An image processing method and system
An image processing and scene image technology, applied in the field of visual inspection, can solve problems such as inability to flexibly adjust, and the algorithm recognition results are not reflected.
Active Publication Date: 2022-03-18
BEIJING RONGLIAN YITONG INFORMATION TECH CO LTD
View PDF16 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
At present, the recognition parameters of the CV model are fixed internally and cannot be adjusted flexibly. If the target size in the screen exceeds the maximum recognition pixel or does not reach the minimum recognition pixel, it will not be recognized, and will not be reflected in the algorithm recognition results
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
[0059] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.
[0060] Refer below figure 1 and image 3 An image processing method and system proposed in an embodiment of the present invention will be described.
[0061] Such as figure 1 As shown, an image processing method includes steps S1-S4:
[0062] S1: Obtain sample scene information and a sample scene image taken in the sample scene, perform model training according to the sample scene information and the sample scene image, and obtain a sample cv model; the configuration parameters of the sample cv model include the recognition range of pixels ; The recognition range includes the maximum recognition pixel and the minimum recognition pixel;
[0063] S2: Obtain the sc...
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 and system, comprising: obtaining sample scene information and sample scene images taken in the sample scene, performing model training according to the sample scene information and the sample scene image, and obtaining a sample cv model; obtaining The scene information of the scene to be recognized, and the actual scene image of the scene to be recognized is photographed; the scene information of the scene to be recognized is compared with the sample scene information, and a comparison result is obtained, and the sample cv model is calculated according to the comparison result The recognition range of the pixels is adjusted to obtain a modified cv model; the actual scene image is input into the modified cv model, and the recognition result of the actual scene image is output. Beneficial effects: the maximum recognition pixel and the minimum recognition pixel of the sample cv model are adjusted according to the scene information of the scene to be recognized and the sample scene information, so as to increase the accuracy of the final recognition result.
Description
technical field [0001] The invention belongs to the technical field of visual inspection, and in particular relates to an image processing method and system. Background technique [0002] The model algorithm will generate an image recognition model based on the model training data set. Due to the impossibility of infinitely many scenes in the training data set and the physical reasons for the imaging of the object itself, the smaller / larger the size of the target in the picture after exceeding a certain range, it can be The worse the resolution, the algorithm model will have a suitable maximum recognition pixel and minimum recognition pixel for the recognizable pixels of the target, because when the maximum recognition pixel is exceeded and the minimum recognition pixel is smaller than the minimum recognition pixel, the recognition accuracy will be greatly reduced. At present, the recognition parameters of the CV model are fixed internally and cannot be adjusted flexibly. If...
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 Patents(China)
IPC IPC(8): G06T7/00G06T7/13G06T5/00G06N20/00
CPCG06T7/0002G06T7/13G06N20/00G06T2207/10028G06T5/70
Inventor 任永建师天磊许志强孙昌勋
Owner BEIJING RONGLIAN YITONG INFORMATION TECH CO LTD