Facial Parts-Based Face Hallucination Method

Autor: Kaori Kataoka, Hideki Koike, Akira Suzuki, Shingo Ando
Rok vydání: 2010
Předmět:
Zdroj: Lecture Notes in Computer Science ISBN: 9783642136801
ICISP
DOI: 10.1007/978-3-642-13681-8_1
Popis: Face hallucination produces high-resolution facial images from low-resolution inputs. In this paper, we propose a facial-parts-based face hallucination method. Since our goal is face recognition rather than face reconstruction, the contour information of facial-parts(such as eyes) is important. This method reconstructs facial parts as entities instead of dividing them into small blocks. We obtain the contours of facial parts by using the Active Appearance Model(AAM), and transform training images based on contours. We confirm that the proposed method significantly enhances face recognition performance.
Databáze: OpenAIRE