中文摘要：

为了能快速准确的识别原料肉与注水肉,提出了一种基于可见-近红外光谱和稀疏表示的无损的识别方法。通过向猪肉样本（包括猪皮、脂肪层和肌肉层）注水的方法建立注水肉模型,采集未注水的原料肉和6类不同注水量的注水肉的可见和近红外漫反射光谱数据。为了消除光谱数据中的冗余信息并提高分类效果,对光谱数据进行光调制和归一化等预处理并截取有效波段,根据是否注水以及注水量的多少对样本进行分类。用所有训练样本构成原子库（字典）,通过l1最小化将测试样本表示为这些原子的最稀疏的线性组合。计算测试样本与各类的投影误差,将最小投影误差对应的类作为测试样本的所属类别,并应用留一法进行交叉检验,比较了稀疏表示法与支持向量机的识别结果。实验结果表明,利用稀疏表示法对于原料肉与注水肉的识别准确率可达到90%以上,获得了较好的分类效果,优于支持向量机的识别结果。而对于不同注水量的注水肉识别准确率与注水量之差正相关。稀疏方法不需要进行传统模式识别模型的前期学习与特征提取,适用于高维、小样本量数据的处理,计算成本低,将其用于注水肉的光谱数据识别具有一定的创新性,并取得了较满意的结果,为原料肉和注水肉的无损识别提供了一种有效方法。

英文摘要：

The present paper proposed a new nondestructive method based on visible/near infrared spectrum （Vis/NIRS） and sparse representation to rapidly and accurately discriminate between raw meat and water-injected meat .Water-injected meat mod-el was built by injecting water into non-destructed meat samples comprising pigskin ,fat layer and muscle layer .Vis/NIRS data were collected from raw meat and six scales of water-injected meat with spectrometers .To reduce the redundant information in the spectrum and improve the difference between the samples ,some preprocessing steps were performed for the spectral data , including light modulation and normalization .Effective spectral bands were extracted from the preprocessed spectral data .The meat samples were classified as raw meat and water-injected meat ,and further ,water-injected meat with different water injection rates .All the training samples were used to compose an atom dictionary ,and test samples were represented by the sparsest line-ar combinations of these atoms via l1-minimization .Projection errors of test samples with respect to each category were calculat-ed .A test sample was classified to the category with the minimum projection error ,and leave-one-out cross-validation was con-ducted .The recognition performance from sparse representation was compared with that from support vector machine （SVM ） . Experimental results showed that the overall recognition accuracy of sparse representation for raw meat and water-injected meat was more than 90% ,which was higher than that of SVM .For water-injected meat samples with different water injection rates , the recognition accuracy presented a positive correlation with the water injection rate difference .Spare representation-based clas-sifier eliminates the need for the training and feature extraction steps required by conventional pattern recognition models ,and is suitable for processing data of high dimensionality and small sample size .Furthermore ,it has a low computational cost .In this paper ,spare