Classification method for carrying out refined grade sorting on apples based on physiological cognition characteristics of people

The invention discloses a classification method for carrying out refined grade sorting on apples based on physiological cognition characteristics of people. The classification method comprises the following steps: 1, obtaining brain imaging data when a human brain watches and recognizes the apples; 2, processing the brain imaging data to obtain a positive activity factor alpha of an apple with a red color, a large size and a regular shape; 3, directly training a support vector machine algorithm by using pictures which are red in color, large in size, regular in shape, green in color, small in size and irregular in shape, and adjusting a decision boundary by using a penalty function HL; 4, bringing the influence of the positive activity factors in the human brain recognition in the step 2 into the decision boundary adjustment process in the step 3, increasing the punishment intensity when it is judged that errors exist, and further optimizing and adjusting the decision boundary; and 5, classifying the samples