The usefulness of the hit-miss transform (HMT) and related transforms for pattern matching in document image applications is examined. Although the HMT is sensitive to the types o...
We investigate a form of modular neural network for classification with (a) pre-separated input vectors entering its specialist (expert) networks, (b) specialist networks which ar...
ngly better objective function value until an optimal solution is reached. From an abstract point of view, an augmentation problem is solved in each iteration. That is, given a fea...
We analyze theoretically the subspace best approximating images of a convex Lambertian object taken from the same viewpoint, but under different distant illumination conditions. Si...
— The traditional image representations are not suited to conventional classification methods, such as the linear discriminant analysis (LDA), because of the under sample problem...
Dacheng Tao, Xuelong Li, Xindong Wu, Stephen J. Ma...