African Gender Classification Using Clothing Identification Via Deep Learning

Facial recognition systems have mostly been employed for gender classification in computer vision over the years. The development of advance tools and concepts in deep learning and computer vision, especially with developing convolutional neural networks t o construct maps of facial features or utilizing transfer learning of models pretrained on huge volume of data, has overtime, further enhanced the credibility and resultant reliability of using facial recognition techniques for many forms of attribute iden tification in computer vision. However, the use of facial recognition for attributes identification and classification are not without pitfalls as most facial recognition techniques require clear images and high - quality videos of clearly defined facial features to be effective [5] . In real life situations, facial images, especially when obtained under non ideal situations, are often distorted, blurred or concentrated on positions that are not appropriate for proper feature detection by facial recognition techniques. For example, co mmon f acial recognition techniques are often unable to detect facial features on images where the face is inside view, taken from distance, partially covered or even blurred. While new innovative techniques, like Google's Mediapipe facial recognition system are addressing some of these limitations, these are still valid problems today for most facial recognition techniques such as the OpenCV Facial Cascades.