Human Identification Based on Shallow Learning Using Facial Features

摘要

Today, identity recognition systems have achieved high accuracy and widely used in specific application areas such as recognition system based on retina imaging in immigration inspection, civil security and citizen management. Identity recognition is a very important task in intelligent surveillance systems. In these systems, human is required to be submissive for data acquisition to identify themselves. However, the automated monitoring systems are required to be active for information retrieval and human is passively monitored in this situation. In this kind of approach, human recognition is still a challenging task for the overall system performance. This study proposes a solution for human identification based on the human face recognition in images extracted from conventional cameras at a low resolution and quality. Our proposed approach for human identification is based on histogram of oriented gradients (HOG) feature descriptor and Support vector machine (SVM) classifier using a similarity matric estimation. The proposed method was evaluated on some standard databases which are available online and on our own collected dataset.