Image Retrieval Method Based on Improved Frequency-turned Algorithm
Guannan Deng, Can Cui, Zhe Ma, Mei Zhang · 2022
In order to solve the problem that the salient area is not prominent enough and redundant information exists in the image retrieval algorithm based on salient target detection, this paper proposes an improved FT algorithm using the single-threshold segmentation method and the multi-threshold segmentation method. This method can remove noise information, improve the saliency map effect, and enhance the weight of salient regions. The experimental results show that the method proposed in this paper can improve the accuracy of image retrieval, and has certain theoretical and practical significance.