Unlock instant, AI-driven research and patent intelligence for your innovation.
Image character segmentation method, device, equipment and storage medium
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 technology of character segmentation and segmentation position, which is applied in the field of image processing, and can solve problems such as low accuracy rate, misclassification and omission, and poor character segmentation effect, so as to improve the segmentation accuracy and segmentation effect, and solve the effect of omission
Active Publication Date: 2022-05-31
SHENZHEN YIHUA COMP +2
View PDF13 Cites 0 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, the existing image character recognition methods usually only segment characters of a uniform size in the image. When the image data contains characters of different sizes, misclassification and omission often occur, and the character segmentation effect is poor and low accuracy
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
[0043] Wherein, the preset segmentation conditions can be set according to the number and value of character points and prior knowledge of characters.
[0045] Step 150, determine the upper boundary and the lower boundary of the single character obtained by column division according to the search rule.
Embodiment 2
[0055] Wherein, the first preset value may be the same as the second preset value, and may also be different from the second preset value. optional, section
[0056] Specifically, when judging the setting area of one column of the character string image to be divided, it can be set from the column.
[0057] Step 240, if the number and
[0059] In the embodiment of the present invention, after the valid position determination in the setting area of all the columns is completed, there may be
[0067] Wherein, the second target processing area is an area including the lower boundary of the character string in the character string image to be segmented. the first
[0069] Wherein, the seventh preset value may be the same as the eighth preset value, and may also be different from the eighth preset value. optional, section
[0070] Specifically, when judging one of the setting areas of the second target processing area, the setting area can be set from the column.
[0075] Step 21...
Embodiment 3
[0084] In step 341, the position where the sum of the number of each column character point is 0 is determined as the first candidate segmentation position.
[0091] Step 350, according to the search rule, determine the upper boundary and lower boundary of the single character obtained by column division.
[0095] Step 352, taking the row and the largest position as the reference position.
[0096] Correspondingly, the row and the largest position can be used as the reference position. It should be noted that in order to ensure the reference position
[0102] Wherein, the preset requirement may be that the variance is less than a certain threshold. The optimal split position set includes a variance that meets the requirements
[0103] In this embodiment of the present invention, after the optimal segmentation position set is obtained, each
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 embodiment of the present invention discloses an image character segmentation method, device, equipment, and storage medium. The method includes: dividing the character string image to be segmented into equal-area set areas, and determining the number of character points included in each set area. Quantity and value; According to the quantity and value and the upper boundary determination condition, determine the upper boundary of the character string in the character string image to be divided; According to the upper boundary and the lower boundary determination condition, determine the lower boundary of the character string in the character string image to be divided; Within the line range corresponding to the upper boundary and the lower boundary, determine the character segmentation position according to the preset segmentation condition, and perform column-wise segmentation on the character string in the character string image to be segmented according to the character segmentation position; determine the single column-wise segmentation according to the search rule The upper and lower boundaries of the characters solve the problems of omission, misclassification and poor segmentation effect when the existing character segmentation methods segment characters of different sizes, thereby improving the segmentation accuracy and segmentation effect of characters of different sizes.
Description
A kind of image character segmentation method, device, equipment and storage medium technical field Embodiments of the present invention relate to the technical field of image processing, and in particular, to a method, device, and device for segmenting image characters. equipment and storage media. Background technique [0002] With the development of image processing technology, users often need to extract the character information contained in the image and For identification, for example, when identifying the authenticity of banknotes, it is necessary to extract the serial number information corresponding to the banknotes. However, existing glyph recognition Other methods, usually only the characters of the same size in the image are segmented, when the image data contains characters of different sizes, Misclassification and omission often occur, and the segmentation effect of characters is poor and the accuracy rate is low. SUMMARY OF THE INVENTION Embodiment...
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