Robust superpixels using color and contour features along linear path
This work addresses the need for more accurate and regular superpixel decompositions in computer vision applications, though it appears incremental as it builds on existing trade-offs in the field.
The paper tackled the problem of superpixel decomposition by proposing SCALP, a framework that jointly enforces color homogeneity, contour adherence, and shape regularity, resulting in improved accuracy and robustness to noise while maintaining computational complexity, with evaluations showing it outperforms state-of-the-art methods on standard datasets.
Superpixel decomposition methods are widely used in computer vision and image processing applications. By grouping homogeneous pixels, the accuracy can be increased and the decrease of the number of elements to process can drastically reduce the computational burden. For most superpixel methods, a trade-off is computed between 1) color homogeneity, 2) adherence to the image contours and 3) shape regularity of the decomposition. In this paper, we propose a framework that jointly enforces all these aspects and provides accurate and regular Superpixels with Contour Adherence using Linear Path (SCALP). During the decomposition, we propose to consider color features along the linear path between the pixel and the corresponding superpixel barycenter. A contour prior is also used to prevent the crossing of image boundaries when associating a pixel to a superpixel. Finally, in order to improve the decomposition accuracy and the robustness to noise, we propose to integrate the pixel neighborhood information, while preserving the same computational complexity. SCALP is extensively evaluated on standard segmentation dataset, and the obtained results outperform the ones of the state-of-the-art methods. SCALP is also extended for supervoxel decomposition on MRI images.