Brightness normalization for Blurred Image Matching

Abstract

Blurred Image Matching (BIM) is based on image pre-processing and Blob detection. BIM methods has been designed to function with images presenting a strong level of noise of different kinds. The technique shows an excellent robustness, speed and unique features when compared to existing methods. This article investigates the process BIM is based on, proposes a new way to improve the range of noise the technique can process with a good range of success by adding image normalization. Moreover, the article investigates the technique’s performances when confronted to different parameters, thus suggestion an ideal brightness for the blob detection to perform at the best of its capacities.