Abstract:Aiming at the difficulty of detecting weak and small targets with low contrast and low signal to noise ratio in traditional detection methods,a detecting method based on gradient feature extraction is proposed.First,with the isotropy of targets and the distribution characteristics in the gradient,two directional gradient features are extracted.Then,through the improved local contrast algorithm,the similarity of the two directional gradient features was suppressed respectively,and the two directional gradient features are merged to enhance the target while suppressing the background.Finally,the result image is segmented by adaptive threshold to obtain the final detection result.The experimental result shows that the proposed algorithm can not only effectively detect targets with extremely low signal to noise ratio and contrast,but also has a good suppression effect on complex edge scenes.It is superior to other algorithms in terms of signal to noise ratio,background suppression factor and detection rate.