A Gender Recognition System Using Facial Images with High Dimensional Data

Abstract

Gender recognition has been seen as an interesting research area that plays important roles in many fields of study. Studies from MIT and Microsoft clearly showed that the female gender was poorly recognized especially among dark-skinned nationals. The focus of this paper is to present a technique that categorise gender among dark-skinned people. The classification was done using SVM on sets of images gathered locally and publicly. Analysis includes; face detection using Viola-Jones algorithm, extraction of Histogram of Oriented Gradient and Rotation Invariant LBP (RILBP) features and trained with SVM classifier. PCA was performed on both the HOG and RILBP descriptors to extract high dimensional features. Various success rates were recorded, however, PCA on RILBP performed best with an accuracy of 99.6% and 99.8% respectively on the public and local datasets. This system will be of immense benefit in application areas like social interaction and targeted advertisement.

Perspective on Dark-Skinned Emotion Recognition Using Deep-Learned and Handcrafted Feature Techniques

“…These features are used to train different classifiers such as neural networks, Nearest Neighbor, and SVM [23]. Further details are as reported in [24].…”

“…Irhebhude and Kolawole [24] focused on presenting a technique that categorized gender among dark-skinned people. The classification was done using SVM on sets of images gathered locally and publicly.…”

“…The image part of the face was detected automatically, and the detected face position was cropped accordingly [50]. The Viola-Jones algorithm, as described in Irhebhude, Kolawole [24], was used for face detection. The feature works with images in squares, with multiple pixels in each box.…”

“…To enhance the description ability, the RILBP descriptor was used; this encodes the local facial features in a multi-resolution spatial histogram and combines the distribution of local intensity with the spatial information [23]. Studies have shown good results for gender recognition and age estimation Irhebhude, Kolawole [24], using the RILBP descriptor. Following the steps as reported by the authors, the technique extracted texture features with a dimension length of 36 for further classification.…”

Gender recognition based fingerprints using dynamic horizontal voting ensemble deep learning

“…Some of these traits have been used in gender based classification researches. In ealier study, Machine learning method was used in identifying gender through facial images [6], [7]. Fingerprints, however, have been acclaimed to be the most known and used biometric solutions to authenticate people in biometric systems [8].…”