单样本条件下基于图像增强和Fourier频谱的人脸识别

目前有许多处理正面视觉人脸的识别方法，当有充分数量的有代表性的样本时，能取得较好的识别效果。然而当处理单样本识别问题时，现有的许多方法的识别率将明显下降或甚至不适用。为了加强单训练样本的分类信息，训练样本与其基于受扰动的奇异值的重构图组合成新样本，Fourier频谱作为人脸识别特征，在ORL人脸库上的实验结果表明了该方法的有效性。

Face Recognition Based on Image Enhancement and Fourier Spectrum for One Training Image per Person

At present there are many methods that could deal well with frontal view face recognition when there is sufficient number of representative training samples. However, few of them can work well when only one training sample per class is available. In order to enhance the classification information of the single training sample, each training sample is combined with its reconstructed image gotten by perturbing the image's singular values into a new training sample. The Fourier spectrum is used as feature for recognition. Experimental results on ORL show the effectiveness of the method.