The invention relates to a detection and grading 
system for tenderness of fresh beef based on multispectral imagery, which belongs to the technical field of detection of 
food quality. In a dark box, the lens of a CCD industrial camera is aligned with the center of a table board of a height-adjustable objective table, two multispectral 
light source assemblies are symmetrically arranged at a left sidewall and a right sidewall of the dark box respectively through two 
light source fixing supports, and a large power 
LED array on each of multispectral 
light source assemblies is composed of LEDs of 6 kinds of wave bands; during detection, a sample to be detected is put on the table board of the height-adjustable objective table, the LEDs of 6 kinds of wave bands alternately radiate in order, the CCD industrial camera acquires multispectral images of the sample to be detected, a multispectral 
beef sample reflection image in an interested area of a 
lean meat part is extracted through 
computer image processing, and therefore, marbling of beef is extracted, and evaluation and grading of content of marbling of the beef are carried out, and tenderness of the beef is predicted. The detection and grading 
system provided by the invention is applicable to companies dealing with 
cutting, marketing, 
processing and import and export of fresh beef and to market supervision by quality and technical supervision departments.