In order to improve the recognition rate of the traditional LBP algorithm when extracting target image features, a feature extraction method based on mask iterative ROI to improve the LBP algorithm is proposed. The extraction method using mask iterative ROI reduces the processing of interference information or invalid regions and shortens the defective region extraction time. Based on the local binary pattern (LBP) to determine the circular area of the said central pixel point according to the preset radius, the gray value size relationship between the neighboring sampling points is added into the consideration, and together with the central threshold, it is used as the influence factor to decide the LBP coding situation, and the directional features hidden between the neighboring points are fully utilized to further improve the accuracy of image recognition, and the experiment showed that using the PASCAL VOC gear defect dataset as the validation sample, the defect images captured in the experiment showed a 2% improvement in SVM recognition accuracy compared to traditional LBP algorithm, with a maximum recognition rate of 99.32%. The Manhattan recognition accuracy improved by 0.67% compared to traditional LBP algorithm, with a maximum recognition rate of 98.54%. The European recognition accuracy improved by 0.44% compared to traditional LBP algorithm, with a maximum recognition rate of 97.87%.