Image description method and device, electronic equipment and storage medium
An image description and image technology, applied in the field of computer vision, can solve the problems of poor user interaction, descriptive text style and single content, and achieve the effect of improving interactivity, ensuring richness and pertinence
Pending Publication Date: 2020-12-01
IFLYTEK CO LTD
View PDF24 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] Embodiments of the present invention provide an image description method, device, electronic equipment, and storage medium to solve the problem of descriptive text generated by existing image description methods having a single style and content and poor interaction with users
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0041] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments It is a part of embodiments of the present invention, but not all embodiments. 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.
[0042] When describing images, technologies such as CNN (Convolutional Neural Networks, Convolutional Neural Networks), RNN (Recurrent Neural Networks, Recurrent Neural Networks) and Attention (attention) mechanisms are usually used in the prior art to establish description models, The features are encoded to obtain a feature vector in a fixed-dim...
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
Login to View More Abstract
Embodiments of the invention provide an image description method and device, electronic equipment and a storage medium. The method comprises the steps of determining target information in a to-be-described image, wherein the target information comprises a plurality of target objects and relationships among the target objects; based on the previous text sequence, determining attention information to be described currently from the target information, forming a current text sequence based on the attention information, wherein the previous text sequence and the current text sequence are text sequences obtained through the previous description task and the current description task respectively, and the current text sequence comprises the previous text sequence; and taking the text sequence obtained by the last description task as a description text of the to-be-described image. According to the method, the device, the electronic equipment and the storage medium provided by the embodiment of the invention, the description text obtained by image description can fit interest points and knowledge points needing to be noticed by a user, the richness and pertinence of image description are ensured, and the interactivity with the user is improved.
Description
technical field [0001] The invention relates to the technical field of computer vision, in particular to an image description method, device, electronic equipment and storage medium. Background technique [0002] Image Caption refers to the use of computer vision technology to generate descriptive text about the image content for a given image, so as to realize the conversion from image pixels to text. [0003] The descriptive text generated by the existing image description methods usually presents the same sentence pattern, resulting in poor diversity in the style and content of the generated descriptive text, and the description of the image is not rich enough to meet the interests of the user's attention. points and knowledge points. Contents of the invention [0004] Embodiments of the present invention provide an image description method, device, electronic equipment, and storage medium to solve the problem of descriptive text generated by existing image description...
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
Login to View More Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00G06K9/46
CPCG06V20/20G06V10/462
Inventor 张晋烽张启韩金金王兴宝雷琴辉王智胜王雪初
Owner IFLYTEK CO LTD