The contribution of color for edge detection in natural scenes
Place: Large Lecture Room
Affiliation: Department of General and Experimental Psychology Justus Liebig University Giessen. Germany
In a statistical analysis of over 700 natural scenes from the McGill calibrated color image database we found that luminance and chromatic edges are statistically independent. These results show that chromatic edge contrast is an independent source of information that natural or artificial vision systems can linearly combine with other cues for the proper segmentation of objects (Hansen and Gegenfurtner, 2009, Visual Neuroscience, 26, 35?49). It is unclear to what degree humans use this information. Here we investigated the contribution of color and luminance information to predict human-labeled edges. Edges were detected in three planes of the DKL color space (L + M, L ? M, S ? (L + M)) and compared to human-labeled edges from several data sets. We used a ROC framework for a threshold-independent comparison of edge detector responses (provided by the Sobel operator) to ground truth (given by the human marked edges). The average improvement as quantified by the difference between the areas under the ROC curves for pure luminance and luminance/chromatic edges was small. The improvement was only about 3% if both L ? M and S ? (L + M)) edges were used in addition to the luminance edges, and about 2% if only a single additional color channels was used (L ? M or S ? (L + M)). Interesting, the same improvement for chromatic information (2.5%) occurred if the ROC analysis was based on human-labeled edges in gray-scale images. Observers probably use high-level knowledge to correctly mark edges even in the absence of a luminance contrast. The advantage of the additional chromatic channels was small (about 3%) on average but reached up to 11% for some images. For few images the performance decreased. Overall, color was advantageous of 90% out of the images we evaluated. We interpret our results such that chromatic information is on average beneficial for the detection of edges and can be highly useful and even crucial in special scenes.