Gender classification via lips: Static and dynamic features

This paper is about gender classification using face image and voice of a speaker. The basic aim of the paper is to predict the gender of speaker through voice sample using Auto-correlation method and predict the gender of speaker through their face image using fisher face algorithm and integrated the obtained to increase the accuracy of gender classifier. The algorithm has been applied with the help of MATLAB programming. A collected database of voice samples and image samples of male and female students has been concerned. The classification algorithm is applied on the database and accuracy of gender classifier is determined.

Advances in distributed computing and artificial intelligence journal, 2023

Gender classification is an important biometric task. It has been widely studied in the literature. Face modality is the most studied aspect of humangender classification. Moreover, the task has also been investigated in terms of different face components such as irises, ears, and the periocular region. In this paper, we aim to investigate gender classification based on the oral region. In the proposed approach, we adopt a convolutional neural network. For experimentation, we extracted the region of interest using the RetinaFace algorithm from the FFHQ faces dataset. We achieved acceptable results, surpassing those that use the mouth as a modality or facial sub-region in geometric approaches. The obtained results also proclaim the importance of the oral region as a facial part lost in the Covid-19 context when people wear facial mask. We suppose that the adaptation of existing facial data analysis solutions from the whole face is indispensable to keep-up their robustness.

This paper describes a new simple, but effective, approach to speaker verification using video sequences of lip movements. We use Motion History Images (MHI) to provide a biometric template of a spoken word for each speaker. Class-dependent correlation filters are then created by a weighted optimization of training MHI samples. Feature extraction is performed by correlating a test MHI against each correlation filter. A Bayesian classifier is deployed for classification. We carry out an extensive performance evaluation of our approach with respect to the number of training samples and different words. Results clearly show the efficacy of our method.

The Visual Computer, 2013

This research paper introduces three robust approaches for features extraction for gender classification. The first approach is based on using Discrete Cosine Transform (DCT) and consists of two different methods for calculating features values. The second approach is based on the extraction of texture features using the gray-level cooccurrence matrix (GLCM). The third approach is based on 2D-wavelet transform. The extracted features vectors are classified using SVM. For precise evaluation, the databases used for gender evaluation are based on images from the AT@T, Faces94, UMIST, and color FERET databases. Kfold cross validation is used in training the SVM. The accuracies of gender classification when using one of the two proposed DCT methods for features extraction are 98.6 %, 99.97 %, 99.90 %, and 93.3 % with 2-fold cross validation, and 98.93 %, 100 %, 99.9 %, and 92.18 % with 5-fold cross validation. The accuracies of GLCM texture features approach for facial gender classification are 98.8 %, 99.6 %, 100 %, and 93.11 %, for AT@T, Faces94, UMIST, and FERET, databases. The accuracies for all databases when using 2D-WT are ranging between 96.18 % and 99.6 % except FERET and its accuracy is 92 %.

Symmetry

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).

Abstract Computer vision-based gender detection from facial images is a challenging and important task for computer vision-based researchers. The automatic gender detection from face images has potential applications in visual surveillance and human-computer interaction systems (HCI). Human faces provide important visual information for gender perception. This research presents a novel approach for gender detection from facial images. The system can automatically detect face from input images and the detected facial area is taken as region of interest (ROI).

International Journal of Scientific Research in Computer Science, Engineering and Information Technology, 2021

Increasing population and changing lifestyle become a more confusing task for detecting gender from facial images. To solve such a fragile problem several handy approaches are readily available in computer vision. Although, very few of these approaches achieve good accuracy. The features like lightning, illumination, noise, ethnicity, and various facial expression hamper the correctness of the images. Keeping these things in mind, we propose our research work on the identification of gender from facial features. The major component of face recognition is to develop a machine learning model which will classify the images this can be done by haar-cascade-classifier. To train the model with images more accurately we would perform few image processing concepts for the data to perform data analysis and preprocessing for structuring our data. This can be done by OpenCV. After that, we have used PCA ( Principle Comprehend Analysis ) to compute Eigenvalues and for the optimal components, we will get the class name from the knowledge base and confidence score from the SVM-based face recognition model. In our project work, we get good accuracy.

2018

Gender classification is arguably one of the more important visual tasks for an extremely social animal like us humans— many social interactions critically depend on the correct gender perception of the parties involved. Many research studies have been conducted on face recognition to improve its accuracy since the first research. But face recognition still far from achieving accuracy that on par with human facial features and gender classification. However, all of them have still disadvantage such as not complete reflection about face structure or face texture. In general, gender classification in supervised learning setting requires extraction of features from face images, training classifiers using those features (eyes, nose and mouth) and finally performing classification of new faces. This work uses appearance-based approach with dimensionality reduction techniques for feature extraction. The features extracted from the training set are used for training KNN/SVM classifier. And...

2021

The real-time gender classification based on facial images is proposed by an approach using a convolutional neural network (CNN). In contrast with the other CNN solutions that were implied over the pattern recognitions the CNN architecture which has been put forward displays a much reduction in design complications. The count of processing layers in the CNN is decreased by only four due to which it leads to meld the convolutional and sub sampling layers. However in conventional CNNs, we replace the convolution operation with cross-correlation, so it reduces the computational load. The perspective used for either evaluating or distinguishing these characteristics from the images of the facial features have been relied on variation from the element of facial measurements or ”modified” face descriptors. The results are corresponding to a classification which is better at its performance and also while verifying that the proposed CNN is an effective real-time solution for gender recogni...

2009