Robust Image Classification Using Multi-level Neural Networks
Image classification problem is one of the most challenges of computer vision. In this paper, a robust image clas-sification approach using multilevel neural networks is proposed. In this approach, each image is fixedly divided into five regions each equal to half of the original image. Then these regions are classified by the multilevel neural classifier into five categories, i.e., Sky, Water, Grass, Soil and Urban. Both color moments and multilevel wavelets decomposition technique are used to extract features from the regions. Such features have been experimentally proved to be computationally efficient and effective in representing image contents. Experimental results clarify that the proposed approach performs better than other state-of-the-art classification approaches.
Image classification multi-level neural net-works feature eztraction wavelets decomposition
Samy Sadek Ayoub Al-Hamadi Bernd Michaelis Usama Sayed
Institute for Electronics,Signal Processing and Communications,Otto-von-Guericke University Magdebur Electrical Engineering Department,Assiut University,Egypt
国际会议
上海
英文
2709-2712
2009-11-20（万方平台首次上网日期，不代表论文的发表时间）