Adaboost和信息瓶颈算法在图像检索中的应用

提出基于Adaboost特征选择和信息瓶颈算法的图像检索方法，提取图像的量化颜色直方图特征和Gabor小波纹理特征，采用Adaboost特征选择算法进行特征降维；用信息瓶颈算法对图像进行聚类，得到每个图像类的聚类中心；计算查询示例图像和对应图像类的图像之间的相似度，按照相似度的大小返回检索结果。实验表明，提出的方法可以明显提高检索效率以及检索的精度。

Application of Adaboost and information bottleneck algorithm in image retrieval

An image retrieval method based on Adaboost feature selecting information bottleneck algorithm is proposedt,he color and texture feature of image library is extracted and Adaboost algorithm is used to select feature and reduce the fea-ture dimensionality.Information bottleneck algorithm for image clustering is proposed and each cluster center of image class is obtained.The similarity between the sample image and retrieval the corresponding categories is calculated,according to the size of the similarity to return to retrieval results.The experimental results show that the proposed method has a good retrieval performance.