论文信息 - Gender Classification using Facial Embeddings: A Novel Approach

Gender Classification using Facial Embeddings: A Novel Approach

Abstract Image Processing for Human recognition involves using bio-metric traits such as Face, Iris, Voice and other physical traits to uniquely identify human faces. With the increase in Image Data on the Internet, there is a huge demand for Artificial Intelli-gence(AI) algorithms that can perform classification tasks like Race and Gender Classification. The advent of Deep Learning Techniques like Convolutional Networks has led to a rapid ascent in accuracy in various image classification tasks. Through this paper, a novel method to predict Gender of a person by applying various Machine Learning Classification Techniques on Facial Em-beddings has been proposed. The facial embeddings are found by passing through a Pretrained Inception Network. The maximum accuracy obtained by the proposed work to classify gender is 97%.

[1] Reecha Sharma,et al. Age Invariant Face Recognition using K-PCA and K-NN on Indian Face Age Database (IFAD) , 2015 .

[2] Joachim M. Buhmann,et al. Distortion Invariant Object Recognition in the Dynamic Link Architecture , 1993, IEEE Trans. Computers.

[3] Alexander Binder,et al. Layer-Wise Relevance Propagation for Deep Neural Network Architectures , 2016 .

[4] Di Huang,et al. Local Binary Patterns and Its Application to Facial Image Analysis: A Survey , 2011, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[5] Roope Raisamo,et al. Evaluation of Gender Classification Methods with Automatically Detected and Aligned Faces , 2008, IEEE Transactions on Pattern Analysis and Machine Intelligence.