Image recognition method and image recognition device
An image recognition and image technology, applied in the field of image recognition, can solve the problems of missed detection or wrong detection of dangerous goods or smuggled goods, inability to accurately identify dangerous goods or smuggled goods, etc.
Active Publication Date: 2017-06-20
NEUSOFT CORP
View PDF18 Cites 16 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] However, since the existing method is manually operated, it is inevitable to have the problem of missed detection or wrong detection when identifying dangerous goods or smuggled goods, so that dangerous goods or smuggled goods cannot be accurately identified
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
[0030] Specific embodiments of the present disclosure will be described in detail below in conjunction with the accompanying drawings. It should be understood that the specific embodiments described here are only used to illustrate and explain the present disclosure, and are not intended to limit the present disclosure.
[0031] The embodiments of the present disclosure can be applied to security inspection scenarios. In this scenario, when a passenger's luggage or package is undergoing security inspection, the security inspection device acquires an image of the luggage or package through X-rays, thereby identifying dangerous items and smuggled items through the acquired image. ; The present disclosure obtains multiple rotated images at different rotation angles by rotating the acquired images, and recognizes the items in passenger luggage or packages according to the obtained multiple rotated images, so that the rotated images at different angles can accurately identify Ident...
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 relates to an image recognition method and an image recognition device. The method comprises steps: the image of a to-be-recognized article is acquired; along the center of the article image, the article image is rotated according to multiple rotation angles to obtain multiple rotation images; through a preset classification model, a first image marker and the confidence corresponding to the first image marker are determined from the multiple rotation images, wherein the first image marker is used for marking the image of the to-be-recognized article belonging to the target class in the multiple rotation images, and the confidence is used for representing the confidence of the to-be-recognized article marked by the first image marker belonging to the target class; and according to the confidence and the first image marker, a target image marker is determined in the article image, wherein the target image marker is used for marking the image of the to-be-recognized article belonging to the target class in the article image.
Description
technical field [0001] The present disclosure relates to the field of image processing, and in particular, to an image recognition method and device. Background technique [0002] With the development of the economy, there are more and more passengers and commodities going to and from trade ports, railway stations, airports and other customs supervision areas, and the dangerous and smuggled items hidden in passenger luggage not only seriously threaten the safety of passengers' lives and property , endangering national security and interests. [0003] At present, the domestic security inspection system mainly relies on the identification of security personnel through human eyes. When passengers' luggage or packages pass through the conveyor belt or security gate, the image scanned by X-rays will appear on the display screen connected to the equipment. Security personnel identify dangerous or smuggled items by observing images and color blocks on the screen. [0004] However...
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): G06K9/00G06K9/32
CPCG06V20/10G06V10/242
Inventor 邹博齐智峰刘玉洁周玲武
Owner NEUSOFT CORP