In this paper we propose an strategy to fuse visual features and unstructured-text data in a medical image retrieval system. The main goal of this work is to investigate whether the semantic information from text descriptions can be transferred to a visual similarity measure. Then, a system to search using the query-by-example paradigm is evaluated instead of a keyword-based search. We achieve this by using Latent Semantic Kernels to generate a new representation space whose coordinates define latent concepts that merge visual patterns and textual terms. The proposed method is tested in a medical image collection from the ImageCLEFmed08 challenge. The experimental evaluation tests the system using different image queries. The results show an improvement of the visual-text fused approach with respect to only using visual information.

Over the past few years, the microscopic image analysis has become increasingly important for the diagnosis and classification of diseases in natural and health sciences. Although some computational tools are available for image processing on those areas, their efficiency is limited by lack of adaptation to the specific problem. This work presents a simple and direct method to identify and classify spores with the use of machine vision and supervised learning techniques in order to detect diseases in bee colonies. The method makes use of segmentation techniques to identify spores which are subsequently classified by means of multi-class kernel-based vector machines. Different computer vision tools have been combined and applied to enhance the images and get the relevant information. The results are encouraging and are also applicable to the diagnosis of other parasitic diseases.