Multi Focus Image Fusion Using Statistical Approaches

Pictures of the long focal lengths cameras, suffer from the problem of limited depth of field. Consequently, it is often difficult to obtain good focus for all objects in the picture. In this work, the problem of multi focus is solved by taking several pictures with different focus points, and then fusing them together to form a single image using image fusion method. Contrast of the source images is used as a measure to select the proper pixels (pixels with high focus) to obtain the fused (output) image. This work proposed three statistical measures of contrast to calculate the pixels gradient magnitude. Those three measures are applied and compared with the traditional method of gradient magnitude measures (Sobel and Perwit) in Multi focus Image Fusion. The results show that the proposed method gave better results than Sobel and Perwit methods.