Title :
Versatile neural network method for recovering shape from shading by model inclusive learning
Author :
Kuroe, Yasuaki ; Kawakami, Hajimu
Author_Institution :
Dept. of Inf. Sci., Kyoto Inst. of Technol., Kyoto, Japan
fDate :
July 31 2011-Aug. 5 2011
Abstract :
The problem of recovering shape from shading is important in computer vision and robotics. In this paper, we propose a versatile method of solving the problem by neural networks. We introduce a mathematical model, which we call `image-formation model´, expressing the process that the image is formed from an object surface. We formulate the problem as a model inclusive learning problem of neural networks and propose a method to solve it. In the proposed learning method, the image-formation model is included in the learning loop of neural networks. The proposed method is versatile in the sense that it can solve the problem in various circumstances. The effectiveness of the proposed method is shown through experiments performed in various circumstances.
Keywords :
computer vision; learning (artificial intelligence); neural nets; shape recognition; computer vision; image-formation model; learning loop; learning method; mathematical model; model inclusive learning; recovering shape; robotics; shading; versatile neural network; Accuracy; Brightness; Imaging; Mathematical model; Neural networks; Shape; Surface treatment;
Conference_Titel :
Neural Networks (IJCNN), The 2011 International Joint Conference on
Conference_Location :
San Jose, CA
Print_ISBN :
978-1-4244-9635-8
DOI :
10.1109/IJCNN.2011.6033644