||Intensity normalization is important in quantitative image analysis, especially when extracting features based on intensity. In automated microscop, particularly in large cellular screening experiments, each image contains similar objects (ie. cells) but the density or amount of pbjects may vary markedly from image to image. Standard intensity normalization methods such as histogram matching or mean value matching are based on the assumption that both the type and the amount of content are similar in the images to be matched. This is typically not the case in cellular screening images. I will talk about how intensity normalization can be improved by incorporating gradient magnitude information in the process.