CN116704517A - Character recognition method in therapy control system display, electronic equipment and storage medium - Google Patents

Character recognition method in therapy control system display, electronic equipment and storage medium Download PDF

Info

Publication number
CN116704517A
CN116704517A CN202310669387.9A CN202310669387A CN116704517A CN 116704517 A CN116704517 A CN 116704517A CN 202310669387 A CN202310669387 A CN 202310669387A CN 116704517 A CN116704517 A CN 116704517A
Authority
CN
China
Prior art keywords
character
character image
image block
block
blocks
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202310669387.9A
Other languages
Chinese (zh)
Inventor
菅影超
王虹
马善达
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Ruier Medical Science & Technology Co ltd
Original Assignee
Jiangsu Ruier Medical Science & Technology Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jiangsu Ruier Medical Science & Technology Co ltd filed Critical Jiangsu Ruier Medical Science & Technology Co ltd
Priority to CN202310669387.9A priority Critical patent/CN116704517A/en
Publication of CN116704517A publication Critical patent/CN116704517A/en
Pending legal-status Critical Current

Links

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/16—Image preprocessing
    • G06V30/162—Quantising the image signal
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/14—Image acquisition
    • G06V30/148—Segmentation of character regions
    • G06V30/15—Cutting or merging image elements, e.g. region growing, watershed or clustering-based techniques
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/18—Extraction of features or characteristics of the image
    • G06V30/1801—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections
    • G06V30/18076—Detecting partial patterns, e.g. edges or contours, or configurations, e.g. loops, corners, strokes or intersections by analysing connectivity, e.g. edge linking, connected component analysis or slices
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
    • G06V30/10—Character recognition
    • G06V30/19—Recognition using electronic means
    • G06V30/19007—Matching; Proximity measures
    • G06V30/19013—Comparing pixel values or logical combinations thereof, or feature values having positional relevance, e.g. template matching

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Character Input (AREA)

Abstract

The invention provides a character recognition method, electronic equipment and storage medium in a display of a treatment control system, wherein the character recognition method comprises the following steps: acquiring an image in a therapy control system display; acquiring an image to be recognized comprising characters; performing binarization processing on the image to be identified; removing an edge blank area of the binarized image; performing character segmentation on the binarized image to obtain a plurality of first character image blocks, wherein the first character image blocks are single character image blocks or adhesion character image blocks; confirming the category of the first character image block, and performing the following processing: the first character image block is a single character image block, and then the single character in the single character image block is identified by matching with the template character image; the first character image block is a sticky character image block, and the sticky character image block is subjected to anti-sticky treatment so as to identify each character in the sticky character image block. The invention enables automatic identification of planning information in a treatment control system display.

Description

Character recognition method in therapy control system display, electronic equipment and storage medium
Technical Field
The present invention relates to the field of medical treatment, and in particular, to a character recognition method, an electronic device, and a storage medium in a display of a therapy control system.
Background
Before radiation treatment, the planning information of the patient displayed in the display of the treatment control system needs to be read, so that the information accuracy of the treatment patient is ensured.
At present, the plan information in the display of the treatment control system is generally identified by adopting a manual reading mode, and the situation of identification errors is easy to occur due to human eye fatigue.
Therefore, it is necessary to implement automatic recognition of the plan information by using an image automatic recognition technology, however, the plan information has 26 english letters in case of each, and also has special characters, and the difficulty of recognition is high. In addition, sticky characters may exist in the planning information, so that the difficulty of automatic identification is further increased. For the above reasons, the known image recognition method is adopted to recognize the plan information, and the error rate is high.
Disclosure of Invention
In order to solve the above technical problem, the present invention first provides a character recognition method in a therapy control system display, which can implement automatic recognition of planning information in the therapy control system display. The detailed technical scheme of the character recognition method of the invention is as follows:
a method of character recognition in a therapy control system display, comprising:
acquiring an image in a therapy control system display;
acquiring an image to be recognized comprising characters from a predetermined area of the image;
performing binarization processing on the image to be identified to obtain a binarized image;
removing an edge blank area of the binarized image;
performing character segmentation on the binarized image with the edge blank area removed to obtain a plurality of first character image blocks, wherein the first character image blocks are single character image blocks or adhesion character image blocks;
confirming the category of the first character image block, and performing the following processing:
if the first character image block is a single character image block, the single character in the single character image block is identified by matching with a template character image;
and if the first character image block is a sticky character image block, performing anti-sticky treatment on the sticky character image block to identify each character in the sticky character image block.
In some embodiments, character segmentation is performed on the binarized image with the edge blank areas removed to obtain a number of first character image blocks, including:
segmenting the binarized image from left to right by adopting a connected domain analysis method;
and removing the marginal blank areas of each segmented image obtained by segmentation to obtain a plurality of first character image blocks.
In some embodiments, confirming the category of the first character image block comprises:
comparing the width of the first character image block with a preset threshold value to determine the category of the first character image block, wherein the category is specifically as follows:
the width of the first character image block is smaller than the preset threshold value, and the first character image block is determined to be a single character image block; otherwise, the first character image block is determined to be the adhesion character image block.
In some embodiments, performing a de-blocking process on the block of stuck characters to perform recognition of each character in the block of images includes:
carrying out connected domain analysis on the adhered character image blocks, and roughly dividing the adhered character image blocks into a plurality of second image character blocks according to the high-low positions in the connected domain analysis result, wherein the second image character blocks are capitalized single character graphic blocks comprising one capitalized character, or lower capitalized single character graphic blocks comprising one lower capitalized single character, or equal-high adhered character image blocks comprising at least a plurality of capitalized single characters or a plurality of lower capitalized single characters;
confirming the category of the second character image block, and performing the following processing:
if the second character image block is a capitalized single character image block or a lowercase single character image block, the identification of capitalized single characters or lowercase single characters in the capitalized single character image block or the lowercase single character image block is implemented by matching with a template character image;
if the second character image block is a high adhesion character image block, further de-adhesion treatment is carried out on the high adhesion character image block so as to identify each character in the high adhesion character image block.
In some embodiments, the confirming the category of the second character image block includes:
comparing the width of the second character image block with a preset threshold value to determine the category of the second character image block, wherein the category is specifically as follows:
the width of the second character image block is smaller than the preset threshold value, and the second character image block is determined to be a capitalized single character graphic block or a lowercase single character graphic block; otherwise, the second character image block is determined to be the equal-height adhesion character image block.
In some embodiments, the performing the deblocking process on the contour block to perform recognition of each character in the contour block comprises:
the size processing is carried out on the equal-height adhesion character image, and the processed equal-height adhesion character image T with the target size is obtained new ；
According to the proportion T new Carrying out resize processing on the template character image by_h/M_h to obtain a processed and equal-height adhesion character image T new Template character images M having the same height new Wherein T is new H is the processed contour adhesion character image T new M_h is the height value of the template character image before processing;
template character image M processed according to template character image new Width-sized peer-to-peer high-adhesion character image T new Cutting is carried out, and third character image blocks containing single characters are extracted one by one;
and matching the character image with the template character image, and identifying single characters in the third character image block.
A second aspect of the present invention provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the character recognition method provided in the first aspect of the present invention when executing the program.
A third aspect of the present invention provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the character recognition method provided by the first aspect of the present invention.
The technical scheme provided by the invention is based on an image recognition technology, and realizes automatic recognition of the planning information in the display of the treatment control system. Particularly, the method solves the segmentation and recognition of the sticky characters included in the plan information, thereby improving the recognition accuracy of the plan information.
Drawings
FIG. 1 is a flow chart of a character recognition method according to an embodiment of the present invention;
FIG. 2 is a flowchart of a character recognition method according to another embodiment of the present invention;
FIG. 3 is a flowchart of a character recognition method according to another embodiment of the present invention;
FIG. 4 is a schematic diagram illustrating an implementation process of a character recognition method according to an embodiment of the present invention;
fig. 5 is a schematic diagram showing effects of stages in the execution of the character recognition method according to the embodiment of the invention.
Detailed Description
Specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
In the present invention, the term "in some embodiments" does not specifically refer to the same embodiment, and they may be the same embodiment or different embodiments.
As shown in fig. 1, the character recognition method in a display of a therapy control system provided by the invention comprises the following steps:
s100, acquiring an image in a display of the treatment control system.
In the implementation process, an image acquisition card can be adopted to acquire images displayed by a display of the treatment control system. The image format displayed in the treatment control system display is a standard format including patient planning information displayed in characters. Of course, the planning information of the character display is located in a display area at a predetermined position within the image, such as a display area of a predetermined size at an intermediate position of the image.
In addition, the image in the display of the treatment control system can be acquired by taking a picture through a camera, and the possibility of adhesion is higher due to the influence of factors such as shooting distance, pixels and the like on characters in the acquired image.
S200, acquiring an image to be recognized including characters from a preset area of the image.
The image to be identified is located in a display area of a predetermined area in the image, and the display area of the image to be identified is also generally preset. Therefore, the acquisition of the image to be identified can be realized only by intercepting the area image in the preset area.
S300, binarizing the image to be identified to obtain a binarized image.
After binarization processing, the image becomes simple, the data volume is reduced, and characters in the image to be recognized are fully highlighted. The technology of binarizing images is very mature, and various known binarization processing algorithms can be selected according to the needs in the specific implementation process, and the description is omitted.
S400, removing the marginal blank area of the binarized image.
Specifically, the binarized image can be divided left and right and divided up and down to obtain an external rectangle containing the target character, the external rectangle is taken as a frame to obtain the binarized image, the upper end of the uppercase character and the upper edge of the external rectangle are positioned at the same height, and a gap exists between the upper end of the lowercase character and the upper edge of the external rectangle. Thereby laying a foundation for subsequent character segmentation.
S500, performing character segmentation on the binarized image with the edge blank area removed to obtain a plurality of first character image blocks, wherein the first character image blocks are single character image blocks or adhesion character image blocks.
Since the character pixels of the binarized image are zero, the background pixel value is non-zero. Thus, the first character segmentation of the binarized image may be performed using a method of scanning the binarized image from left to right, which is well known to those skilled in the art. Specifically, after the scanning starts, the column with the first pixel point being zero is marked as the left boundary of the first character, then the right scanning is performed to mark the right boundary of the first character with the column position with the first pixel point becoming non-zero, so that one character is segmented, and then the above operation is repeated to the right scanning until all columns are scanned, so that the character segmentation of the current row in the binary image can be completed.
The segmented character image blocks may be single character images or cohesive character image blocks. Whether the character is a sticky character can be determined later by the width of the obtained character image.
S600, confirming the category of the first character image block.
The first character image block is a single character image block in that only one character is included therein, and its width dimension substantially coincides with the width of one single character.
The first character image block is a sticky character image block, and at least two sticky characters are ensured in the sticky character image block, and the width dimension of the sticky character image block is at least the width of two characters.
Based on this consideration, the categories of all the first character image blocks can be identified one by one in the following manner:
comparing the width of the first character image block with a preset threshold value to determine the category of the first character image block, wherein the category is specifically as follows: determining the first character image block as a single character image block when the width of the first character image block is less than a predetermined threshold; otherwise, the first character image block is determined to be a sticky character image block.
Wherein the predetermined threshold is slightly greater than the width of a single character.
S700, if the first character image block is a single character image block, the single character in the single character image block is identified by matching with the template character image.
For example, the template character image includes at least 26 uppercase english alphabetic characters and 26 lowercase english alphabetic characters. In order to be able to perform exact matching, it is optional to perform a unified resolution process on the first character image block and the template character image prior to matching so that the first character image block and the template character image are uniform in size.
S800, if the first character image block is the adhesion character image block, performing anti-adhesion processing on the adhesion character image block to identify each character in the adhesion character image block.
In the prior art, there are already a number of mature de-blocking methods, and the step S800 of the present invention may directly use these mature de-blocking methods to divide the block of blocking characters into a plurality of single character image blocks including only one single character, and then identify the characters in the single character image blocks one by one.
However, the processing procedure of these deblocking processing methods is generally complex and requires a lot of computing resources, and in view of this, the embodiment of the present invention provides a preferred way to implement deblocking processing on the block of the sticky character image, which specifically includes the following steps:
as shown in fig. 2, step S800 includes the following sub-steps:
s810: and carrying out connected domain analysis on the adhered character image blocks, and roughly dividing the adhered character image blocks into a plurality of second image character blocks according to the high-low positions in the connected domain analysis result, wherein the second image character blocks are capitalized single character graphic blocks comprising one capitalized character, or small capitalized single character graphic blocks comprising one small capitalized single character, or equal-height adhered character image blocks comprising at least a plurality of capitalized single characters or a plurality of small capitalized single characters.
In the sticky character image block, although there is a sticky between adjacent characters, the height of the uppercase characters is significantly higher than the height of the lowercase characters. Therefore, in performing connected domain analysis on the stuck character image block, if the heights between two consecutive areas are significantly different, division of the two areas can be performed. The sticky character image block may be finally cut into a number of second image character blocks.
Of course, there is also an extreme case where all characters in the sticky character image block are high-consistent uppercase characters, or all low-order characters. For this case, coarse segmentation cannot be performed, that is, one second image character block output in S810 is actually an original non-performed sticky character image block.
S820: and confirming the category of the second character image block.
The specific confirmation process is the same as the previous step S600, specifically:
comparing the width of the second character image block with a predetermined threshold to determine the category of the second character image block:
when the width of the second character image block is less than the predetermined threshold, the second character image block is determined to be a capital single character graphic block or a small single character graphic block.
Otherwise, the first character image block is determined to be the contour adhesion character image block. Note that the difference from step S600 is that the equal-height sticky character image block determined at this time includes a plurality of characters in which the presence of sticky are all uppercase characters having the same height or lowercase characters.
S830: if the second character image block is a capitalized single character image block or a lowercase single character image block, the identification of capitalized single characters or lowercase single characters in the capitalized single character image block or the lowercase single character image block is implemented by matching with the template character image.
The specific matching process is the same as the previous step S700, and will not be repeated here.
S840: if the second character image block is the equal-high adhesion character image block, further de-adhesion processing is carried out on the equal-high adhesion character image block so as to realize the identification of each character in the equal-high adhesion character image block.
In the specific implementation process, the conventional various anti-adhesion treatment methods can be adopted to implement further anti-adhesion treatment on the equivalent high-adhesion character image blocks so as to extract each character in the image blocks and identify the characters one by one.
The embodiment of the invention also provides a better anti-adhesion treatment mode for the equal-height adhesion character image blocks, which comprises the following specific processes:
as shown in fig. 3, step S840 may further include the following sub-steps:
s841: the method comprises the steps of carrying out the size processing on a peer-to-peer high-adhesion character image T to obtain a processed equal-high-adhesion character image T with a target size new 。
S842: according to the proportion T new Carrying out resize processing on the template character image M by_h/M_h to obtain a processed and equal-height adhesion character image T new Template character images M having the same height new Wherein:
T new h is the processed contour adhesion character image T new M_h is the height value of the template character image before processing;
s843: template character image M processed according to template character image new Width-sized peer-to-peer high-adhesion character image T new Clipping is carried out, and third character images containing single characters are extracted one by one.
S843: and matching the extracted third character image template character images, and identifying single characters in the third character images.
Thus, the identification of all characters in the image in the control system display is completed, and the planning information of the patient can be accurately known through the identification result.
In order to enable a person skilled in the art to understand the solution of the invention more clearly, the implementation of the invention will be described from another point of view by means of a more specific recognition case, in connection with fig. 4 and 5.
As shown in fig. 4 to 5, the implementation process of the identification case is specifically as follows:
and step 1, acquiring an image in a display of the treatment control system.
And 2, acquiring an area to be identified from the image, namely a patient planning information area, wherein the patient planning information area is the image to be identified.
And 3, performing binarization processing on the image to be identified to obtain a binarized image shown in fig. 5 (a).
And 4, performing left-right segmentation and up-down segmentation on the binarized image to obtain an external rectangle containing the target character. In order to be shown in fig. 5 (b), a rectangle box added to the image represents a circumscribed rectangle.
And 5, performing character segmentation on the binarized image from left to right to obtain a plurality of characters. Judging whether the width of the obtained character is smaller than a width threshold A or not, and judging whether the character is an adhesion character or not (T). Specifically, if the width of the character is smaller than A, the character is described as a single character (S), and the template characters M and S are subjected to the size reduction processing so as to keep the same size, a matching algorithm is adopted to calculate the matching rate of the template characters M and S, and the character with the highest matching rate is obtained, namely the final recognition result. If greater than A, it is indicated to be a sticky character T, as shown in FIG. 5 (c).
And 6, carrying out connected region analysis on the adhesion character T, and roughly dividing the single character with the upper case or the adhesion character according to the middle and high positions of the analysis result, as shown in fig. 5 (d).
And 7, dividing the result by adopting a left-right and up-down dividing method, wherein the dividing result is shown in fig. 5 (e) and 5 (f).
And 8, judging whether the character widths in the steps 5 (e) and 5 (f) are smaller than the threshold A in sequence. If the matching rate is smaller than A, the matching rate is calculated by using a matching algorithm, and the character with the highest matching rate is obtained, namely the final recognition result. If the number is greater than A, the bonding character T is described as bonding character T, and the bonding character T is subjected to the size processing to obtainT new . Then according to the ratio (T new h/M_h) carrying out resize treatment on M, and keeping the same height to obtain M new . Then according to M new Width M of (2) new W is equal to T new Cutting to obtain T 1 And T 2 As shown in FIG. 5 (g), T is on the left side 1 T on the right side 2 。
Step 9, calculating T 1 And the matching rate of M, obtaining the character with the highest matching rate, namely the final recognition result. Re-judging T 2 And (5) width, repeating the above operation until all characters are completely recognized.
The invention also provides an electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor executing the character recognition method in the display of the treatment control system provided by the invention.
The invention also provides an electronic device, the computer readable storage medium stores a computer program, and the program is executed by a processor to realize the character recognition method in the display of the treatment control system.
The invention has been described above in sufficient detail with a certain degree of particularity. It will be appreciated by those of ordinary skill in the art that the descriptions of the embodiments are merely exemplary and that all changes that come within the true spirit and scope of the invention are desired to be protected. The scope of the invention is indicated by the appended claims rather than by the foregoing description of the embodiments.

Claims (8)

1. A method of character recognition in a therapy control system display, comprising:
acquiring an image in a therapy control system display;
acquiring an image to be recognized comprising characters from a predetermined area of the image;
performing binarization processing on the image to be identified to obtain a binarized image;
removing an edge blank area of the binarized image;
performing character segmentation on the binarized image with the edge blank area removed to obtain a plurality of first character image blocks, wherein the first character image blocks are single character image blocks or adhesion character image blocks;
confirming the category of the first character image block, and performing the following processing:
if the first character image block is a single character image block, the single character in the single character image block is identified by matching with a template character image;
and if the first character image block is a sticky character image block, performing anti-sticky treatment on the sticky character image block to identify each character in the sticky character image block.
2. The character recognition method according to claim 1, wherein said performing character segmentation on said binarized image with edge margin areas removed to obtain a plurality of first character image blocks comprises:
segmenting the binarized image from left to right by adopting a connected domain analysis method;
and removing the marginal blank areas of each segmented image obtained by segmentation to obtain a plurality of first character image blocks.
3. The character recognition method according to claim 1, wherein said confirming the category of the first character image block includes:
comparing the width of the first character image block with a preset threshold value to determine the category of the first character image block, wherein the category is specifically as follows:
the width of the first character image block is smaller than the preset threshold value, and the first character image block is determined to be a single character image block; otherwise, the first character image block is determined to be the adhesion character image block.
4. The character recognition method according to claim 1, wherein the performing the deblocking process on the block of the stuck character image to perform recognition of each character in the block of the image comprises:
carrying out connected domain analysis on the adhered character image blocks, and roughly dividing the adhered character image blocks into a plurality of second image character blocks according to the high-low positions in the connected domain analysis result, wherein the second image character blocks are capitalized single character graphic blocks comprising one capitalized character, or lower capitalized single character graphic blocks comprising one lower capitalized single character, or equal-high adhered character image blocks comprising at least a plurality of capitalized single characters or a plurality of lower capitalized single characters;
confirming the category of the second character image block, and performing the following processing:
if the second character image block is a capitalized single character image block or a lowercase single character image block, the identification of capitalized single characters or lowercase single characters in the capitalized single character image block or the lowercase single character image block is implemented by matching with a template character image;
if the second character image block is a high adhesion character image block, further de-adhesion treatment is carried out on the high adhesion character image block so as to identify each character in the high adhesion character image block.
5. The character recognition method according to claim 4, wherein said confirming the category of the second character image block includes:
comparing the width of the second character image block with a preset threshold value to determine the category of the second character image block, wherein the category is specifically as follows:
the width of the second character image block is smaller than the preset threshold value, and the second character image block is determined to be a capitalized single character graphic block or a lowercase single character graphic block; otherwise, the second character image block is determined to be the equal-height adhesion character image block.
6. The character recognition method according to claim 4, wherein the performing the deblocking process on the contour block to perform recognition of each character in the contour block comprises:
the size processing is carried out on the equal-height adhesion character image, and the processed equal-height adhesion character image T with the target size is obtained new ；
According to the proportion T new Carrying out resize processing on the template character image by_h/M_h to obtain a processed and equal-height adhesion character image T new Template character images M having the same height new Wherein T is new H is the processed contour adhesion character image T new M_h is the height value of the template character image before processing;
template character image M processed according to template character image new Width-sized peer-to-peer high-adhesion character image T new Cutting is carried out, and third character image blocks containing single characters are extracted one by one;
the recognition of the single character in the third character image block is performed by matching with the template character image.
7. An electronic device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the character recognition method of any one of claims 1 to 6 when the program is executed by the processor.
8. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored thereon a computer program which, when executed by a processor, implements the character recognition method according to any one of claims 1 to 6.
CN202310669387.9A 2023-06-07 2023-06-07 Character recognition method in therapy control system display, electronic equipment and storage medium Pending CN116704517A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310669387.9A CN116704517A (en) 2023-06-07 2023-06-07 Character recognition method in therapy control system display, electronic equipment and storage medium

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310669387.9A CN116704517A (en) 2023-06-07 2023-06-07 Character recognition method in therapy control system display, electronic equipment and storage medium

Publications (1)

Publication Number Publication Date
CN116704517A true CN116704517A (en) 2023-09-05

Family

ID=87844512

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310669387.9A Pending CN116704517A (en) 2023-06-07 2023-06-07 Character recognition method in therapy control system display, electronic equipment and storage medium

Country Status (1)

Country Link
CN (1) CN116704517A (en)

Similar Documents

Publication Publication Date Title
US6404936B1 (en) Subject image extraction method and apparatus
US8103077B2 (en) Method and system for locating opaque regions in chest X-ray radiographs
JP6080259B2 (en) Character cutting device and character cutting method
US20060245650A1 (en) Precise grayscale character segmentation apparatus and method
EP2270746A2 (en) Method for detecting alterations in printed document using image comparison analyses
JP2009211179A (en) Image processing method, pattern detection method, pattern recognition method, and image processing device
CN114299086B (en) Image segmentation processing method, electronic equipment and system for low-contrast imaging
US9864898B2 (en) Feature point input assisting device, feature point input assisting method, and storage medium stored with program
CN111105427A (en) Lung image segmentation method and system based on connected region analysis
CN117115117B (en) Pathological image recognition method based on small sample, electronic equipment and storage medium
EP1202213A2 (en) Document format identification apparatus and method
CN112017148B (en) Method and device for extracting single-segment skeleton contour
JP3597148B2 (en) Fingerprint feature extraction device, fingerprint feature extraction method, and fingerprint extraction program
US6289123B1 (en) Character extracting method and its apparatus
CN116704517A (en) Character recognition method in therapy control system display, electronic equipment and storage medium
CN114529570A (en) Image segmentation method, image identification method, user certificate subsidizing method and system
CN110751158B (en) Digital identification method, device and storage medium in therapeutic bed display
CN111027521B (en) Text processing method and system, data processing device and storage medium
JP4164166B2 (en) Irradiation area extraction apparatus, irradiation area extraction method, and computer-readable storage medium
JP4116179B2 (en) Image processing method, image processing apparatus, and recording medium
JP2004094427A (en) Slip image processor and program for realizing the same device
JP6613625B2 (en) Image processing program, image processing apparatus, and image processing method
JP7480997B2 (en) Image processing device, image processing method, and program
CN113256614B (en) Medical image processing system
JP4732626B2 (en) Form processing method, apparatus, and program

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination