A Fusion Model for Saliency Detection Based on Semantic Soft Segmentation

Abstract

With the rapid development of neural networks in recent years, saliency detection based on deep learning has made great breakthroughs. Most deep saliency detection algorithms are based on convolutional neural networks, which still have great room for improvement in the edge accuracy of salient objects recognition, which may lead to fuzzy results in practical applications such as image matting. In order to improve the accuracy of detection, a saliency detection model based on semantic soft segmentation is proposed in this paper. Firstly, the semantic segmentation module combines spectral extinction and residual network model to obtain low-level color features and high-level semantic features, which can clearly segment all kinds of objects in the image. Then, the saliency detection module locates the position and contour of the main body of the object, and the edge accurate results are obtained after the processing of the two modules. Finally, compared with the other 11 algorithms on the DUTS-TEST data set, the weighted F-measure value of the proposed algorithm ranked first, which was 5.8% higher than the original saliency detection algorithm, and the accuracy was significantly improved.