APPLYING MULTI-CLASS NEURAL NETWORK TO SCENE IMAGE CLASSIFICATION

摘要：

In this paper, we show a specific high-level classification problem (scene images classification) using the low level features such as representative colors and Gabor textures. Based on the low level features, we introduce the neural network as the multi-class classifier to classify the eight different objects in images. Experimental results show our method is promising. Keyword: Image Retrieval, neural network, scene image classification

作者: YULI SHEN JIANFEN REN

作者单位: Information School, Guangdong Ocean University, Zhanjiang, 524088, China Automatic Control department of North Western Polytechnic University xian, china, 710072

会议类型: 国际会议

会议名称: 第四届中华文化自然遗产数字化及保护与数字博物馆研讨会

会议地点: 开封

会议语种:英文

页码: 359-363

在线出版日期: 2006-10-15（万方平台首次上网日期，不代表论文的发表时间）