Deep Learning based Real-Time Face Detection and Gender Classification using OpenCV and Inception v3

Automatic object identification and recognition of the objects are done through CCTV cameras. In this approach, the entire footage is stored which leads to more data storage requirements. Apparently, the cost for data storage is more. This paper proposes the technique in which CCTV cameras record the data only when the motion is detected in the footage. Therefore, the proposed algorithm reduces the cost of the data storage device and will be implemented in home, office, garden, and cabin etc. to Figure out the unusual activity. Face and Gender is the most basic information on human beings. It is of great significance in the field of face recognition. However, due to factors such as lighting, poses and expressions, gender classification has the problem of low accuracy. In this paper, Haar cascades are used to detect the human face from the real time image and the detected face is cropped and fed to the Inception V3 which performs gender classification. The IMDB datasets are used in this research work for training and testing. In addition, real-time face detection and gender classification were also performed. From the results, the accuracy for predicting the gender classification is 97.4 %.