Experimental results show that the proposed approach is more accurate in image semantic classification than other ones, such as SVMs classifier using color and textural features. 實(shí)驗結果表明,本文提出的方法在圖像語(yǔ)義分類(lèi)的準確性方面要優(yōu)于諸如采用色彩特征和紋理特征的支持向量機分類(lèi)器的其它方法。