A quick and accurate detection method which can identify whether the meat contain excessive moisture is proposed. By using near-infrared (NIR) spectroscopy measurement, the meat moisture content model is established. In order to improve the accuracy and sensitivity of NIR spectra measurement, image information and the pH value data are used as assistant parameters of the meat moisture content model. Multi-sensor information fusion is performed on the moisture, image information and pH value. The detection is completed with a support vector machine (SVM) data classifier.