Visual saliency detection method based on semantic enhanced convolutional neural network

Abstract

The invention discloses a visual saliency detection method based on a semantic enhanced convolutional neural network, and the method comprises the steps: improving a classic model VGG16, introducing aconvolution layer to replace a full connection layer, and better storing the detail information of an image; and adding a BN layer behind the convolution layer to accelerate the training speed of thenetwork, and adding a dropout layer behind the added convolution layer to solve the over-fitting problem of the network. And an SENet network unit is embedded after the final convolution layer to further improve the semantics of the network performance enhancement features. According to the method, the problem that deep features of the image cannot be extracted by a traditional method can be solved, detail information of the image can be enhanced, and loss of main feature information of the image and interference of noise in network propagation can be reduced by performing self-adaptive weighting on the extracted features. According to the invention, the visual saliency map with more accurate target area and less noise can be obtained.

Description

technical field [0001] The invention belongs to the technical field of visual saliency, and in particular relates to the design of a visual saliency detection method based on a semantically enhanced convolutional neural network. Background technique [0002] In recent years, with the continuous improvement of hardware computing capabilities, deep learning technology has been widely used in the field of computer vision, and has played an important role in various subdivided fields. Compared with various traditional algorithms, deep learning technology does not require too many cumbersome operations such as manual feature extraction and manual model building. extract. In the field of visual saliency, traditional methods often extract effective features that have been verified by experiments, and perform calculations at different scales, and then fuse the feature maps to obtain the corresponding saliency maps. However, after using deep learning technology, the neural network ...

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to solve the problem that the existing image saliency detection and calculation methods using convolutional neural network cannot extract the deep features of the image, and propose a visual saliency detection based on semantically enhanced convolutional neural network method, which can enhance the detailed information of the image and adaptively weight the extracted features, thereby reducing the loss of the main feature information of the image and the interference of noise in the network transmission

Images