Face authentication system using pseudo Zernike moments on wavelet subband

Pang, Ying Han; Teoh, B. J. Andrew; Ngo, Chinh

doi:10.1587/elex.1.275

Cited by 8 publications

(5 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They include Eigenpalms and Eigenfinger (2) (8) (9) , Fisherpalms (10) , those based on local and global texture (6) (11) , using Gabor filters (12) , and Fourier Transform (2) (13) (14) . On the other hand, structural methods extract information from structural features of palmprints such as principal lines, wrinkles, creases and minutiae and include the use of the Radon transform to extract principal lines (15) , extraction of features based on palm creases (16) (17) , extraction of structural features using wavelets and pseudo Zernike moments (18) (19) , and the use of hand geometry features (20) .…”

Section: Related Workmentioning

confidence: 99%

“…The major drawback of these methods is their failure to effectively account for the effects of noise because they use the whole DFT image and give equal weight to all frequency bands. This ignores the noise which is encoded in the high frequency components and can adversely affect discrimination (19) (22) . In previous work (23) , DFT features were used in combination with a genetic algorithm to select an optimal set of coefficients which are weighted in such a way that the high-frequency components are less likely to be selected.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

A Local DCT-II Feature Extraction Approach for Personal Identification Based on Palmprint

et al. 2010

View full text Add to dashboard Cite

Biometric applications based on the palmprint have recently attracted increased attention from various researchers. In this paper, a method is presented that differs from the commonly used global statistical and structural techniques by extracting and using local features instead. The middle palm area is extracted after preprocessing for rotation, position and illumination normalization. The segmented region of interest is then divided into blocks of either 8×8 or 16×16 pixels in size. The type-II Discrete Cosine Transform (DCT) is applied to transform the blocks into DCT space. A subset of coefficients that encode the low to medium frequency components is selected using the JPEG-style zigzag scanning method. Features from each block are subsequently concatenated into a compact feature vector and used in palmprint verification experiments with palmprints from the PolyU Palmprint Database. Results indicate that this approach achieves better results than many conventional transform-based methods, with an excellent recognition accuracy above 99% and an Equal Error Rate (EER) of less than 1.2% in palmprint verification.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

A Local DCT-II Feature Extraction Approach for Personal Identification Based on Palmprint

et al. 2010

View full text Add to dashboard Cite

show abstract

“…The holistic matching methods can further be classified into two groups: the frequency based methods and sub space based methods. Most of the frequency methods utilize the low frequency components and discard the high frequency components due to the fact that low frequency components are insensitive to noise and facial expression, whereas the high frequency components are more sensitive to noise [3,4]. Fourier transform [5][6][7] and discrete cosine transform [8][9][10] are most frequently used in these methods. )…”

Section: Introductionmentioning

confidence: 99%

Face recognition using effective and fast approach

2016

IJMTER

View full text Add to dashboard Cite

Face recognition process in human perception utilizes two kinds of features. The first are global features used to describe the whole face image, while the second are local features used to describe finer details of the face. The combined face recognition methods stimulate the technique used by human perception to recognize the face images in a natural way. Therefore, the combinations of global and local features have received significant success in face recognition problem. In this paper, we propose a combined global and local face recognition method. The global features are obtained using complex Zernike moments (CZMs), while the local features are captured using a modified form of the local binary pattern (LBP) descriptor. The CZMs use both the magnitude and phase of complex moments to represent global features effectively. We use fast algorithm to compute Zernike moments (ZMs) to increase the speed of the proposed method. A new form of LBP which uses a 5 5 window instead of the convention 3 3 window has been developed which enhances recognition rate significantly. Extensive experiments have been conducted on five different face databases, namely, FERET, JAFFE, YALE, UMIST, and ORL to evaluate the performance of the proposed method under different face recognition conditions. Results of these experiments reveal that the proposed method is much more robust against facial expression, pose, and illumination variations than the existing combined approaches.

show abstract

“…Hence, feature extraction techniques are crucial to retrieve those representative and discriminative features from the data. Numerous feature extraction techniques have been proposed [2][3] [4][5] [6] [7][8] [9].…”

Section: Introductionmentioning

confidence: 99%

Discriminative Discriminant Common Vector in face verification

Pang

Teoh

Ping

et al. 2014

2014 International Conference on Computer and Information Sciences (ICCOINS)

View full text Add to dashboard Cite

Discriminant Common Vectors (DCV) is proposed to solve small sample size problem. Face recognition encounters this dilemma where number of training samples is always smaller than the data dimension. In literature, it is shown that DCV is efficient in face recognition. In this paper, DCV is enhanced for further boosting its discriminating power. This modified version is namely Discriminative Discriminant Common Vectors (DDCV). In this technique, a local Laplacian matrix of face data is computed. This matrix is used to derive a regularization model for computing discriminative class common vectors.Experimental results demonstrate that DDCV illustrates its effectiveness on face verification, especially on facial images with significant intra class variations.

show abstract

Face authentication system using pseudo Zernike moments on wavelet subband

Cited by 8 publications

References 7 publications

A Local DCT-II Feature Extraction Approach for Personal Identification Based on Palmprint

A Local DCT-II Feature Extraction Approach for Personal Identification Based on Palmprint

Face recognition using effective and fast approach

Discriminative Discriminant Common Vector in face verification

Contact Info

Product

Resources

About