scholarly journals Image Perturbation-Based Deep Learning for Face Recognition Utilizing Discrete Cosine Transform

Electronics ◽  
2021 ◽  
Vol 11 (1) ◽  
pp. 25
Author(s):  
Jaehun Park ◽  
Kwangsu Kim
Keyword(s):  
Deep Learning ◽  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Large Scale ◽  
User Study ◽  
Emotion Classification ◽  
Cosine Transform ◽  
Privacy Leakage ◽  
Attribute Classification ◽  
Biometric Information

Face recognition, including emotion classification and face attribute classification, has seen tremendous progress during the last decade owing to the use of deep learning. Large-scale data collected from numerous users have been the driving force in this growth. However, face images containing the identities of the owner can potentially cause severe privacy leakage if linked to other sensitive biometric information. The novel discrete cosine transform (DCT) coefficient cutting method (DCC) proposed in this study combines DCT and pixelization to protect the privacy of the image. However, privacy is subjective, and it is not guaranteed that the transformed image will preserve privacy. To overcome this, a user study was conducted on whether DCC really preserves privacy. To this end, convolutional neural networks were trained for face recognition and face attribute classification tasks. Our survey and experiments demonstrate that a face recognition deep learning model can be trained with images that most people think preserve privacy at a manageable cost in classification accuracy.

scholarly journals Face recognition using fractional coefficients and discrete cosine transform tool

2021 ◽  
Vol 11 (1) ◽  
pp. 892
Author(s):  
Mourad Moussa ◽  
Maha Hmila ◽  
Ali Douik
Keyword(s):  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Recognition System ◽  
Video Frame ◽  
Support Vector ◽  
Expression Recognition ◽  
Discrimination Power ◽  
Cosine Transform ◽  
Discrimination Criterion ◽  
Biometric Information

Face recognition is a computer vision application based on biometric information for automatic person identification or verification from image sequence or a video frame. In this context DCT is the easy technique to determine significant parameters. Until now the main object is selection of the coefficients to obtain the best recognition. Many techniques rely on premasking windows to discard the high and low coefficients to enhance performance. However, the problem resides in the shape and size of premask. To improve discriminator ability in discrete cosine transform domain, we used fractional coefficients of the transformed images with discrete cosine transform to limit the coefficients area for a better performance system. Then from the selected bands, we use the discrimination power analysis to search for the coefficients having the highest power to discriminate different classes from each other. Feature selection algorithm is a key issue in all pattern recognition system, in fact this algorithm is utilized to define features vector among several ones, where these features are selected according a specified discrimination criterion. Many classifiers are used to evaluate our approach like, support vector machine and random forests. The proposed approach is validated with Yale and ORL Face databases. Experimental results prove the sufficiency of this method in face and facial expression recognition field.

PHOTOMETRIC NORMALIZATION FOR FACE RECOGNITION USING LOCAL DISCRETE COSINE TRANSFORM

2013 ◽  
Vol 27 (03) ◽  
pp. 1360005 ◽  
Author(s):  
HEYDI MENDEZ-VÁZQUEZ ◽  
JOSEF KITTLER ◽  
CHI HO CHAN ◽  
EDEL GARCÍA-REYES
Keyword(s):  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Total Error ◽  
Incident Light ◽  
Low Frequency ◽  
Recognition System ◽  
Classifier Fusion ◽  
Limiting Factors ◽  
Cosine Transform ◽  
Depth Analysis

Variations in illumination is one of major limiting factors of face recognition system performance. The effect of changes in the incident light on face images is analyzed, as well as its influence on the low frequency components of the image. Starting from this analysis, a new photometric normalization method for illumination invariant face recognition is presented. Low-frequency Discrete Cosine Transform coefficients in the logarithmic domain are used in a local way to reconstruct a slowly varying component of the face image which is caused by illumination. After smoothing, this component is subtracted from the original logarithmic image to compensate for illumination variations. Compared to other preprocessing algorithms, our method achieved a very good performance with a total error rate very similar to that produced by the best performing state-of-the-art algorithm. An in-depth analysis of the two preprocessing methods revealed notable differences in their behavior, which is exploited in a multiple classifier fusion framework to achieve further performance improvement. The superiority of the proposal is demonstrated in both face verification and identification experiments.

Face Recognition System using Discrete Cosine Transform combined with MLP and RBF Neural Networks

2012 ◽  
Vol 4 (4) ◽  
pp. 11-35 ◽  
Author(s):  
Fatma Zohra Chelali ◽  
Amar Djeradi
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Discrete Cosine Transform ◽  
Recognition Rate ◽  
Recognition System ◽  
Rbf Neural Networks ◽  
Cosine Transform ◽  
Linear Discriminant ◽  
Face Recognition System ◽  
Dct Coefficients

Proposed is an efficient face recognition algorithm using the discrete cosine transform DCT Technique for reducing dimensionality and image parameterization. These DCT coefficients are examined by a MLP (Multi-Layer Perceptron) and radial basis function RBF neural networks. Their purpose is to present a face recognition system that is a combination of discrete cosine transform (DCT) algorithm with a MLP and RBF neural networks. Neural networks have been widely applied in pattern recognition for the reason that neural-networks-based classifiers can incorporate both statistical and structural information and achieve better performance than the simple minimum distance classifiers. The authors demonstrate experimentally that when DCT coefficients are fed into a back propagation neural network for classification, a high recognition rate can be achieved by using a very small proportion of transform coefficients. Comparison with other statistical methods like Principal component Analysis (PCA) and Linear Discriminant Analysis (LDA) is presented. Their face recognition system is tested on the computer vision science research projects and the ORL database.

Sign in / Sign up

Export Citation Format

Share Document