Traditional Ceramic Sculpture Feature Recognition Based on the Machine Learning Algorithm

Aiming at the problems of low recognition accuracy, high line noise, and time cost feature in traditional ceramic sculpture modeling methods, this paper designed a method based on machine learning algorithm. By constructing sparse representation model image, posterior probability image was determined Gaussian distribution pixels carried out to determine law super-resolution reconstruction realized. The state classified by kernel classification method. Finally, algorithm red BP neural network is introduced construct error threshold constantly iterated realize recognition. experimental results show that has accuracy identifying features, can effectively suppress short overhead, which certain feasibility.