Face detection using 2D-Discrete Cosine Transform and Back Propagation Neural Network

Tayyab, Moeen; Zafar, Muhammad Faisal

doi:10.1109/icet.2009.5353205

Cited by 7 publications

(4 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another paper deals with using SOM in facial recognition. A paper entitled "A MATLAB based Face Recognition System using Image Processing and Neural Networks" by Jawad Nagi, Syed Khaleel Ahmed, and Farrukh Nagi presents another technique for facial recognition, this time using two-dimensional discrete cosine transform (2D-DCT) to compress images [9]. Through this technique, redundant data is removed, and features based on skin color are extracted from faces.…”

Section: Literature Reviewmentioning

confidence: 99%

Face Recognition Using MATLAB

Africa¹,

Abello²,

Gacuya³

et al. 2019

IJATCSE

View full text Add to dashboard Cite

This project dives into the topic of facial recognition and facial detection in a digital communications system. Face recognition is a technology that is widely used today which brings various benefits to society. Facial recognition differs from facial detection in the aspect that facial detection only finds and detects the present face/s in an image whereas, in facial recognition, the computer finds the face/s present in a subject and is able to distinguish the face from a sample of different faces. This research focuses on the implementation of both a facial recognition system and a facial detection system in MATLAB. This research would use the different imaging toolboxes available in the program and would be judged on its ability to accurately detect and recognize a sample in a given database. Additionally, this system should be able to create and to read a database of different faces.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Face Recognition Using MATLAB

Africa¹,

Abello²,

Gacuya³

et al. 2019

IJATCSE

View full text Add to dashboard Cite

show abstract

“…Examples of hybrid approaches include the combination of PCA and radial basis functions (RBFs) or a neural network [77]. Transformation-based methods include the discrete cosine transform (DCT) [68], DCT and hidden Markov model (HMM), DCT and neural networks [75], Weber local binary image cosine transform (WLBI-CT) [33], and Fourier transform (FT). Khan et al [33] proposed the Weber local binary image cosine transform (WLBI-CT) technique, to extract and integrate the frequency components of images obtained using the Weber local descriptor and local binary descriptor.…”

Section: Developments In Face Recognition Approachesmentioning

confidence: 99%

Feature redundancy approach to efficient face recognition in still images

2019

View full text Add to dashboard Cite

This paper proposes the use of redundant features for efficient recognition of faces in still images using a novel system framework that offers a detailed systematic workflow for solving the facial recognition problem. It accepts still frontal face images, processes and represents salient facial features (face, eyes, nose, and mouth) using facial detection and extraction techniques. The extracted features are then modeled by an ensemble of self-organizing maps. The ensemble outputs are later reassembled into a single dataset consisting of a normalized image Euclidean distance matrix to enhance the search space for optimal convergence and classification. The feasibility of the framework is tested using an experiment facial database captured during the study, and three benchmark facial expression databases, namely the Extended Cohn-Kanade (CK+) database, the Japanese Female Facial Expressions database, and the MMI Facial Expression database. The results suggest that feature redundancy is indeed useful for efficient facial recognition, as the support vector machine classification recorded high accuracies across the various databases, with the normalized image Euclidean distance dataset producing the highest performance, when compared with the localized principal component analysis and unnormalized image Euclidean distance datasets. Furthermore, overall classification accuracy of above 99% was achieved for the experiment (nonexpressive still face) database, compared with the benchmark facial expression databases, which yielded slightly lower results. A future direction of this work is further improvement of the framework to robustly handle severe facial variations.

show abstract

“…The performance indices employed in evaluating the developed algorithm are the correct detection rate (CDR), miss rate (MR) and false detection rate (FDR). In estimating the performance indices, the mathematical expression used are as follows; % 100   TF TP CDR (13) % 100   TF TN MR (14) % 100   TF FP FPR (15) where TF is the total number of faces. The result of the measured detection accuracy for the developed algorithm is presented in Table 1.…”

Section: Developed Algorithm Detection Accuracy Evaluationmentioning

confidence: 99%

“…Eyes and mouth were then extracted using principal component analysis on the detected skin like region. Likewise, in [14], segmented skin like region with the Hue saturation value color space were employed. Feature vector of the segmented skin like region was calculated with two dimensional discrete cosine transform.…”

Section: Related Workmentioning

confidence: 99%

Development of a Face Detection Algorithm Based on Skin Segmentation and Facial Feature Extraction

Popoola¹,

Akinola²

2017

International Journal of Engineering Technologies IJET

View full text Add to dashboard Cite

This paper presents a face detection algorithm capable of detecting face(s) without prior training as a face classifier. The technique employed in developing the algorithm is based on skin segmentation and facial feature extraction of the two eyes and mouth. Skin segmentation was done in the red, green, blue color space. White balance correction was employed to correct the change in image temperature that occurs due to change in lighting conditions at the point of acquiring image. Morphological operations and bounding box were employed to search and extract face region from the segmented skin region. Facial feature, eyes and mouth, were extracted for final verification of the sensed face using the Laplacian of Gaussian filter and the isosceles triangle matching rules. The extracted features were used to develop the face detection algorithm. The developed algorithm was evaluated using random images taken under different lighting conditions. Furthermore, the efficiency of the developed face detection algorithm was evaluated using a standard face detection image database. The result obtained shows that the developed face detection algorithm performed satisfactorily well with 81.37% detection accuracy. Furthermore, the results obtained from the performance evaluation of the developed face detection for this study has shown it clearly that accuracy detection of dissimilar faces in images with complex background is possible and attainable.

show abstract

Face detection using 2D-Discrete Cosine Transform and Back Propagation Neural Network

Cited by 7 publications

References 5 publications

Face Recognition Using MATLAB

Face Recognition Using MATLAB

Feature redundancy approach to efficient face recognition in still images

Development of a Face Detection Algorithm Based on Skin Segmentation and Facial Feature Extraction

Contact Info

Product

Resources

About