Abstract | ||
---|---|---|
Today many algorithms for monochrome images have been developed based on the information provided by the gradient vector. However, these algorithms can not be applied to color images without an accurate approximation of the color gradient vector argument. Moreover, there is a great number of applications that require to know with the maximum accuracy as possible the direction of the color variation in color images. This paper presents a new breakthrough in our work on the approximation of the argument of the color gradient vector. Taking into consideration that Hue and Saturation provide very useful basis for judging color uniformity, and that in the Smith's HSI color space there is a close relationship between chromaticity and how humans perceive colors, in our proposal the argument of the Chromaticity gradient vector is approached based on the Hue and Saturation information. Moreover, we present a fuzzy measure of the quality or reliability of the proposed approach that, considering the inherent vagueness of the chromaticity values of the image pixels, provides us with a credibility-accuracy degree of the obtained values. |
Year | Venue | Keywords |
---|---|---|
2009 | PROCEEDINGS OF THE JOINT 2009 INTERNATIONAL FUZZY SYSTEMS ASSOCIATION WORLD CONGRESS AND 2009 EUROPEAN SOCIETY OF FUZZY LOGIC AND TECHNOLOGY CONFERENCE | Color gradient, Color image processing, Gradient argument, Gradient reliability, Gradient vector |
Field | DocType | Citations |
Computer vision,Image gradient,Color space,Color histogram,Hue,Color balance,Color model,Artificial intelligence,Mathematics,Color quantization,Color gradient | Conference | 1 |
PageRank | References | Authors |
0.38 | 11 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Belén Prados-Suárez | 1 | 10 | 5.97 |
Pilar Sobrevilla | 2 | 285 | 41.28 |
Eduard Montseny | 3 | 272 | 40.75 |
Santiago Romaní | 4 | 20 | 2.78 |