Image recognition method and device, computer equipment and storage medium
A computer equipment and image recognition technology, applied in the field of image recognition, can solve the problems affecting the accuracy of synthetic images and insufficient feature richness, and achieve the effect of high feature richness and improved recognition accuracy.
Pending Publication Date: 2020-12-22
TENCENT TECH (SHENZHEN) CO LTD
View PDF11 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, the richness of features obtained by feature extraction and fusion methods in related technologies is insufficient, which affects the accuracy of synthetic images generated by replacing partial regions.
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
[0050] Reference will now be made in detail to the exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numerals in different drawings refer to the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with aspects of the present application as recited in the appended claims.
[0051] Before describing the various embodiments shown in this application, several concepts involved in this application are firstly introduced:
[0052] 1) Machine Learning (ML) is a multi-field interdisciplinary subject, involving probability theory, statistics, approximation theory, convex analysis, algorithm complexity theory and other disciplines. Specializes in the study of how c...
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
The invention discloses an image recognition method and device, computer equipment and a storage medium. The method comprises the steps that: a first feature map and a second feature map are acquiredaccording to a to-be-detected image and a first feature scale, and the first feature map is a feature map extracted from a residual image of the to-be-detected image; according to the first feature map and the second feature map, a third feature map and a fourth feature map are obtained according to a second feature scale; a feature vector is obtained according to the third feature map and the fourth feature map; and according to the feature vector, a recognition result of the to-be-detected image is obtained, the recognition result is used for indicating whether the to-be-detected image contains a replacement area. By means of the image recognition method and device, computer equipment and storage medium of the technical schemes, the recognition accuracy of a composite image generated inthe mode that a partial area is replaced can be improved.
Description
technical field [0001] The present application relates to the technical field of image recognition, in particular to an image recognition method, device, computer equipment and storage medium. Background technique [0002] With the rapid development of deep generative models, a large number of face-changing images appear in the network. These face-changing images endanger network security and violate user privacy. [0003] In related technologies, for the recognition of synthetic images (typically such as face-changing images) generated by partial region replacement, a high-frequency filter is usually used to transform the RGB image into a high-frequency space, and the RGB and high-frequency images are respectively Establish network branches, fuse high-level features at the end of the network, and identify them through the fused features. [0004] However, the richness of the features obtained by the feature extraction and fusion methods in the related art is insufficient,...
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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/168G06N3/045
Inventor 张勇罗宇辰严骏驰刘威
Owner TENCENT TECH (SHENZHEN) CO LTD