The goal of semi-supervised image segmentation is to obtain the segmentation from a partially labeled image. By utilizing the image manifold structure in labeled and unlabeled pixels, semi-supervised methods propagates the user labeling to the unlabeled data, thus minimizing the need for user labeling. Several semi-supervised learning methods have been proposed in the literature. In this paper, we consider the delinquent of segmentation of large collections of images and the classification of images by allied diseases. We are detecting diseased images by the process of segmentation and classification. The segmentation used in this paper has two advantages. First, user can specify what they want by highly controlling the segmentation. Another is, at initial stage this model requires only minimum tuning of model parameters. Once initial tuning is done, the setup can be used to automatically segment a large collection of images that are distinct but share similar features. And for classification of diseases, a manifold learning method, called parameter-free semi-supervised local Fisher discriminant analysis is used. This method preserves the global structure of unlabeled samples in addition to separating labeled samples in different classes from each other. The semi-supervised method has an analytic form of the globally optimal solution, which can be computed efficiently by Eigen decomposition. Espousal experiments on various collections of biological images suggest that the proposed model is effective for segmentation with classification and is computationally efficient.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.