An Efficient Method for Face Feature Extraction and Recognition based on Contourlet Transform and Principal Component Analysis using Neural Network

Chitaliya, Nehal; Trivedi, A.I.

doi:10.5120/1066-1260

Cited by 12 publications

(11 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Each individual has 20 face images, with distinct subject containing variation in illumination and facial expression [20]. Fig (11) shows example images of the Face94 database.…”

Section: Face94mentioning

confidence: 99%

“…These images are fed to the DFB, and as a result the directional information can be captured. The scheme can be repeated on the coarse image [20]. The PDFB decomposes the given image into directional sub-bands at multiple scales.…”

Section: Directional Filter Bank (Dfb)mentioning

confidence: 99%

“…The high frequency content like smooth contours and directional edges can be captured by using DFB [20]. The DFB is implemented by utilizing a k-level binary tree decomposition that results k 2 directional sub-bands with wedge shaped frequency partitions as illustrated in Fig (5).…”

Section: Directional Filter Bank (Dfb)mentioning

confidence: 99%

“…Fig-(13) shows the overall process of calculating the CT coefficients, and applying the training, then identifying the test images [20].…”

Section: Algorithm Descriptionmentioning

confidence: 99%

See 3 more Smart Citations

Face Identification based on Contourlet Transform and Multi-layer Perceptron Classifier

Hassoon¹,

AL-Azzawi²,

Tashan³

2016

IJCA

View full text Add to dashboard Cite

Useful properties of the Contourlet Transform (CT) are exploited in this paper to investigate more discriminant features to enhance the face identification performance. In this paper a face identification system is suggested based on CT, and Multi-Layer Perceptron (MLP) Classifier. The main reasons behind using the CT are: First, the CT supports progressive data compression/expansion, hence it is used for image compression. Second, since the features in human face are not just horizontal or vertical. CT is utilized for feature extraction because it is a genuine 2-D transform that can capture the edge information in all directions. After decomposing an image by CT, low and high frequency coefficients of CT are calculated in different scales and various angles. The frequency coefficients are utilized as an input feature vector for a neural network classifier. Simple feed forward MLP neural network is used to achieve the identification process. The network parameters are tuned to optimal values, in order to produce fair comparison between different types of feature vectors. To evaluate the algorithm performance five different databases are used. Some of them of high variability, which examines the algorithm robustness against variability. In addition, the proposed algorithm is evaluated using a generated database which composes two databases. Then the suggested method is compared to other classical feature-based methods such as, wavelet, and Principle Component Analysis (PCA). The results indicate that the CT-based method has better identification rate, and is faster than the Wavelet-based and the PCA-based methods. This is due to the high sparsity of the CT and its efficient capability of compression. An average identification rate of 93.94% is obtained for the CT-based method, 85.12% for the Wavelet and 79.96% for the PCA.

show abstract

“…Each individual has 20 face images, with distinct subject containing variation in illumination and facial expression [20]. Fig (11) shows example images of the Face94 database.…”

Section: Face94mentioning

confidence: 99%

Section: Directional Filter Bank (Dfb)mentioning

confidence: 99%

Section: Directional Filter Bank (Dfb)mentioning

confidence: 99%

“…Fig-(13) shows the overall process of calculating the CT coefficients, and applying the training, then identifying the test images [20].…”

Section: Algorithm Descriptionmentioning

confidence: 99%

See 2 more Smart Citations

Face Identification based on Contourlet Transform and Multi-layer Perceptron Classifier

Hassoon¹,

AL-Azzawi²,

Tashan³

2016

IJCA

View full text Add to dashboard Cite

show abstract

“…These feature projection vectors are used as inputs to train the neural network. [10] When a new image is considered for recognition, its feature projection vector is calculated from the Eigenfaces, and this image gets its new descriptors. These descriptors are fed to the neural network and the network is simulated with these descriptors, where the network outputs are compared.…”

Section: Feed Forward Neural Networkmentioning

confidence: 99%

Face Recognition Using Wavelet Neural Network

Dharani¹,

Vibhute²

2017

IJARCSSE

View full text Add to dashboard Cite

Automatic face recognition system is an important component of intelligent human computer interaction systems for biometric. It is an attractive biometric approach, to distinguish one person from another. To perform Automatic face recognition system, the hybrid approach Wavelets face detection and Neural Network based Face Recognition is used. The face recognition accuracy is can be increased using a combination of Wavelet, PCA-FLD and Neural Networks. Preprocessing, feature extraction and classification rules are three crucial issues for face recognition. For preprocessing and feature extraction steps, we apply a combination of wavelet transform and PCA-FLD. During the classification stage, the Neural Network is explored to achieve a robust decision in presence of wide facial variations.

show abstract

An adaptive e-learning environment centred on learner's emotional behaviour

Kanimozhi

Raj

2017

2017 International Conference on Algorithms, Methodology, Models and Applications in Emerging Technologies (ICAMMAET)

View full text Add to dashboard Cite

An Efficient Method for Face Feature Extraction and Recognition based on Contourlet Transform and Principal Component Analysis using Neural Network

Cited by 12 publications

References 16 publications

Face Identification based on Contourlet Transform and Multi-layer Perceptron Classifier

Face Identification based on Contourlet Transform and Multi-layer Perceptron Classifier

Face Recognition Using Wavelet Neural Network

An adaptive e-learning environment centred on learner's emotional behaviour

Contact Info

Product

Resources

About