Unlock instant, AI-driven research and patent intelligence for your innovation.

Automatic Generation Method of Image Annotation Sentence

An image annotation and automatic generation technology, applied in biological neural network models, instruments, calculations, etc., can solve the problems of unnatural and unrich image annotation sentences

Active Publication Date: 2021-04-16
NAT UNIV OF DEFENSE TECH
View PDF4 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] However, the existing models often select the area to focus on in the image based on certain weights, and these weights are often only guided by the state of the hidden layer of the neural network in the decoder, local and global information of the image, and generate Image annotation sentences are often unnatural and not rich

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Automatic Generation Method of Image Annotation Sentence
  • Automatic Generation Method of Image Annotation Sentence
  • Automatic Generation Method of Image Annotation Sentence

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0016] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.

[0017] Such as figure 1 As shown, a method 100 for automatically generating image tagging sentences provided by an embodiment of the present invention mainly includes:

[0018] Step S110: Perform feature extraction on a given image to obtain image local features and image global features. Specifically, for example, feature extraction is performed on the given image by CNN (Convolutional Neural Network) to obtain the image local features and the image global featur...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The embodiment of the present invention discloses a method for automatically generating image annotation sentences, including: performing feature extraction on a given image to obtain image local features and image global features; finding multiple nearest neighbor training images in the training data set; obtaining multiple annotations sentence; converting the tagging sentence corresponding to the maximum average similarity to obtain a reference tagging sentence vector; initializing the hidden layer state of the previous time step; and cyclically generating image tagging sentences including a plurality of image tagging words. The embodiment of the present invention effectively improves the quality of automatically generated image annotation sentences, and the generated image annotation sentences are more in line with the standard of human speech.

Description

technical field [0001] The invention relates to a typical combined application of computer vision and natural language processing—the technical field of automatic generation of image annotations, in particular to a method for automatically generating image annotation sentences. Background technique [0002] The challenge of automatic image captioning (also known as image text or image captioning) generation (Image captioning) is how to design a good model that can make full use of image information and generate more rich image descriptions similar to human language. Generating a meaningful description requires not only the algorithm to identify the objects in the image, but also the algorithm to identify the relationship between the attributes and activities of the objects, and then obtain semantic information through natural language description. [0003] With the widespread use of camera-capable mobile smart terminals and the rapid development of the Internet, multi-modal ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06K9/62G06N3/04
CPCG06N3/049G06V10/757G06N3/045G06F18/214
Inventor 白亮刘爽王昊冉郭金林郭延明
Owner NAT UNIV OF DEFENSE TECH