Obiekt

Autor:

Shang, Lingjuan ; Liang, Jing ; Wang, Aibo ; Sun, Hao ; Liu, Wang ; Xie, Xufen ; Lian, Yusheng

Współtwórca:

Urbańczyk, Wacław. Redakcja

Opis:

Optica Applicata, Vol. 54, 2024, nr 1, s. 69-83 ; Optica Applicata is an international journal, published in a non-periodical form in the years 1971-1973 and quarterly since 1973. From the beginning of the year 2008, Optica Applicata is an Open Access journal available online via the Internet, with free access to the full text of articles serving the best interests of the scientific community. The journal is abstracted and indexed in: Chemical Abstracts, Compendex, Current Contents, Inspec, Referativnyj Zhurnal, SCI Expanded, Scopus, Ulrich’s Periodicals Directory ; kliknij tutaj, żeby przejść

Abstrakt:

Objective To study the conversion model of RGB color space to CIE1976 L*a*b* color space with higher accuracy, which provides some value for the fields of computer color matching, color detection, and color reproduction. Methods The method of three-dimensional look-up table method and back propagation (BP) neural network are proposed, and the effect of the model built under the two methods is evaluated under the calculation of CIE1976 L*a*b* and CIE2000 color difference by NCS color card data. Results Under the calculation of CIE1976 L*a*b* color difference, the average color difference under the four interpolation methods of the three-dimensional look-up table is within 3, and the average color difference of the BP neural network algorithm is 1.8720. Under the calculation of CIE2000 color difference, the average color difference of the four interpolation methods of the three-dimensional look-up table drops within 1, and the average color difference of the BP neural network also shows a downward trend, and the specific value is 1.3449. Conclusions According to the result obtained by the research method, the color difference of the tetrahedral interpolation method is the smallest among the four interpolation methods of the three-dimensional look-up table method under both color difference formulas. Whether it is the three-dimensional look-up table method or the BP neural network, the model obtained by the CIE2000 color difference formula is the best. In general, for the two methods, the BP neural network method is more convenient and faster, and the color difference effect is also desirable.

Wydawca:

Oficyna Wydawnicza Politechniki Wrocławskiej

Miejsce wydania:

Wrocław

Data wydania:

2024

Typ zasobu:

artykuł

Identyfikator zasobu:

doi:10.37190/oa240106

Źródło:

<sygn. PWr A3481II> ; kliknij tutaj, żeby przejść ; kliknij tutaj, żeby przejść

Język:

eng

Powiązania:

Optica Applicata ; Optica Applicata, Vol. 54, 2024 ; Optica Applicata, Vol. 54, 2024, nr 1 ; Politechnika Wrocławska. Wydział Podstawowych Problemów Techniki

Prawa:

Wszystkie prawa zastrzeżone (Copyright)

Prawa dostępu:

Dla wszystkich w zakresie dozwolonego użytku

Lokalizacja oryginału:

Politechnika Wrocławska