Portrait Identification in Digitized Paintings on the Basis of a Face Detection System
Christos‐Nikolaos Anagnostopoulos, Ioannis E. Anagnostopoulos, Ilias G. Maglogiannis, Dimitrios D. Vergados · 2007
In this paper, the problem of automatic identification of portraits in paintings collections is addressed. A face detection approach in digital images is now implemented n digitized paintings, which is based on fuzzy logic rules especially set for detecting possible skin areas in color images. The candidate regions are then forwarded in a Probabilistic Neural Network (PNN), which is properly trained for face identification. The test sample for assessing the proposed method consists of 200 digitized paintings downloaded from the website of the State Hermitage Museum. The overall performance of the system reached 88.8%.