Gender recognition with Gabor filters

Ignat, Anca; Coman, Mihaela Denisa

doi:10.1109/ehb.2015.7391374

Cited by 12 publications

(10 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In Ignat and Coman (2015) Gabor filters were used as feature extractor and support vector machine (SVM) and nearest neighbour as classifiers. Gender recognition based on colour information was introduced in Lin and Zhao (2011).…”

Section: Literature Reviewmentioning

confidence: 99%

“…ANN: (Golomb et al, 1990), (Mirza et al, 2013), (Zhou & Li, 2016), (Jaswante et al, 2013). SVM: (Ignat & Coman, 2015), (Jain et al, 2005), (Deniz et al, 2011), (Shan, 2011)., (Chang et al, 2011), (Lee et al, 2013).…”

Section: Classifiersmentioning

confidence: 99%

“…Gabor: (Ignat & Coman, 2015). LBP: (Vergara et al, 2016), (Lian & Lu, 2007), (Sun et al, 2006), (Shan, 2011)., (Lee et al, 2013).…”

Section: Featuresmentioning

confidence: 99%

See 2 more Smart Citations

Improving the SVM gender classification accuracy using clustering and incremental learning

Dagher

Azar

2019

Expert Systems

View full text Add to dashboard Cite

Gender recognition has been playing a very important role in various applications such as human–computer interaction, surveillance, and security. Nonlinear support vector machines (SVMs) were investigated for the identification of gender using the Face Recognition Technology (FERET) image face database. It was shown that SVM classifiers outperform the traditional pattern classifiers (linear, quadratic, Fisher linear discriminant, and nearest neighbour). In this context, this paper aims to improve the SVM classification accuracy in the gender classification system and propose new models for a better performance. We have evaluated different SVM learning algorithms; the SVM‐radial basis function with a 5% outlier fraction outperformed other SVM classifiers. We have examined the effectiveness of different feature selection methods. AdaBoost performs better than the other feature selection methods in selecting the most discriminating features. We have proposed two classification methods that focus on training subsets of images among the training images. Method 1 combines the outcome of different classifiers based on different image subsets, whereas method 2 is based on clustering the training data and building a classifier for each cluster. Experimental results showed that both methods have increased the classification accuracy.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Section: Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

Improving the SVM gender classification accuracy using clustering and incremental learning

Dagher

Azar

2019

Expert Systems

View full text Add to dashboard Cite

show abstract

“…A. Ignat and M. Coman [8] performed feature extraction using Gabor Filters to get the information significant for gender with various orientation angles. They also tested state-of-the art classifiers on the AR and FERET face databases.…”

Section: Table-i: Performance Analysis Of Pca and 2dpca With Four Condimentioning

confidence: 99%

Gender Classification from Facial Images

Ahmed,

Choudhury

2019

IJEAT

View full text Add to dashboard Cite

Gender is one striking feature that human can deduce effortlessly when looking at a face. Here, we try to classify the gender (male or female) based on the face images. The first part of this paper presents a review of different methods/approaches used for gender recognition. We present a comparative analysis for gender recognition using PCA, 2dPCA and its variants. Finally, we develop an iterative model using 2dPCA which updates itself when new samples are encountered. This model is expected to be fruitful in real-life situation as it can learn when it comes across new test samples. We consider CFD, CUHK, ORL and Yale facial data-sets for our experiments.

show abstract

“…Another comprehensive technique on Multiple attributes (MA) has been conducted by Liu, Xu and Chiu [30]. The common adopted methods from gender recognition system that only focus on the face image to make gender identification was include using LBP and PCA for feature extraction and dimension reduction, Euclidean and Manhattan classifiers are used [31], and using Gabor Filters to extract features, Support Vector Machines, k-NN classifiers were tested [32], and using Discrete Cosine Transform (DCT) to extract features, K-nearest neighbor classifier (KNN) classifiers are used [33].…”

mentioning

confidence: 99%

Convolutional Neural Network Model in Machine Learning Methods and Computer Vision for Image Recognition: A Review

2018

J. Appl. Sci. Res.

View full text Add to dashboard Cite

Nowadays, Convolutional Neural Networks (CNNs) have shown that much successful in various machine learning and computer vision problems [1], [2]. Moreover, Convolutional Neural Networks (CNNs) are used in variety of areas in recognition and robotic field. There are a number of reasons that convolutional neural networks (CNNs) are becoming important. In the meantime convolutional neural networks (CNNs) have been applied with great success to the image recognition of objects in the air from the past few years [3]. From the sides of validity it is more naturally and simply in term of capturing an image. CNNs assumes the nature of the image, such as static images and where pixel dependencies are. Thus, compared to standard feed-forward neural networks with similarly-sized layers, CNNs have much fewer connections and parameters and that will make they are easier to train, while by theoretically the best achievement and may be just a little worse [4]. In addition, the capacity of CNNs can be controlled by varying their depth and breadth due to their architecture performance. Consequently, the typical architecture of CNNs is a multilayer stack of simple modules such as convolutional layer, pooling layer and fully-connected layer. Starting with the raw input, each module transforms the representation at one level into a higher and more abstract level [5]. Meanwhile, for recognition tasks, higher ranking of dataset representations an increase aspects of the input which are important for discrimination and limit unrelated of variations. From that, the latest technique of image recognition is introduce. Only a year later, the deep learning technique based on convolutional neural network has achieved great performance improvement in large-scale image classification tasks and set off the upsurge of deep learning besides it is a new hotspot in the domain of pattern recognition [6]. It allows a model that consists of multiple processing layers to study data representation with various levels of abstraction. Furthermore, in deep learning techniques, besides data formation, transfer learning is useful when someone wants to train on their own dataset for various reasons, for example, the dataset may not be enough to train the full neural net and cause problems in transfer learning [7]. Specifically, transfer learning may be used to take a pre-trained Deep Neural Networks, replacing the fully-connected layers (and potentially the last convolutional layer) and training those layers on the related dataset. Nevertheless, it has been observed that deep neural networks (DNNs) easily suffer from over fitting with small samples. In this review, the technique of machine learning is important to ensure the quality and efficiency of image in terms of capturing, verification and clustering that want to train more effectiveness especially in image recognition by using the accurate learning machines method The objective of this paper is to study the various machine learning required to apply in the CNNs mode depending on the data and occasional...

show abstract

Gender recognition with Gabor filters

Cited by 12 publications

References 16 publications

Improving the SVM gender classification accuracy using clustering and incremental learning

Improving the SVM gender classification accuracy using clustering and incremental learning

Gender Classification from Facial Images

Convolutional Neural Network Model in Machine Learning Methods and Computer Vision for Image Recognition: A Review

Contact Info

Product

Resources

About