Objective In the study and practice of the tongue characterization of traditional Chinese medicine,experienced doctors find that a large number of the tongue images collected by tongue image instrument cannot meet the clinical requirement,which directly affects the final result of tongue image analysis.This paper focuses on the research about tongue image quality assessment to provide help for the accurate selection of image in clinic.Methods We analyze the requirements of tongue inspection,statistics of local normalized luminance based on natural scene statistics model,texture,color and geometric features of tongue images are extracted respectively,and then support vector machine (SVM) is used for classification.By using the classification accuracy,we verify whether this method can provide help for the accurate selection of image in clinic.Results Through the extracted feature of tongue image,we get a better evaluation of tongue image quality and can accurately select the tongue images used in clinic.Conclusions Experimental results show the feasibility of quality assessment for tongue image.This approach is expected to be applied in the new generation of tongue image analysis instrument,providing high-quality reference data for assisted tongue image analysis.