Intelligent image inpainting based on a brain-mimicking Recognition-Mining-Synthesis network

Autor:	Shao-Han Tang, Yu-Han Chen, Chuan-Yung Tsai, Liang-Gee Chen
Rok vydání:	2009
Předmět:	Computer science business.industry ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Inpainting Bayesian network Pattern recognition Iterative reconstruction Attention model Image (mathematics) Intelligent Network Computer vision Artificial intelligence business Image restoration
Zdroj:	2009 IEEE 13th International Symposium on Consumer Electronics.
Popis:	In this paper, a new image inpainting method based on a brain-mimicking Bayesian network is proposed. It features the Hierarchical-Spatial-Temporal prediction for simulating brain's neural projections. The trained network can recognize image and automatically mine for defects by its attention model, before synthesizing lost image parts. Difficult inpainting problems, like images with important features lost, are shown to have good results.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::484798e8282ba10ffef5b3199600c446 https://doi.org/10.1109/isce.2009.5157010 Zobrazit plný text záznamu