Illumination Estimation Is Sufficient for Indoor-Outdoor Image Classification (CROSBI ID 673463)
Prilog sa skupa u zborniku | izvorni znanstveni rad | međunarodna recenzija
Podaci o odgovornosti
Banić, Nikola ; Lončarić, Sven
engleski
Illumination Estimation Is Sufficient for Indoor-Outdoor Image Classification
Indoor-outdoor image classification is a well-known problem for which multiple solutions have been proposed, many of which use both low-level and high-level features put into various models. Despite varying complexity, the accuracy of most of these models is reported to be around 90%. In this paper it is shown that the same accuracy can be obtained by simple manipulation of only low-level features extracted from the image in the early phase of image formation and based on the simplest forms of illumination estimation, namely methods such as Gray-World. Additionally, it is shown how using the built-in camera auto white balance is also enough to effectively achieve state-of-the-art indoor-outdoor classification accuracy. The results are presented and discussed.
Illumination estimation ; indoor-outdoor ; image classification
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
nije evidentirano
Podaci o prilogu
473-486.
2018.
objavljeno
10.1007/978-3-030-12939-2_33
Podaci o matičnoj publikaciji
40th German Conference on Pattern Recognition
Podaci o skupu
German Conference on Pattern Recognition
poster
09.10.2018-12.10.2018
Stuttgart, Njemačka