Method and apparatus of automatically recognizing objects based on artificial intelligence deep learning
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
A deep learning and automatic recognition technology, applied in the field of security inspection object recognition, can solve the problems of detection and recognition errors, low accuracy, etc., and achieve the effect of improving accuracy, reducing security inspection costs, and improving accuracy
Active Publication Date: 2018-11-13
北京迈格斯智能科技有限公司
View PDF1 Cites 22 Cited by
Summary
Abstract
Description
Claims
Application Information
AI Technical Summary
This helps you quickly interpret patents by identifying the three key elements:
Problems solved by technology
Method used
Benefits of technology
Problems solved by technology
However, in this technical solution, although the deep learning model is used to realize the automatic detection and identification of contraband, but in this solution, the X-ray machine is only set at one angle, but in view of the different angles of the items placed, There is no difference in the images obtained at the same angle for different items. For example, for a knife, if it is placed on a plane, the image taken from above will look like a knife, and when the same knife is placed vertically, The image captured above is a straight line, which is basically the same as a stick, so using the technical solution disclosed in the above patent still has the risk of detection and recognition errors, and the accuracy rate is not high
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
Click on the blue label to locate the original text in one second.
Reading with bidirectional positioning of images and text.
Smart Image
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0038] The present invention will be further described in detail below in conjunction with the accompanying drawings, so that those skilled in the art can implement it with reference to the description.
[0039] It should be understood that terms such as "having", "comprising" and "including" used herein do not exclude the presence or addition of one or more other elements or combinations thereof.
[0040] Such as figure 1 with figure 2 As shown, the present invention provides a method for automatically recognizing objects based on artificial intelligence deep learning, which mainly includes the following steps:
[0041] Step 1. The X-ray images of the items to be identified are collected by X-ray machines arranged in different directions in the item identification area;
[0042] Step 2. Input the collected X-ray images in various directions into the preset deep learning model at the same time, so as to extract the multi-dimensional data of the corresponding items to be ide...
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 a method and apparatus of automatically recognizing objects based on artificial intelligence deep learning. The method of automatically recognizing objects based on artificialintelligence deep learning includes the steps: collecting X-ray images of objects to be recognized by X-ray machines disposed in different orientations of an objection recognition area; inputting thecollected X-ray images in various orientations into a preset deep learning model to extract multi-dimensional data of the corresponding objects to be identified in the X-ray images; fusing the multi-dimensional data to generate data features corresponding to the multi-dimensional data; respectively extracting the classification features and the position features from the data features; and calculating the confidence values of the classification features, and combining the classification features in which the confidence values are greater than the preset minimum value and the corresponding position features as the recognition result to output. The method and apparatus of automatically recognizing objects based on artificial intelligence deep learning utilize the cross-imaging and preset deep learning model to synthesize multi-dimensional images into a one-way composite image, thus greatly improving the recognition rate of contraband, avoiding missed detection, and realizing full automation of security inspection.
Description
technical field [0001] The invention relates to the technical field of security inspection object recognition, in particular to a method and device for automatically recognizing objects based on deep learning of artificial intelligence. Background technique [0002] Security inspection machine, also known as security inspection instrument, including security inspection X-ray machine, luggage inspection machine, channel X-ray machine, object inspection X-ray machine, X-ray security inspection instrument, X-ray luggage inspection machine, X-ray detector, X-ray foreign object detection Machines, X-ray security inspection machines, X-ray luggage detectors, Sanpin detectors, Sanpin inspection machines, Sanpin inspection devices, and dangerous inspection devices. [0003] Security inspection machines are widely used in airports, railway stations, bus stations, government buildings, embassies, conference centers, exhibition centers, hotels, shopping malls, large-scale events, post ...
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
Application Date:The date an application was filed.
Publication Date:The date a patent or application was officially published.
First Publication Date:The earliest publication date of a patent with the same application number.
Issue Date:Publication date of the patent grant document.
PCT Entry Date:The Entry date of PCT National Phase.
Estimated Expiry Date:The statutory expiry date of a patent right according to the Patent Law, and it is the longest term of protection that the patent right can achieve without the termination of the patent right due to other reasons(Term extension factor has been taken into account ).
Invalid Date:Actual expiry date is based on effective date or publication date of legal transaction data of invalid patent.