scholarly journals Gender Classification using Fisherface and Support Vector Machine on Face Image

2019 ◽  
Vol 1 (1) ◽  
pp. 32-40
Author(s):  
Muhammad Noor Fatkhannudin ◽  
Adhi Prahara

Computer vision technology has been widely used in many applications and devices that involves biometric recognition. One of them is gender classification which has notable challenges when dealing with unique facial characteristics of human races. Not to mention the challenges from various poses of face and the lighting conditions. To perform gender classification, we resize and convert the face image into grayscale then extract its features using Fisherface. The features are reduced into 100 components using Principal Component Analysis (PCA) then classified into male and female category using linear Support Vector Machine (SVM). The test that conducted on 1014 face images from various human races resulted in 86% of accuracy using standard k-NN classifier while our proposed method shows better result with 88% of accuracy.

2012 ◽  
Vol 235 ◽  
pp. 74-78 ◽  
Author(s):  
Jia Jun Zhang ◽  
Li Juan Liang

The background noise influences the face image recognition greatly. It is crucial to remove the noise signals prior to the face image recognition processing. For this purpose, the wavelet de-noising technology has combined with the kernel principal component analysis (KPCA) to identify face images in this paper. The wavelet de-noising technology was firstly used to remove the noise signals. Then the KPCA was employed to extract useful principal components for the face image recognition. By doing so, the dimensionality of the feature space can be reduced effectively and hence the performance of the face image recognition can be enhanced. Lastly, a support vector machine (SVM) classifier was used to recognize the face images. Experimental tests have been conducted to validate and evaluate the proposed method for the face image recognition. The analysis results have showed high performance of the newly proposed method for face image identification.


2019 ◽  
Vol 3 (2) ◽  
pp. 80-84 ◽  
Author(s):  
Mustafa H. Mohammed Alhabib ◽  
Mustafa Zuhaer Nayef Al-Dabagh ◽  
Firas H. AL-Mukhtar ◽  
Hussein Ibrahim Hussein

Facial analysis has evolved to be a process of considerable importance due to its consequence on the safety and security, either individually or generally on the society level, especially in personal identification. The paper in hand applies facial identification on a facial image dataset by examining partial facial images before allocating a set of distinctive characteristics to them. Extracting the desired features from the input image is achieved by means of wavelet transform. Principal component analysis is used for feature selection, which specifies several aspects in the input image; these features are fed to two stages of classification using a support vector machine and K-nearest neighborhood to classify the face. The images used to test the strength of the suggested method are taken from the well-known (Yale) database. Test results showed the eligibility of the system when it comes to identify images and assign the correct face and name.


2021 ◽  
Vol 2021 ◽  
pp. 1-8
Author(s):  
Louis Asiedu ◽  
Bernard O. Essah ◽  
Samuel Iddi ◽  
K. Doku-Amponsah ◽  
Felix O. Mettle

The face is the second most important biometric part of the human body, next to the finger print. Recognition of face image with partial occlusion (half image) is an intractable exercise as occlusions affect the performance of the recognition module. To this end, occluded images are sometimes reconstructed or completed with some imputation mechanism before recognition. This study assessed the performance of the principal component analysis and singular value decomposition algorithm using discrete wavelet transform (DWT-PCA/SVD) as preprocessing mechanism on the reconstructed face image database. The reconstruction of the half face images was done leveraging on the property of bilateral symmetry of frontal faces. Numerical assessment of the performance of the adopted recognition algorithm gave average recognition rates of 95% and 75% when left and right reconstructed face images were used for recognition, respectively. It was evident from the statistical assessment that the DWT-PCA/SVD algorithm gives relatively lower average recognition distance for the left reconstructed face images. DWT-PCA/SVD is therefore recommended as a suitable algorithm for recognizing face images under partial occlusion (half face images). The algorithm performs relatively better on left reconstructed face images.


2019 ◽  
Vol 892 ◽  
pp. 200-209
Author(s):  
Rayner Pailus ◽  
Rayner Alfred

Adaboost Viola-Jones method is indeed a profound discovery in detecting face images mainly because it is fast, light and one of the easiest methods of detecting face images among other techniques of face detection. Viola Jones uses Haar wavelet filter to detect face images and it produces almost 80%accuracy of face detection. This paper discusses proposed methodology and algorithms that involved larger library of filters used to create more discrimination features among the images by processing the proposed 15 Haar rectangular features (an extension from 4 Haar wavelet filters of Viola Jones) and used them in multiple adaptive ensemble process of detecting face image. After facial detection, the process continues with normalization processes by applying feature extraction such as PCA combined with LDA or LPP to extract our week learners’ wavelet for more classification features. Upon the process of feature extraction proposed feature selection to index these extracted data. These extracted vectors are used for training and creating MADBoost (Multiple Adaptive Diversified Boost)(an improvement of Adaboost, which uses multiple feature extraction methods combined with multiple classifiers) is able to capture, recognize and distinguish face image (s) faster. MADBoost applies the ensemble approach with better weights for classification to produce better face recognition results. Three experiments have been conducted to investigate the performance of the proposed MADBoost with three other classifiers, Neural Network (NN), Support Vector Machines (SVM) and Adaboost classifiers using Principal Component Analysis (PCA) as the feature extraction method. These experiments were tested against obstacles of POIES (Pose, Obstruction, Illumination, Expression, Sizes). Based on the results obtained, Madboost is found to be able to improve the recognition performance in matching failures, incorrect matching, matching success percentages and acceptable time taken to perform the classification task.


2021 ◽  
pp. 1-15
Author(s):  
Ashutosh Dhamija ◽  
R. B. Dubey

Face recognition is one of the most challenging and demanding field, since aging affects the shape and structure of the face. Age invariant face recognition is a relatively new area in face recognition studies, which in real-world implementations recently gained considerable interest due to its huge potential and relevance. The Age invariant face recognition, however, is still evolving and evolving, providing substantial potential for further study and progress inaccuracy. Major issues with the age invariant face recognition involve major variations in appearance, texture, and facial features and discrepancies in position and illumination. These problems restrict the age invariant face recognition systems developed and intensify identity recognition tasks. To address this problem, a new technique Quadratic Support Vector Machine- Principal Component Analysis (QSVM-PCA) is introduced. Experimental results suggest that our QSVM-PCA achieved better results especially when the age range is larger than other existing techniques of face-aging dataset of FGNET. The maximum accuracy achieved by demonstrated methodology is 98.87%.


Author(s):  
Ajit Singh ◽  
Chander Kant

Interest in facial recognition hypotheses and algorithms has grown steadily over the last few decades. Video monitoring, criminal identification, building access control, and unmanned and autonomous vehicles are only a few examples of concrete applications that are becoming increasingly attractive to industry. Various techniques are being developed, including local, holistic, and hybrid approaches, which use only a few face image characteristics or the entire facial features to provide a face image description. Many methods have good results, if there are sufficiently representative training samples per person, in the face recognition system. Facial part finding and extraction show the utmost vital role in face and age recognition. In this research work a new algorithm is proposed for Face and Age Recognition (FAR) by using Discrete Wavelet Transform (DWT), Radial Basis Function Support Vector Machine (RBF-SVM) classifier, and Rotational Local Binary Pattern (RLBP). RLBP is utilized for the selection and extraction of features from the face image. In this algorithm, extract the face component like Nose, Mouth, Left and Right eye. In the preprocessing stage median filter is used to remove noises from the face image. By using this, there is an improvement in the feature extraction procedure. In pattern recognition, a basic errand is finding a picture from the picture parts. For the implementation of results FG-NET ((Face and Gesture Recognition Network) and AT&T datasets are used. The detection rate of face recognition has reached up to 92–98% and the detection rate for age recognition is 87%. The proposed algorithm is compared with SVM shows better over previous algorithms and also estimate the value of accuracy.


Symmetry ◽  
2019 ◽  
Vol 11 (6) ◽  
pp. 770 ◽  
Author(s):  
Khalil Khan ◽  
Muhammad Attique ◽  
Ikram Syed ◽  
Asma Gul

Automatic gender classification is challenging due to large variations of face images, particularly in the un-constrained scenarios. In this paper, we propose a framework which first segments a face image into face parts, and then performs automatic gender classification. We trained a Conditional Random Fields (CRFs) based segmentation model through manually labeled face images. The CRFs based model is used to segment a face image into six different classes—mouth, hair, eyes, nose, skin, and back. The probabilistic classification strategy (PCS) is used, and probability maps are created for all six classes. We use the probability maps as gender descriptors and trained a Random Decision Forest (RDF) classifier, which classifies the face images as either male or female. The performance of the proposed framework is assessed on four publicly available datasets, namely Adience, LFW, FERET, and FEI, with results outperforming state-of-the-art (SOA).


2020 ◽  
Author(s):  
Damodara Krishna Kishore Galla ◽  
BabuReddy Mukamalla ◽  
Prakasha Reddy

Abstract Image processing is a field in which biometric traits such as Face, voice, lip movements, hand geometry, odour, gait, iris, retina, fingerprint etc., are essential for recognition. The face is the most critical biometric trait for recognition because the face is an easily approachable biometric trait. There is no need for attention from a human being for face recognition. Human face classification is a challenging task for a machine. In this project, minimum distance classifier used with LASSO based gender classification. Database of 100 images (50 male and 50 female face images which considered from 4 different databases) used for face recognition and classification. Original face image database used for the gender classification. This approach of dual classfication ((1) Recognizing or classfying human faces from various objects and (2) Classifying gender through face recognition) is made possible with the help of combining modified SIFT feature in combination with ridge regression (RR), elastic net (EN) and lasso regression with GSVM (LRGS) based classificatioins. The final classfication results with accuracy are as follows for RR- 89.6%, EN- 93.5%, LR-93.2% and propsed approach(LRGS) with 98.4% accurate detection rate with rediction names.


Sign in / Sign up

Export Citation Format

Share Document