For a long time, fabric defect detection has been completed by quality inspectors. Meanwhile, the process of defect discrimination is greatly affected by subjective factors and has the problems of low detection efficiency and high cost. With the close combination of computer vision technology and various fields, fabric defect detection system based on vision has gradually become an important solution to replace manual quality inspection. For the fabric defect detection based on vision, this paper reviews the aspects including industry development, general detection standards, overall structure of the system and key technologies in detection algorithms, introduces the existing fabric defect detection products based on vision in the market, analyzes the common defect detection standards and the basic structure of the detection system, and summarizes and compares the research status of image processing and deep learning technology in the field of fabric defect detection in recent years. Finally, the paper summarizes the key problems to be solved, and discusses the possible development direction in the future.