ILLUMINATION NORMALIZATION USING LOCAL GRAPH STRUCTURE

The problem associated with Illumination variation is one of the major problems in image processing, pattern recognition, medical image, etc; hence ther e is a need to handle and deal with such variations . This paper presents a novel and efficient algorithm for images illumination correction call local graph str ucture (LGS). LGS features are derived from a general defi nition of texture in a local graph neighborhood. Th e idea of LGS comes from a dominating set for a graph of the image. The experiments results on ORL face database images demonstrated the effectiveness of t he proposed method. The new LGS method can be stabilized more quickly and obtain higher correct r ate compare to local binary pattern (LBP). Finally, LGS is simple and can be easily applied in many fields, such as image processing, pattern recognition, med ical image as preprocessing