A copper strip surface defect detection system based on multi-feature fuzzy recognition comprises an encoder module, an image acquisition module, an image processing module, wherein the encoder module is used for obtaining the speed information of the operation of a copper strip and generating a frequency signal; the image acquisition module is used for acquiring the surface color image of the copper strip; and the image processing module is used for carrying out defect detection on the surface color image of the copper strip, wherein the defect detection of the image processing module specifically comprises the following processes of: applying a pre-judgment algorithm, if a defect is included, performing defected image division by a Canny algorithm, extracting the width-length ratio, circularity, squareness and invariant moment characteristics of the defected image and then inputting the extracted characteristic vectors into a multi-feature fuzzy recognition classifier, thereby identifying the type of the defect. By using the system, the identification rate and recognition accuracy of the type of the surface defect of the copper strip are improved, the requirements of enterprises for detecting and storing the surface defect information of the copper strip are met; and simultaneously, the system can be applied to the surface quality detection of other materials.