Bayesian network is a probability, which is based on a probabilistic inference network of graphical and Bayesian formula is the basis of the probability of network. The paper analyzes general Semantic pixel naming and the implementation process and concept of Bayesian per pixel segmentation (BPPS). On this basis, author presents a novel deep learning framework for clustering and information mining for probabilistic per pixel segmentation, which author terms it as Bayesian per pixel segmentation (BPPS) by initially checking out the noise in the image. This new method is more accurate and efficient.