Abstract:
Digital entertainment relies heavily on photo-to-face sketch synthesis. An intelligent face sketch synthesis system must be light-resistant. Such a system will perform well in real-world uncontrolled lighting conditions.
However, previous face sketch synthesis methods synthesize sketches under well-controlled lighting. When lighting changes, these methods produce unsatisfactory results. This paper introduces a cascaded face sketch synthesis framework with a multiple feature generator and a cascaded low-rank representation.
The multiple feature generator generates a sketch feature in an artist’s style and a photo feature that is robust to different illuminations. Both features enable database selection of the best sketch candidates for a photo patch.
Cascaded low-rank representation reduces the gap between synthesized face sketches and artist-drawn sketches. Experimental results show that the cascaded framework generates realistic sketches comparable to current methods on the Chinese University of Hong Kong face sketch database under well-controlled illuminations.
This framework outperforms these methods on the extended Chinese University of Hong Kong face sketch database and web-sourced Chinese celebrity face photos under different illuminations. This framework allows for the novel implementation of computer-aided optical systems that are crucial to face sketch synthesis and optical imaging.
Note: Please discuss with our team before submitting this abstract to the college. This Abstract or Synopsis varies based on student project requirements.
Did you like this final year project?
To download this project Code with thesis report and project training... Click Here
