Data backflow method for improving precision of cv algorithm
An algorithm and data technology, applied in the field of data reflow to improve the accuracy of cv algorithm, can solve problems such as not covering all scenarios, using wrongly identified images, and ineffective algorithm optimization.
Pending Publication Date: 2020-05-19
BEIJING RONGLIAN YITONG INFORMATION TECH CO LTD
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, the cv algorithm will use the corresponding training data set to train the algorithm model during model training. When the model training is mature, it can improve the detection accuracy of scenes similar to the training data set. However, in practical applications, these training data The set cannot cover all the scenes, which may lead to a decrease in the recognition effect of the scene inconsistent with the training data set. In addition, even in the same scene, if there is light interference, the target distance is too far, and the background color is close to the detection target color value Other factors will also affect the accuracy of recognition. It can be seen that the wrong image identified by the cv algorithm has a high value for the directional optimization of the cv algorithm, which can achieve a higher fitting detection effect of the cv algorithm for more scenes
However, the existing retrieval interface generally displays the results of the detected images and the captured information, and only allows the user to delete the wrongly recognized images, which does not make effective use of the wrongly recognized images, and even if it is Using these wrongly identified images can only be processed by screenshots or downloaded, and then sent to the algorithm maintenance personnel for optimization. This optimization method is not only inefficient, but also its optimization effect on the algorithm is not obvious.
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
[0069] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without creative efforts fall within the protection scope of the present invention.
[0070] refer to figure 1 , is a schematic flowchart of a data reflow method for improving the accuracy of the cv algorithm provided by an embodiment of the present invention. The data return method for improving the accuracy of the cv algorithm includes the following steps:
[0071] Step S1, performing screening processing on predetermined conditions for the image detection results of the cv algorithm, so as to obtain a list of corresponding image detection result...
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 provides a data backflow method for improving the precision of a cv algorithm. According to the data backflow method for improving the precision of the cv algorithm, a user is allowed tocarry out label processing and storage processing on an image which is wrongly identified; therefore, transferable editing can be carried out on an image with an identification error; therefore, subsequent high-efficiency classification processing and data backflow processing are carried out on the image with the identification error conveniently; according to the data backflow method for improving the precision of the cv algorithm, directional optimization processing can be carried out on the cv algorithm by utilizing the image with wrong identification after backflow, so that the detectionaccuracy of the cv algorithm and the applicability to different scenes are improved.
Description
technical field [0001] The invention relates to the technical field of image processing, in particular to a data return method for improving the accuracy of a cv algorithm. Background technique [0002] At present, the cv algorithm will use the corresponding training data set to train the algorithm model during model training. When the model training is mature, it can improve the detection accuracy of scenes similar to the training data set. However, in practical applications, these training data The set cannot cover all the scenes, which may lead to a decrease in the recognition effect of the scene inconsistent with the training data set. In addition, even in the same scene, if there is light interference, the target distance is too far, and the background color is close to the detection target color value And other factors will also affect the accuracy of recognition. It can be seen that the wrong image identified by the cv algorithm has a high value for the directional op...
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): G06F16/51G06F16/583G06F16/55G06K9/62
CPCG06F16/51G06F16/583G06F16/55G06F18/24
Inventor任永建孙昌勋许志强
OwnerBEIJING RONGLIAN YITONG INFORMATION TECH CO LTD