Dynamic weighted histogram equalization for contrast enhancement using for Cancer Progression Detection in medical imaging

Contrast-enhancement is very essential and ideal to produce a maximum contrast of many computer-vision and image-processing applications with minimum brightness error. Moreover, there is no mechanism to control the brightness error, contrast in conventional histogram equalization and mean shift problem that is usually occurs when the histogram equalization based contrast enhancement methods has used. The purpose of this research is to devise an intelligently robust framework based on the image data that is collected during several phases of Ultrasound (US) cancer image by automating the real-time image enhancement, segmentation, classification and progression the widely spreading of cancer disease at initial stages moreover, we have proposed a new methodology of contrast optimization that overcomes the mean-shift problem. The data is collected and preprocessed, while image segmentation techniques has used to partition and extract the concerned object from the enhanced image.