| Summary: | 碩士 === 國立雲林科技大學 === 電子與資訊工程研究所 === 94 === Image classification had become an important topic in multimedia processing. Recently, neural network-based methods had been proposed to solve the classification problem. Among them, the radial basis function (RBF) neural network is the most popular architecture because it has good learning and approximate capacity. However, the traditional RBF neural networks were sensitive to center initialization. In order to obtain appropriate centers, it needs to find significant features for further RBF clustering. In addition, the training procedure of the traditional RBF network is time-consuming. Therefore, in this thesis, a combination of self-organizing map (SOM) neural network and learning vector quantization (LVQ) is proposed to select more appropriate centers for RBF network, and a modular RBF (MRBF) neural network is proposed to improve the classification accuracy and speed up the training time.
Traditional region-based retrieval systems attempt to reduce the gap between high-level semantic and low-level features by representing images at the object level. However, in feature extraction, it is difficult to obtain adequate object feature because it is relative to segmentation method. In this thesis, we combine both segmentation method and user interaction to obtain adaptive object features for further semantic-based photograph analysis and overcome these problems mentioned above by using the proposed MRBF network.
The texture images classification results show that the proposed MRBF network has faster learning speed and higher accuracy rate than traditional RBF network. For semantic-based photograph analysis, the experimental results also show a reasonable classification results in human visual perception.
|
|---|
