CAJ | 학술논문

　　针对SURF对图像局部特征具有极好的描述能力，但对于全局特征描述能力不强的缺点，提出将SURF和全局颜色特征相融合的图像分类算法，提取图像的SURF特征向量集，并利用随机直方图算法将该向量集进行数据归约成单一高维特征向量；提取图像HSV颜色直方图；分别利用支持向量机（SVM）对这两种特征进行分类；将两个分类结果进行高层特征融合得到最终分类结果。实验结果表明，该算法显著提高了图像分类的准确率。
　　침대SURF대도상국부특정구유겁호적묘술능력，단대우전국특정묘술능력불강적결점，제출장SURF화전국안색특정상융합적도상분류산법，제취도상적SURF특정향량집，병이용수궤직방도산법장해향량집진행수거귀약성단일고유특정향량；제취도상HSV안색직방도；분별이용지지향량궤（SVM）대저량충특정진행분류；장량개분류결과진행고층특정융합득도최종분류결과。실험결과표명，해산법현저제고료도상분류적준학솔。
SURF(Speeded Up Robust Feature)has excellent description ability for local features, but isn’t strong for describ-ing global features. This paper proposes an image classification algorithm based on the combination of SURF and global fea-tures. The SURF vector sets are extracted, and the vector sets are reduced to a single high dimensions feature vector by employing the random histogram algorithm. The HSV(Hue, Saturation, and Value)color histogram is extracted. These two features are classified with SVM(Support Vector Machine), respectively. The two classification results are integrated by the algorithm of high-level cue integration to get the ultimate classification result. The experimental results demonstrate that the proposed algo-rithm greatly improves the accuracy of image classification.