Big data image curve reverse analysis method and system
What is Al technical title?
Al technical title is built by PatSnap Al team. It summarizes the technical point description of the patent document.
An analysis method and big data technology, applied in the field of image recognition technology and text recognition, can solve the problems of inaccurate analysis, time-consuming, high labor costs, etc., and achieve the effect of speeding up the analysis speed
Inactive Publication Date: 2018-04-13
苏州灯蓝软件科技有限公司
View PDF5 Cites 6 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
For massive image data, if manual operation is used, the labor cost is high, it is too time-consuming, and the analysis is not accurate
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 1
[0042] Such as figure 1 As shown, a method for reverse analysis of a large data image curve in accordance with this embodiment includes the following steps:
[0043] S1: load the image file, read the image data, and obtain the RGB data of the image file;
[0044] S2: filter the image file, and then perform binarization operation to convert the RGB data into black and white two-color data; read the image data to obtain the RGB color of the image, filter the image to remove the background color, and use the threshold value to convert the RGB data Data converted into black and white, generally black is the curve and text, and white is the background.
[0045] S3: extract the curve in the image according to the black and white two-color data;
[0046] S4: identify the reference point coordinate data marked on the image file;
[0047] S5: select 2 reference point coordinates identified to construct coordinate registration;
[0048] S6: Transform the image curve coordinates into...
Embodiment 2
[0056] Such as figure 2 As shown, a large data image curve reverse analysis system consistent with this embodiment includes the following modules:
[0057] The image loading module is used to load image files, read image data, and obtain the RGB data of image files;
[0058]The image processing module is used to filter the image file, and then perform binarization operation to convert the RGB data into black and white two-color data; read the image data, obtain the RGB color of the image, filter the image to remove the background color, and use the threshold , convert RGB data into black and white two-color data, generally black is the curve and text, and white is the background.
[0059] The curve extraction module is used to extract the curve in the image according to the black and white two-color data;
[0060] An identification data module is used to identify the reference point coordinate data marked on the image file;
[0061] Coordinate registration module, used to ...
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 big data image curve reverse analysis method. The method comprises following steps of S1: loading an image file, reading image data and acquiring RGB data of the image file;S2: filtering the image file, carrying out binarization operation and converting the RGB data into black color and white color data; S3: extracting curves in the image according to the black color andwhite color data; S4: recognizing reference point coordinate data marked on the image file; S5: selecting recognized two reference point coordinates and constructing coordinate registering; and S6: converting the image curve coordinates into physical coordinates. The invention also discloses a big data image curve reverse analysis system. According to the invention, by use of the image recognition technology and the text recognition technology, curves on the image are automatically recognized, and then, according to coordinate information of the text recognition, coordinate registering is added to the curves, so the coordinates can be converted into the actual physical x, y coordinates according to image pixel coordinates on the curves, the analysis speed is quick and the curve coordinateanalysis is accurate.
Description
technical field [0001] The invention relates to the fields of image recognition technology and character recognition technology, in particular to a method and system for reverse analysis of big data image curves. Background technique [0002] At present, many image documents contain a large amount of curve data, and the x, y physical coordinates on the curve in the image need to be extracted, and the extracted curve coordinate data can be used for subsequent data calculation. The reverse analysis and extraction function of image curve data is often used as input data for big data calculations. [0003] The traditional image curve data extraction is to enlarge and print the image, and the staff uses a ruler to configure the xy coordinate axis on the paper image, and then manually uses the ruler to measure according to the coordinates of the points on the curve to obtain the x of the point on the curve , the y-coordinate. For massive image data, if manual operation is used, ...
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.
Login to view more 
Login to view more