Method for automatically generating thumbnail by use of deep neutral network

Abstract

The invention provides a method for automatically generating a thumbnail by use of a deep neutral network. The main content comprises the followings: data set training, boundary frame prediction, image and thumbnail size pair inputting, model training, quick automatic thumbnail generation FATG implementation. The processes are as follows: first training a data base established by use of internet pictures, inputting an original picture and a target thumbnail size, predicting a boundary frame position to determine a region containing important information in combination with a RPN (region proposal network) and R-FCN (region-based full convolution network by use of a FATG model, and producing a boundary frame with aspect ratio equal to the target thumbnail size, extending until to touch the boundary, namely, generating the thumbnail with the required size. By use of the automatic generating provided by the invention, the problems that the generation of the thumbnail is time-consuming and the important information is easy to lose are solved, the thumbnail under the required size can be acquired faster and more accurate, and the picture thumbnail is more precise and real-time to facilitate the daily browsing and image uploading of the people.

Description

technical field [0001] The invention relates to the field of thumbnail generation, in particular to a method for automatically generating thumbnails using a deep neural network. Background technique [0002] Thumbnails are used for easy browsing of image collections, economical use of display space, and reduced transfer times. A thumbnail is a smaller version of the original image, which means it still effectively depicts the original image. Social media sites such as WeChat and Weibo publish content from a wide range of sources, but images must be displayed at a fixed resolution. An ordinary article on WeChat subscription contains dozens of images. To ensure the display effect, it is essentially a thumbnail of a larger image. Therefore, it is very important to ensure that each thumbnail shows the most useful information in the original image. Since thumbnails are ubiquitous and manual generation of thumbnails is very time-consuming, automatic generation of thumbnails has...

AI Technical Summary

Problems solved by technology

[0005] For problems such as time-consuming thumbnail generation and easy loss of important information, the object of the present invention is to provide a method for automatically generating thumbnails using a deep neural network, using Internet pictures to establish a database for training, using a FATG model, including RPN (area proposed network) and R-FCN (region-based fully convolutional network) to predict the optimal bounding box, making image thumbnails more accurate and real-time, and convenient for people to browse and upload images daily

Images