Title :
Three-dimensional object modeling for computer vision using artificial neural networks
Author :
Jiancheng Jia ; En Cao
Author_Institution :
Sch. of Electr. & Electron. Eng., Nanyang Technol. Univ., Singapore
Abstract :
Presents a neural network method for modeling 3D objects and discusses its potential applications in computer vision. Various 3D object models with freeform surfaces and different textures can be generated using this method, by training the network based on the main geometric features of the objects. It is also very flexible and capable of providing the different photometric geometries which are desired in many computer vision applications. Experimental results indicate that the method can be used as a modeling tool in computer vision.<>
Keywords :
computer vision; geometry; image texture; learning (artificial intelligence); neural nets; photometry; solid modelling; 3D object modelling; artificial neural networks; computer vision; freeform surfaces; geometric features; photometric geometries; textures; training; Application software; Artificial neural networks; Computer vision; Layout; Neural networks; Neurons; Object recognition; Photometry; Shape; Surface texture;
Conference_Titel :
TENCON '93. Proceedings. Computer, Communication, Control and Power Engineering.1993 IEEE Region 10 Conference on
Conference_Location :
Beijing, China
Print_ISBN :
0-7803-1233-3
DOI :
10.1109/TENCON.1993.320164
