Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Deep learning model-based image Chinese description method

A deep learning and image description technology, applied in biological neural network models, special data processing applications, instruments, etc., can solve problems such as English description of content that cannot be imaged, and achieve the effect of reducing semantic connections, improving accuracy, and reducing parameters.

Active Publication Date: 2018-05-08
HARBIN UNIV OF SCI & TECH
View PDF7 Cites 41 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Secondly, in the current English text description methods, most of these methods are based on codec rules, and the limitation of this method is that it cannot accurately and completely describe the content of the image in English for complex scenes.

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
  • Deep learning model-based image Chinese description method
  • Deep learning model-based image Chinese description method
  • Deep learning model-based image Chinese description method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0052] The specific embodiments of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0053] A Chinese image description method based on a deep learning model, as shown in 1, includes the following steps:

[0054] Step a, prepare the ImageNet image data set and the AI ​​Challenger image Chinese description data set;

[0055] Step b, using DCNN to pre-train the ImageNet image data set to obtain a DCNN pre-training model;

[0056] Step c, the DCNN pre-training model performs image feature extraction and image feature mapping on the AI ​​Challenger image Chinese description dataset, and transmits it to the GRU threshold recurrent network recurrent neural network;

[0057] Step d, building a word encoding matrix for the AI ​​Challenger image annotation set in the AI ​​Challenger image Chinese description data set, including text preprocessing and word segmentation, establishing a dictionary, and establishing a word ind...

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 invention discloses a deep learning model-based image Chinese description method and belongs to the field of computer vision and natural language processing. The method comprises the steps of preparing an ImageNet image data set and an AI Challenger image Chinese description data set; pre-training the ImageNet image data set by utilizing a DCNN to obtain a pre-trained DCNN model; performing image feature extraction and image feature mapping on the AI Challenger image Chinese description data set, and transmitting image features to a GRU threshold recursive network recurrent neural network;performing word coding matrix construction on an AI Challenger image mark set in the AI Challenger image Chinese description data set; extracting word embedding features by utilizing an NNLM, and finishing text feature mapping; taking the GRU threshold recursive network recurrent neural network as a language generation model, and finishing image description model building; and generating a Chinese description statement. According to the method, the blank of image Chinese description is filled up; a function of automatically generating the image Chinese description is realized; the accuracy ofdescription contents is well improved; and a foundation is laid for development of Chinese NLP and computer vision.

Description

technical field [0001] A Chinese image description method based on a deep learning model of the present invention belongs to the field of computer vision and natural language processing. Background technique [0002] With the development of multimedia and the expansion of the Internet scale, the popularization of hardware devices such as mobile phones and tablets has made the image resources in the Internet grow exponentially. This brings great difficulties to users in image retrieval on the Internet, and it has become impossible to manually label these images. In order to ensure that images can be accurately retrieved by users within a limited time, This needs to enable the machine to automatically understand the content in the image and automatically label the image. Thereby, it is convenient for users to search. [0003] The current image description methods are all based on English text description of images. It is an urgent task to design a Chinese semantic understand...

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
IPC IPC(8): G06F17/27G06F17/30G06N3/04
CPCG06F16/5838G06F40/242G06F40/289G06N3/045
Inventor 王玉静吕世伟谢金宝殷楠楠谢桂芬李佰蔚
Owner HARBIN UNIV OF SCI & TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products