Image processing method and system
An image processing and image technology, applied in the field of image recognition, can solve problems such as large hardware dependence, user identification, and inability to solve time span user identification well, so as to improve search efficiency and save storage space
Pending Publication Date: 2021-09-28
HUAWEI TECH CO LTD
View PDF0 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
However, these methods still rely heavily on hardware, cannot solve user identification in the case of a large time span, and cannot be used when the user is wearing accessories or the face is not facing the camera (in the "frontal" state) for user identification
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
[0034] Embodiments of the present application provide an image processing method and system, which can perform user identification quickly and accurately, and still have a high degree of accurate identification even when the time span of use is large.
[0035] see figure 1 , which shows an image processing system 100 provided by some embodiments of the present application. The system 100 includes: a camera device 101 , a processing device 102 , and a storage device 103 . Wherein, the processing device 102 includes a device or a virtual machine with data processing capabilities, such as but not limited to a central processing unit (CPU: Central Process Unit), an image processor (GPU: Graphic Process Unit), a field programmable gate array (FPGA: Field Programmable GateArray), System on Chip (SoC: Sysem on Chip), Application Specific Integrated Circuit (ASIC: Application Specific Integrated Circuit) or their combination, or a virtual machine built on the cloud server. The camera...
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 processing method. The method comprises the following steps: acquiring a first image; obtaining a template image, wherein the template image has a life value, and the life value is used for measuring whether the template image is valid or not; and comparing the first image with the template image, if the first image is successfully matched with the template image, storing the first image as the template image in a template library, and deleting the template image of which the life value is smaller than a set threshold in the template library. According to the method provided by the embodiment of the invention, the template library is updated when the image is matched each time, and the template image with the life value smaller than the set threshold value in the template library is deleted, so that the template image is kept iteratively updated, and the accuracy of image recognition under a long time span can be realized.
Description
technical field [0001] The present application relates to an image processing technology, and more specifically, to an image recognition technology. Background technique [0002] With the development of informatization and intelligence, more and more devices (such as mobile phones, IoT (Internet of Things), cars, etc.) are equipped with the function of identifying the user's identity. Due to its non-contact and natural nature, face recognition is widely used in fields such as mobile phones, IoT (Internet of Things), and automobiles. The current face recognition generally compares the face image frame obtained by the user through the camera with the face template stored in the system (the face image template obtained when the user first registers) and judges whether they match. However, this solution often leads to recognition rejection when the user has a long service life span and wears accessories (such as hats, masks, scarves, glasses, etc.). [0003] In the automotive ...
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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/241G06V40/161G06V40/172G06V10/82G06V10/454G06N3/0464G06N3/09G06V10/751
Inventor 黄晓林黄为徐文康张峻豪
Owner HUAWEI TECH CO LTD