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

Image classification method and device and terminal

A classification method and image technology, applied in the field of image processing, can solve problems such as poor accuracy of image classification results, and achieve the effect of improving accuracy

Active Publication Date: 2018-07-06
BEIJING DAJIA INTERNET INFORMATION TECH CO LTD
View PDF9 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] Embodiments of the present invention provide an image classification method, device, and terminal to solve the problem of poor accuracy of image classification results in the prior art

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
  • Image classification method and device and terminal
  • Image classification method and device and terminal
  • Image classification method and device and terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0025] refer to figure 1 , shows a flow chart of steps of an image classification method according to Embodiment 1 of the present invention.

[0026] The image classification method of the embodiment of the present invention may include the following steps:

[0027] Step 101: Determine the image feature vector corresponding to the image through a convolutional neural network.

[0028] Wherein, the image corresponds to text description information. The text description information may be the text description information uploaded by the user after uploading the image, or the text description information included in the image.

[0029] The image in this embodiment of the present invention may be a single frame image in a video, or just a multimedia image. An image is input into the convolutional neural network, and after the convolution layer or the pooling layer, the image feature map vector will be obtained. The image feature vector contains multiple points, and each point c...

Embodiment 2

[0039] refer to figure 2 , shows a flow chart of steps of an image classification method according to Embodiment 2 of the present invention.

[0040] The image classification method in the embodiment of the present invention may specifically include the following steps:

[0041] Step 201: Determine the image feature vector corresponding to the image through a convolutional neural network.

[0042] The image corresponds to text description information. The text description information may be the text description information uploaded by the user after uploading the image, or the text description information included in the image.

[0043] For a specific manner of determining an image feature vector corresponding to an image through a convolutional neural network, reference may be made to existing related technologies, which are not specifically limited in this embodiment of the present invention.

[0044] Step 202: Remove stop words in the text description information to obt...

Embodiment 3

[0067] refer to image 3 , shows a structural block diagram of an image classification apparatus according to Embodiment 3 of the present invention.

[0068] The image classification device in the embodiment of the present invention may include: a determination module 301 configured to determine an image feature vector corresponding to an image through a convolutional neural network; wherein, the image corresponds to text description information; a vector generation module 302 configured to The text description information is processed by a bidirectional cyclic neural network to obtain a text feature vector; the fusion module 303 is configured to fuse the image feature vector and text feature vector to obtain a target feature vector; the calling module 304 is configured to The deep neural network is called, and the classification corresponding to the image is determined by the deep neural network according to the target feature vector.

[0069] Preferably, the vector generati...

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 invention provides an image classification method and device and a terminal. The method includes: determining an image feature vector, which corresponds to an image, through a convolutional neural network, wherein the image corresponds to text description information; processing the text description information through a bidirectional recurrent neural network to obtain a textfeature vector; fusing the image feature vector and the text feature vector to obtain a target feature vector; and invoking a deep neural network, and determining a class, which corresponds to the image, by the deep neural network according to the target feature vector. Through the image classification scheme provided by the embodiment of the invention, accuracy of image classification can be improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image classification method, device and terminal. Background technique [0002] Deep learning has been widely used in video images, speech recognition, natural language processing and other related fields. As an important branch of deep learning, convolutional neural network has greatly improved the accuracy of prediction results obtained in computer vision tasks such as target detection and classification due to its strong fitting ability and end-to-end global optimization ability. [0003] At present, when classifying images, according to the characteristics of the images themselves, they are matched under a predetermined label system to obtain the corresponding tags of the images, and the classification to which the images belong is determined according to the tags, and the accuracy of the classification results obtained is poor. In a practical application...

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 Applications(China)
IPC IPC(8): G06K9/62
CPCG06F18/24G06F18/253
Inventor 张志伟杨帆
Owner BEIJING DAJIA INTERNET INFORMATION TECH CO LTD