Attribute recognition device and method and storage medium
An attribute recognition and attribute technology, applied in the field of image processing, can solve the problems of time-consuming, long-term, not considering the correlation and mutual influence of recognition operations, and achieve the effect of reducing redundant operations and time-consuming
Pending Publication Date: 2020-01-14
CANON KK
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, the scene recognition operation and the character attribute recognition operation performed by the two neural networks are independent of each other, and the result of the scene recognition operation is only used to select a suitable neural network for the character attribute recognition operation. The corresponding identification operation does not take into account the possible correlation and mutual influence between the two identification operations, so that the entire identification process takes a long time
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
[0019] Exemplary embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted that the following description is merely illustrative and exemplary in nature, and is in no way intended to limit the invention and its application or uses. Relative arrangements of components and steps, numerical expressions and numerical values set forth in the embodiments do not limit the scope of the present invention unless specifically stated otherwise. Additionally, techniques, methods and devices known to those skilled in the art may not be discussed in detail, but where appropriate should be a part of this description.
[0020] Note that like reference numerals and letters refer to like items in the drawings, therefore, once an item is defined in one figure, it need not be discussed in the following figures.
[0021] For the recognition of object attributes in different scenes (for example, character attribute recog...
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 attribute recognition device and method and a storage medium. The attribute recognition device comprises a unit for extracting a first feature from an image by using a feature extraction neural network; a unit for recognizing a first attribute of the object in the image on the basis of the first feature by using a first recognition neural network; and a unit for recognizing at least one second attribute of the object on the basis of the first feature by using a second recognition neural network, one second recognition neural network candidate being determined from among a plurality of second recognition neural network candidates on the basis of the first attribute as the second recognition neural network. According to the invention, the time consumed by the wholeidentification processing can be greatly reduced.
Description
technical field [0001] The present invention relates to image processing, and more particularly to eg attribute recognition. Background technique [0002] Since person attributes can usually describe a person's appearance and / or body shape, person attribute recognition (especially, multi-task person attribute recognition) is usually used for monitoring processes such as crowd counting and identity verification. Among them, the appearance includes, for example, the person's age, the person's gender, the person's race, the person's hair color, whether the person wears glasses, whether the person wears a mask, etc., and the body shape includes, for example, the person's height, the person's weight, and the clothes worn by the person , Whether the character is carrying a bag, whether the character is pulling a suitcase, etc. Among them, the multi-task character attribute recognition means to recognize multiple attributes of a person at the same time. However, in the actual mon...
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 IPC IPC(8): G06K9/62G06K9/46
CPCG06V10/462G06F18/241G06V10/82G06N3/084G06V40/161G06V10/809G06N3/045G06F18/254G06N20/20G06F18/2155G06F18/2415
Inventor 李岩黄耀海黄星奕
Owner CANON KK