In the conventional copper strip surface defect detection system,the re exist problems that hardware improvement for more detailed information in captured images is confine d by factors such as manufacturing level and costs,and the conventional super-resolution (SR) restoration method has poor real-time performance.In order to resolve these problems,we propose a fast s uper-resolution restoration method based on rough set and pre-classification of texture features in this pa per.First of all,by using the theory of attribute reduction approach of rough set,we select and optimize those stati stical characteristic parameters which offer better descriptions on targets with tiny texture defects.And at the same time,according to the texture features,we make pre-search and pre-classification on sample sets whe n doing matching search.Finally, in the pre-classified sample subsets with similar texture features,we find exa ct matches for the inputs of low-resolution images.Both theoretical analysis and experimental results demon strate that our method is able to enhance high frequency information in defect areas,sharpen edges and details,a nd perform better in real-time systems,and also,it has superiority and feasibility in balancing quality with efficiency in image restoration when applying it in the online system for copper stripe surface defect detection.