Review of DL-Based Generation Techniques of Augmented Images using Portraits Specification

摘要

Artificial Intelligence (AI) reached various domains in our daily problems, among them is aiding law enforcement in identifying suspects by generating face images or retrieving their images from existing databases, based on the description of witnesses. The existing methods like hand-drawn sketches take time and absorb human resources; in addition to that rendering images from the software fails most of the time to sketch a real image and does not get the ideal scenario. In this paper, we present a survey of the recent progress concerning generating images from description and sketch face recognition, we analyze the difference between several algorithms on the problem based on evaluation metrics like accuracy and correlation similarity. We also give an overview of datasets used for generations or recognition.