Global-local optimization model based on multistage convolution neural network and significant detection algorithm

Abstract

The invention provides a significant detection algorithm based on a multistage convolution neural network. The algorithm comprises the following steps of using a global estimation model of a large receptive field to carry out global significance estimation; during a global estimation model training process, using a full connection layer as an output layer to train and initialize parts of convolution layer parameters; using a plurality of alternative convolution layers and liter sampling layers to replace the full connection layer and training and acquiring an optimal global significance estimation graph; using a local convolution neural network with a small receptive field and a large output picture size to fuse global and local information to acquire a high quality significance graph. Through processing of the local convolution neural network, an original image is served as input of the model. A final output result possesses a same size with an original input image and is clear. By using the significant detection algorithm based on the multistage convolution neural network, compared to a traditional method, high accuracy is possessed; a significant object can be accurately found and simultaneously a contour is clear.

Description

【Technical field】 [0001] The invention relates to a method for visual saliency detection in natural images based on a deep convolutional neural network, which is applied to the detection of salient target areas under complex backgrounds. 【Background technique】 [0002] Human vision can quickly find salient objects in the surrounding environment, ignore some information that is not of interest to humans, and focus on important parts of visual images, which can avoid the brain from processing complicated and useless information. Visual saliency detection is to simulate the rapid human perception of environmental behavior. [0003] With the popularization of various digital devices and the rapid development of the Internet, there are more and more pictures and video data. Similar to human vision, computers can extract saliency information in pictures through saliency detection of images or videos, and quickly locate areas in images that need to be processed. Through visual sa...

AI Technical Summary

Problems solved by technology

The effect and operation speed of this method depend greatly on the segmentation algorithm. On the one hand, the boundary division of salient objects depends entirely on the segmentation accuracy of the segmentation algorithm. On the other hand, the running speed is completely limited by the speed of the segmentation algorithm.

Images