feature and stored vault. The vault is successfully decoded when the matched scores should be greater than a predefined threshold value. Experiments were conducted on CASIA database.Simulation result demonstrates that the proposed method gives better performance than other methods and improves the robustness against some security attacks. KEYWORDSbrute force attack, fuzzy vault, palmprint, principal line, security analysis, template protection INTRODUCTIONBiometrics is one of the reliable approaches to measure human individuality with the end goal of authenticating or identifying the character of a core. Palmprint, fingerprint, iris, palm vein, retina, facial features, voice, handwriting, and signatures are commonly used characteristics in person recognition. 1 Among these characteristics, palmprint identification has many advantages: higher acceptance rate, low-resolution image, stable line features, rich texture information, and low intrusiveness. Palms are large in size and palmprint has the features like principal lines, wrinkles, delta point, datum point, minutiae, and creases (a), as shown in Figure 1. 2 Template is a digital representation of the unique feature set that has been obtained from the biometric sample during enrolment process and stored in the system database. It represents a strong link between a person, his/her identity, and these characteristics cannot be easily forged or lost. 3 However, biometric based identification system requires huge volume of biometric information that leads to identity theft and leakage of privacy. Biometric template security has drawn more attention from the researchers. Both biometrics and cryptography have combined in order to address problem of biometric template protection. Various biometric template protection methods have been found in the literature. [4][5][6][7] Biometric cryptosystems have been emerged as a promising tool for biometric template protection. These systems integrate biometric features with the transformed version of cryptographic keys to generate secure biometric template. In biometric cryptosystem, some public information named as helper data is generated. 8 Based on the usage of helper data, biometric cryptosystems can be categorized into two methods, namely, key generation and key...

show abstract

“…In addition, the user acceptance of palmprint is high. Due to the several advantages of palmprint, it has been widely used for identity authentication [4].…”

Section: Introductionmentioning

confidence: 99%

Logical Conjunction of Triple-Perpendicular-Directional Translation Residual for Contactless Palmprint Preprocessing

Leng

Liu

et al. 2014

2014 11th International Conference on Information Technology: New Generations

Self Cite

View full text Add to dashboard Cite

Contactless palmprint recognition systems alleviate the concerns on personal hygiene, acquisition flexibility, etc. Unfortunately, the preprocessing of contactless palmprint image faces several severe challenges, including unconstrained hand placement, complex background, light interference, etc. This paper proposes logical conjunction of triple-perpendiculardirectional translation residual (TPDTR) for the improvement of contactless palmprint image preprocessing. The search of hand valley point is within the borders of hand valley gap detected by TPDTR; therefore, the computational cost is effectively decreased. Furthermore, the anti-interference capacity of region is stronger than that of point and line, so TPDTR improves the accuracy of hand valley point detection. The experimental results confirm the superiorities of TPDTR over the existing methods in computational cost and accuracy.

show abstract

Dynamic weighted discrimination power analysis in DCT domain for face and palmprint recognition

Cited by 123 publications

References 12 publications

Two-Directional Two-Dimensional Random Projection and Its Variations for Face and Palmprint Recognition

Two-Directional Two-Dimensional Random Projection and Its Variations for Face and Palmprint Recognition

Highly secure palmprint based biometric template using fuzzy vault

Logical Conjunction of Triple-Perpendicular-Directional Translation Residual for Contactless Palmprint Preprocessing

Contact Info

Product

Resources

About