Portrait Identification in Digitized Paintings on the Basis of a Face Detection System

  • Authors:
  • Christos-Nikolaos Anagnostopoulos;Ioannis Anagnostopoulos;I. Maglogiannis;D. Vergados

  • Affiliations:
  • Cultural Technology & Communication Dpt., University of the Aegean;Information & Communication Systems Engineering Dpt., University of the Aegean;Information & Communication Systems Engineering Dpt., University of the Aegean;Information & Communication Systems Engineering Dpt., University of the Aegean

  • Venue:
  • Proceedings of the 2007 conference on Emerging Artificial Intelligence Applications in Computer Engineering: Real Word AI Systems with Applications in eHealth, HCI, Information Retrieval and Pervasive Technologies
  • Year:
  • 2007

Quantified Score

Hi-index 0.00

Visualization

Abstract

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%.