Image Content Analysis Using Modular RBF Neural Network
Chuan‐Yu Chang, Hung‐Jen Wang, Chi-Fang Li · 2010
Image content analysis has become an important issue in multimedia processing. Region-based image retrieval systems attempt to reduce the gap between high-level semantics and low-level features by representing images at the object level. Recently, the radial basis function (RBF) neural network has been proposed to solve the classification problem; however, it is time-consuming and sensitive to center initializa- tion. Therefore, modular RBF neural network (MRBFNN) incorporated with a self-organizing map (SOM) and a learning vector quantization (LVQ) neural network is proposed for semantic-based image content clas- sification. Using SOM and LVQ, we can obtain more appropriate centers for the RBF neural network. More- over, principal component analysis (PCA) is applied to reduce the dimension of features. Experimental re- sults show that the proposed method is capable of analyzing components of photographs into semantic cate- gories with high accuracy, resulting in photographic analysis that is similar to human perception.