基于PCA预处理的图像特征属性约简

Image Feature Attributes Reduction Based on PCA Pre-processing

讨论了主分量分析在图像特征属性约简中的应用。运用主成分分析PCA(principal component analysis)对特征向量进行降维处理,并引入粗糙集理论,对其在特征参数属性优化中的运用进行了探索,利用约简算法剔除识别决策表中不必要的属性,揭示出CBIR(content based image retrieval)系统中特征条件判断属性内在的冗余性。UCI数据集处理结果表明PCA预处理可排除无关特征量的影响,有效进行特征提取,降低图像识别处理的复杂性。

The paper discusses the application of Principle Component Analysis （PCA） in image＇ s feature attributes reduction. After PCA pre-processing, Rough Set theory was introduced, and its application in characterized parameters＇ attribute optimization was also explored. The unnecessary attributes were eliminated with an attribute reduction algorithm. The inner redundancy of CBIR was revealed. The result of attribute reduction using UCI dataset proved the algorithm can exclude the influence of unused attributes and decrease the complexity of CBIR effectively.