Interactive multiclass segmentation using superpixel classification
This addresses the problem of efficient and accurate interactive segmentation for users needing to extract semantic objects from images, though it appears incremental as it builds on existing superpixel and classification techniques.
The paper tackles interactive multiclass segmentation by proposing SCIS, a method using superpixel over-segmentation and SVM classification from user strokes, and demonstrates that it significantly outperforms competing algorithms on reference benchmarks.
This paper adresses the problem of interactive multiclass segmentation. We propose a fast and efficient new interactive segmentation method called Superpixel Classification-based Interactive Segmentation (SCIS). From a few strokes drawn by a human user over an image, this method extracts relevant semantic objects. To get a fast calculation and an accurate segmentation, SCIS uses superpixel over-segmentation and support vector machine classification. In this paper, we demonstrate that SCIS significantly outperfoms competing algorithms by evaluating its performances on the reference benchmarks of McGuinness and Santner.