Computational cognitive color perception
2016 IEEE Congress on Evolutionary Computation, CEC 2016, Vancouver, Kanada, 24 - 29 Temmuz 2016, ss.2262-2271, (Tam Metin Bildiri)
- Yayın Türü: Bildiri / Tam Metin Bildiri
- Doi Numarası: 10.1109/cec.2016.7744068
- Basıldığı Şehir: Vancouver
- Basıldığı Ülke: Kanada
- Sayfa Sayıları: ss.2262-2271
- Anahtar Kelimeler: Auto-association, Cognitive computing, Color difference, Fuzzy neural tree, Genetic algorithm, Visual perception
- Maltepe Üniversitesi Adresli: Hayır
Özet
Comprehension of aesthetical color characteristics based on a computational model of visual perception and color cognition are presented. The computational comprehension is manifested by the machine's capability of instantly assigning appropriate colors to the objects perceived. They form a scene with aesthetically pleasing characteristics. The present approach to computational cognition is principally the same as contrived earlier [1]. This work distinguishes itself from the earlier work through the involvement of color differences. The color difference computations are carried out based on a standard human color observer model. The color difference information is combined with geometric perception information using the method of fuzzy neural tree based on likelihood. The study exemplifies the suitability of the computational cognition for modeling cognition phenomenon. Cognitive color perception in computational form has generic relevance to applications involving human-like aesthetical appreciation, as is the case in building architecture, for instance and other design tasks.