Image Quality and Automatic Color Equalization - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2007

Image Quality and Automatic Color Equalization

Résumé

In the professional movie field, image quality is mainly judged visually. In fact, experts and technicians judge and determine the quality of the film images during the calibration (post production) process. As a consequence, the quality of a restored movie is also estimated subjectively by experts [26,27]. On the other hand, objective quality metrics do not necessarily correlate well with perceived quality [28]. Moreover, some measures assume that there exists a reference in the form of an "original" to compare to, which prevents their use in digital restoration field, where often there is no reference to compare to. That is why subjective evaluation is the most used and most efficient approach up to now. But subjective assessment is expensive, time consuming and does not respond, hence, to the economic requirements of the field [29,25]. Thus, reliable automatic methods for visual quality assessment are needed in the field of digital film restoration. Ideally, a quality assessment system would perceive and measure image or video impairments just like a human being. The ACE method, for Automatic Color Equalization [1,2], is an algorithm for digital images unsupervised enhancement. Like our vision system ACE is able to adapt to widely varying lighting conditions, and to extract visual information from the environment efficaciously. We present in this paper is the use of ACE as a basis of a reference free image quality metric. ACE output is an estimate of our visual perception of a scene. The assumption, tested in other papers [3,4], is that ACE enhancing images is in the way our vision system will perceive them, increases their overall perceived quality. The basic idea proposed in this paper, is that ACE output can differ from the input more or less according to the visual quality of the input image In other word, an image appears good if it is near to the visual appearance we (estimate to) have of it. Reversely bad quality images will need "more filtering". Test and results are presented.
Fichier non déposé

Dates et versions

hal-00281797 , version 1 (24-05-2008)

Identifiants

Citer

Majed Chambah, Christophe Saint-Jean, Alessandro Rizzi. Image Quality and Automatic Color Equalization. Image Quality and System Performance IV, Jan 2007, San José, United States. pp.64940B, ⟨10.1117/12.697778⟩. ⟨hal-00281797⟩
45 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More