Automatic identification and location of Mura defect in various screens plays an important role in improving the quality of screens. It is one of the most important technologies that need to be developed urgently. Aiming at the features of low contrast and lack of obvious edge of Mura defect, this paper proposes a method of Mura detection based on image gray curve and its improved method. This improved method is based on the principle of mean filter to smooth the picture and down-sampling. By studying the information about peak and trough of the gray curve on sampling lines, the BP neural network is used to construct an automatic detection and location algorithm for line Mura. The experimental results show that, compared with the existing Mura detection methods, the improved method in this paper can distinguish line Mura defect on the mobile phone screen more accurately and quickly. The accuracy rate is 98.33%, and no parameter needs to be adjusted during the detection process, realizing automatic detection, and positioning of line Mura.