The invention relates to a depression and schizophrenia recognition method. The depression and schizophrenia recognition method comprises the following steps of S1, obtaining the electroencephalogramdata of a patient during opening eyes and closing eyes under resting state; S2, pretreating the electroencephalogram data in the step S1; S3, converting the data obtained during pretreatment in the step S2 into power spectral density PSD; S4, extracting various characteristics of PSD in the step S3, and constructing a characteristic vector; S5, with the characteristic vectors in the step S4 as input of a classifier, classifying the data; S6, performing model assessment on the classification results in the step S5, so as to obtain a classification model being good in generalization ability; andS7, inputting a test set into the classifier model in the step S6, performing classification, and realizing depression and schizophrenia recognition. According to the depression and schizophrenia classification method, a support vector machine classification method is used for treating and classifying the electroencephalogram of the patient, and the method has good divisibility for data, and is higher in accuracy than other classification methods.