Gender Classification Algorithms Research Articles

A novel approach for bias mitigation of gender classification algorithms using consistency regularization

Published research has confirmed the bias of automated face-based gender classification algorithms across gender-racial groups. Specifically, unequal accuracy rates were obtained for women and dark-skinned people for face-based automated gender classification algorithms. To mitigate the bias of gender classification and other facial-analysis-based algorithms in general, the vision community has proposed several techniques. However, most of the existing bias mitigation techniques suffer from a lack of generalizability, need a demographically-annotated training set, are application-specific, and often offer a trade-off between fairness and classification accuracy. This means that fairness is often obtained at the cost of a reduction in the classification accuracy of the best-performing demographic sub-group. In this paper, we propose a novel bias mitigation technique that leverages the power of semantic preserving augmentations at the image- and feature-level in a self-consistency setting for the downstream gender classification task. Thorough experimental validation on gender-annotated facial image datasets confirms the efficacy of our bias mitigation technique in improving overall gender classification accuracy as well as reducing bias across all gender-racial groups over state-of-the-art bias mitigation techniques. Specifically, our proposed technique obtained a reduction in the bias by an average of 30% over existing bias mitigation techniques as well as an improvement in the overall classification accuracy of about 5% over the baseline gender classifier. Therefore, resulting in state-of-the-art generalization performance in the intra- and cross-dataset evaluations. Additionally, our proposed technique operates in the absence of demographic labels and is application agnostic, compared to most of the existing bias mitigation techniques.

AI Based Identification of Gender from Images Based on Facial Features using CNN and OPENCV

The main objective of this paper is to classify the gender based on different facial features such as eyes, nose, mouth, overall features such as face contour, head shape, hair line etc. The gender classification algorithm uses machine learning technique (supervised learning). In this case the algorithm is trained on a set of male and female faces and then used to classify new data. In this paper, face detection and gender classification methods are combined. The face detection acts as a pre- processing operation to the gender classifier that determines the gender. There are multiple methods in which facial recognition systems work, but in general, they work by comparing selected facial features from a given image with faces within a database. It is also described as a Biometric Artificial Intelligence based application that can uniquely identify a person by analyzing patterns based on the person's facial textures and shape. Automated gender recognition plays an important role in many application areas such as human computer interaction, biometric, surveillance, demographic statistics etc. Existing systems has a disadvantage in accuracy. Though there are many algorithms in Present system are being developed and implemented to achieve accuracy in identifying gender the results arestill unsatisfactory. Proposed system has an advantage of accuracy. The accuracy achieved in this system is impressive compared to the existing system. CNN algorithm gives better accuracy compared to other algorithms

An overview for assessing a number of systems for estimating age and gender of speakers

The determination of the age and gender of the speaker of the speech signal is an interesting topic in the interaction between human-machine. Speech signal has a variety of applications ranging from speech analyses to allocate human-machine interactions. This paper aims to conduct a comparative study of age and gender classification algorithms applied to the speech signal. Comparison of experimental results of different sources of voices for speakers of different languages and methods of miscellaneous classification such as Bayes classifier, neural network, support vector machines, K-nearest neighbor, gaussien mixture model and hybrid method based on weighted analysis of a directed non-negative matrix and a neural network with a general recession as well as some deep learning methods, is done in order to show different results to classify the age and gender of the speaker when processing the speech signal. The study showed that methods and algorithms of deep learning have excelled in providing accuracy ratios higher than other methods, and it shows that the hybridization of two or more classification methods increases the accuracy level of the results.

Identifying Gender from Images of Face

The main objective of this project is to classify the gender based on different facial features such as eyes, nose, mouth, overall features such as face contour, head shape, hair line etc. The gender classification algorithm uses machine learning technique (supervised learning). In this case the algorithm is trained on a set of male and female faces and then used to classify new data. In this project, face detection and gender classification methods are combined. The face detection acts as a pre-processing operation to the gender classifier that determines the gender.There are multiple methods in which facial recognition systems work, but in general, they work by comparing selected facial features from a given image with faces within a database. It is also described as a Biometric Artificial Intelligence based application that can uniquely identify a person by analyzing patterns based on the person's facial textures and shape.Automated gender recognition plays an important role in many application areas such as human computer interaction,biometric, surveillance, demographic statistics etc.

An Investigation into the Relationship between Curse of Dimensionality and Dunning-Kruger Effect

This study addresses a novel perspective for analyzing the source of confidence in human behavior. The concept of confidence was examined via the relationship between two phenomena in the area of machine learning and psychology, namely the Dunning-Kruger effect and the curse of dimensionality. A relationship was established between these two phenomena which were investigated in the light of neuroscience. This study claims that confidence is highly related with the total time it takes to reach specific information and this relationship is inversely proportional. Image gender classification algorithm was used to analyze this relationship for this study and the curves which were obtained as a result of this analysis was compared with the curve of Dunning-Kruger effect and curse of dimensionality. This relationship has been explained by the knowledge of human's problem-solving ability and mathematical models of memory.

Soft-biometrics encoding conditional GAN for synthesis of NIR periocular images

Soft-Biometric information, such as gender, has great potential for applications in security, forensics and marketing. Unfortunately, there are few gender-labelled databases available which make state of the art techniques, such as deep learning, difficult to use. An alternative source of data to train these algorithms are synthetic images. Methods based on Generative Adversarial Network are widely used for generating synthetic images. However, low features, such as gender, are not preserved in the images generated by these methods. In this paper, a novel GAN-based algorithm that preserves gender information while generating synthetic images is presented. It uses a latent vector that encodes gender information within the conditional GAN algorithm. Resulting synthetic images were tested using a gender classifier algorithm (CNN). Experiments demonstrate that the proposed method can be a useful tool for the synthesis of gender-labelled images to be used in training Deep Learning gender-classification algorithms. As an additional contribution a novel person-disjoint gender labelled dataset is presented (UNAB-Gender).

Biometric Authentication for Gender Classification Techniques: A Review

One of the challenging biometric authentication applications is gender identification and age classification, which captures gait from far distance and analyze physical information of the subject such as gender, race and emotional state of the subject. It is found that most of the gender identification techniques have focused only with frontal pose of different human subject, image size and type of database used in the process. The study also classifies different feature extraction process such as, Principal Component Analysis (PCA) and Local Directional Pattern (LDP) that are used to extract the authentication features of a person. This paper aims to analyze different gender classification techniques that help in evaluating strength and weakness of existing gender identification algorithm. Therefore, it helps in developing a novel gender classification algorithm with less computation cost and more accuracy. In this paper, an overview and classification of different gender identification techniques are first presented and it is compared with other existing human identification system by means of their performance.

Gender Classification of Low-Resolution Facial Image Based on Pixel Classifier Boosting

© 2016 Kyu-Dae Ban et al. 347 http://dx.doi.org/10.4218/etrij.16.0114.0135 In face examinations, gender classification (GC) is one of several fundamental tasks. Recent literature on GC primarily utilizes datasets containing high-resolution images of faces captured in uncontrolled real-world settings. In contrast, there have been few efforts that focus on utilizing low-resolution images of faces in GC. We propose a GC method based on a pixel classifier boosting with modified census transform features. Experiments are conducted using large datasets, such as Labeled Faces in the Wild and The Images of Groups, and standard protocols of GC communities. Experimental results show that, despite using low-resolution facial images that have a 15-pixel inter-ocular distance, the proposed method records a higher classification rate compared to current state-of-the-art GC algorithms.