Region-based retrieval of biomedical images

Searching digital biomedical images is a challenges problem. Prevalent retrieval techniques involve human-supplied text annotations to describe image contents. Biomedical images, such as pathology slides, usually have higher resolution than general-purpose pictures, making it additionally difficut to index. Precise object segmentation is also extremely difficult and is still an open problem. We are developing a multiresolution region-based retreival system for high-resolution biomedical image databases. The system, based on wavelets, the IRM (Integrated Region Matching) distance, and image classification, is highly robust to inacurate image segmentation and various visual alterations. Tested on a database of more than 70,000 pathology image fragments, the system has demonstrated high accuracy and fast speed.