Level Set KSVD
This work addresses a domain-specific problem in agriculture for detecting crop diseases, but it appears incremental as it combines existing techniques.
The authors tackled image segmentation for detecting fungi spread in crops by merging sparse dictionary learning with a variational level-set method, achieving results compared to other methods on aerial images of cotton fields.
We present a new algorithm for image segmentation - Level-set KSVD. Level-set KSVD merges the methods of sparse dictionary learning for feature extraction and variational level-set method for image segmentation. Specifically, we use a generalization of the Chan-Vese functional with features learned by KSVD. The motivation for this model is agriculture based. Aerial images are taken in order to detect the spread of fungi in various crops. Our model is tested on such images of cotton fields. The results are compared to other methods.