ABSTRACT Obtaining real-time, objective, and high-precision distribution information of surface cracks in mining areas is the first task for studying the development regularity of surface cracks and evaluating their risk. However, the complex surface environment causes low precision of crack extraction in the existing unmanned aerial vehicle (UAV) image methods. Therefore, we propose an extraction method for surface cracks from UAV sub-images after cutting and a new evaluation index of APS (Accuracy-Precision-Sensitivity). First, the UAV image was divided into sub-images with unit sizes of 50, 100, and 200, and the bare ground (BG) and vegetation (VT) datasets based on background characteristics were built. Then, we used the five crack extraction methods improved and proposed to process the datasets. Finally, this study determined the optimal unit size to extract the cracks and the optimal method for a certain size by comparison. The results showed that the extraction method based on the unit method was better than the complete UAV image, and the crack extraction effect of the BG dataset was significantly better than that of the VT dataset. The APS index, which comprehensively considers the accuracy, precision, and sensitivity, is obviously more reasonable than the accuracy index for evaluating crack extraction methods. Moreover, the smaller the unit size, the better the effect of crack extraction. The Hue-Saturation-Value threshold segmentation method had the best extraction effect when the size was small, and the deep learning method was the best when the size was large. We proved that the proposed method can achieve higher-precision crack extraction from UAV images and can also support data calculation in crack feature extraction.