Abstract: For the severe distortion problem of fish-eye lens images, a correction algorithm based on circle segmentation approach was proposed. The circular structure of the fish-eye image features is extensively used in the algorithm and the image is split into concentric circles, then the function method is used to adjust image distortion. A tuning coefficient is introduced to make the algorithm more flexible. The distance between the fish-eye lens and the actual object is considered to adjust the size of tuning coefficient such that a better corrected image is obtained. Matlab experimental results show that the algorithm can achieve satisfactory adjustment results and the calculation of the algorithm takes less time, so that it can be applied to real-time monitoring systems.