Cement is a kind of important building material, its performance is closely related to cement hydration. With the development of computer vision and deep learning, more and more researchers begin to study the hydration state or even mining or prediction the performance of cement by the cement hydration microstructure images. However, collecting real cement hydration microstructure image was extremely costly since the amount of human effort and expertise required. In this article, a fast cement microstructure texture image synthesis method based on PixelCNN was proposed. This method used CNN to extract more implicit features of various scales and achieved a pleased result. During the generation process, an optimization method of cyclic assignment prediction is adopted to avoid convolving all pixels of the image of each convolution, and thereby increasing the speed of texture synthesis. The validity of our method is proved by comparing it with other models.
A Fast Cement Microstructure Texture Image Synthesis Method Based on PixelCNN
Lect. Notes Electrical Eng.
International Conference on Electrical and Information Technologies for Rail Transportation ; 2021 October 21, 2021 - October 23, 2021
Proceedings of the 5th International Conference on Electrical Engineering and Information Technologies for Rail Transportation (EITRT) 2021 ; Chapter : 64 ; 646-653
2022-02-19
8 pages
Article/Chapter (Book)
Electronic Resource
English
A Fast Cement Microstructure Texture Image Synthesis Method Based on PixelCNN
British Library Conference Proceedings | 2022
|Fast Texture-Based Tracking and Delineation Using Texture Entropy
British Library Conference Proceedings | 2005
|Regular-texture image retrieval based on texture-primitive extraction
British Library Online Contents | 1999
|Fast algorithms for histogram matching: Application to texture synthesis
British Library Online Contents | 2000
|