NZ780583B2 - Intelligent image segmentation prior to optical character recognition (ocr) - Google Patents
Intelligent image segmentation prior to optical character recognition (ocr)Info
- Publication number
- NZ780583B2 NZ780583B2 NZ780583A NZ78058320A NZ780583B2 NZ 780583 B2 NZ780583 B2 NZ 780583B2 NZ 780583 A NZ780583 A NZ 780583A NZ 78058320 A NZ78058320 A NZ 78058320A NZ 780583 B2 NZ780583 B2 NZ 780583B2
- Authority
- NZ
- New Zealand
- Prior art keywords
- coordinates
- heart pump
- mosaic image
- source region
- screen
- Prior art date
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/2163—Partitioning the feature space
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/62—Text, e.g. of license plates, overlay texts or captions on TV images
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H30/00—ICT specially adapted for the handling or processing of medical images
- G16H30/40—ICT specially adapted for the handling or processing of medical images for processing medical images, e.g. editing
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16H—HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G16H40/00—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices
- G16H40/60—ICT specially adapted for the management or administration of healthcare resources or facilities; ICT specially adapted for the management or operation of medical equipment or devices for the operation of medical equipment or devices
Abstract
medical device monitoring system and method extract information from screen images from medical device controllers, with a single OCR process invocation per screen image, despite critical information appearing in different screen locations, depending on which medical device controller's screen image is processed. For example, different software versions of the medical device controllers might display the same type of information in different screen locations. Copies of the critical screen information, one copy from each different screen location, are made in a mosaic image, and then the mosaic image is OCR processed to produce text results. Text is selectively extracted from the OCR text results, depending on contents of a selector field on the screen image, such as a software version number or a heart pump model identifier.
Claims (20)
1. A heart pump monitoring system comprising one or more servers configured to automatically: request and receive, via a computer network, from a medical device controller coupled to a heart pump, an image of contents displayed on a screen of the medical device controller, wherein the received image comprises content displayed on the screen at first, second, and third screen coordinates, wherein the first, second, and third screen coordinates are different from one another, and wherein the medical device controller is configured to (a) display operational data about the heart pump at the first screen coordinates or (b) display the operational data about the heart pump at the second screen coordinates; generate a mosaic image, wherein the one or more servers are configured to: (a) copy a first source region, which encompasses the first screen coordinates of the received image, to a predefined destination region at fourth coordinates in the mosaic image, (b) copy a second source region, which encompasses the second screen coordinates of the received image, to a predefined destination region at fifth coordinates, different from the fourth coordinates, in the mosaic image, and (c) copy a third source region, which encompasses the third screen coordinates of the received image, to a predefined destination region at sixth coordinates, different from the fourth and fifth coordinates, in the mosaic image; after the mosaic image is generated, have the mosaic image optical-character- recognized to produce text results; extract a selector text result from the text results, such that the selector text result corresponds to the sixth coordinates in the mosaic image; compare the selector text result to a predefined text; if the selector text result is found to match the predefined text, extract a selected text result from the text results, such that the selected text result corresponds to the fourth coordinates in the mosaic image; otherwise extract the selected text result from the text results, such that the selected text result corresponds to the fifth coordinates in the mosaic image; and if the selected text result is outside a predetermined range, raise an alarm, wherein the selected text result corresponds to the operational data about the heart pump, and wherein the operational data about the heart pump comprises a placement signal, a current speed setting, a motor current value, a current blood flow rate, a minimum blood flow rate, or a maximum blood flow rate.
2. A heart pump monitoring system according to claim 1, wherein the third source region contains a version number of software executed by the medical device controller.
3. A heart pump monitoring system according to claim 1, wherein the third source region contains an identifier of the heart pump coupled to the medical device controller.
4. A heart pump monitoring system according to claim 3, wherein the identifier of the heart pump comprises a serial number or a type code.
5. A heart pump monitoring system according to claim 1, wherein the third source region contains an identifier of an optional feature installed on the medical device controller.
6. A heart pump monitoring system according to claim 1, wherein the predefined destination region at the fourth coordinates in the mosaic image is larger than the first source region, and wherein to copy the first source region to the predefined destination region at the fourth coordinates, the one or more servers are configured to magnify the first source region so as to fill the predefined destination region at the fourth coordinates.
7. A heart pump monitoring system according to claim 1, wherein to copy the first source region to the predefined destination region at the fourth coordinates, the one or more servers are configured to convert at least one non-black pixel of the first source region to a white pixel in the predefined destination region at the fourth coordinates.
8. A heart pump monitoring system according to claim 1, wherein to copy the first source region to the predefined destination region at the fourth coordinates, the one or more servers are configured to convert each non-black pixel of the first source region to a white pixel in the predefined destination region at the fourth coordinates.
9. A heart pump monitoring system according to claim 1, wherein the first source region overlaps with the second source region of the received image.
10. A heart pump monitoring system according to claim 10, wherein the predefined destination region at the fourth coordinates in the mosaic image does not overlap with the predefined destination region at the fifth coordinates in the mosaic image.
11. A heart pump monitoring system according to claim 1, wherein the operational data about the heart pump comprises the placement signal.
12. A heart pump monitoring system according to claim 1, wherein the operational data about the heart pump comprises the current blood flow rate.
13. A method of monitoring a heart pump, the method comprising: requesting and receiving, with one or more processors, via a computer network, from a medical device controller coupled to the heart pump, an image of contents displayed on a screen of the medical device controller, wherein the received image comprises content displayed on the screen at first, second, and third screen coordinates, wherein the first, second, and third screen coordinates are different from one another, and wherein the medical device controller is configured to (a) display operational data about the heart pump at the first screen coordinates or (b) display the operational data about the heart pump at the second screen coordinates; generating, with the one or more processors, a mosaic image, wherein the generation of the mosaic image comprises: (a) copying a first source region, which encompasses the first screen coordinates of the received image, to a predefined destination region at fourth coordinates in the mosaic image; (b) copying a second source region, which encompasses the second screen coordinates of the received image, to a predefined destination region at fifth coordinates, different from the fourth coordinates, in the mosaic image; and (c) copying a third source region, which encompasses the third screen coordinates of the received image, to a predefined destination region at sixth coordinates, different from the fourth and fifth coordinates, in the mosaic image; after generating the mosaic image, having, with the one or more processors, the mosaic image optical-character-recognized to produce text results; extracting, with the one or more processors, a selector text result from the text results, such that the selector text result corresponds to the sixth coordinates in the mosaic image; comparing, with the one or more processors, the selector text result to a predefined text; if the selector text result is found to match the predefined text, extracting, with the one or more processors, a selected text result from the text results, such that the selected text result corresponds to the fourth coordinates in the mosaic image; otherwise, extracting, with the one or more processors, the selected text result from the text results, such that the selected text result corresponds to the fifth coordinates in the mosaic image; and if the selected text result is outside a predetermined range, raising, with the one or more processors, an alarm, wherein the selected text result corresponds to the operational data about the heart pump, and wherein the operational data about the heart pump comprises a placement signal, a current speed setting, a motor current value, a current blood flow rate, a minimum blood flow rate, or a maximum blood flow rate.
14. A method according to claim 13, wherein the third source region contains a version number of software executed by the medical device controller.
15. A method according to claim 13, wherein the third source region contains an identifier of the heart pump coupled to the medical device controller.
16. A method according to claim 15, wherein the identifier of the heart pump comprises a serial number or a type code.
17. A method according to claim 13, wherein the third source region contains an identifier of an optional feature installed on the medical device controller.
18. A method according to claim 13, wherein the predefined destination region at the fourth coordinates in the mosaic image is larger than the first source region, and wherein copying the first source region to the predefined destination region at the fourth coordinates comprises magnifying the first source region so as to fill the predefined destination region at the fourth coordinates.
19. A method according to claim 13, wherein copying the first source region to the predefined destination region at the fourth coordinates comprises converting at least one non- black pixel of the first source region to a white pixel in the predefined destination region at the fourth coordinates.
20. A non-transitory computer-readable storage medium having instructions stored thereon that, when executed by one or more processors, cause the one or more processors to: request and receive, via a computer network, from a medical device controller coupled to a heart pump, an image of contents displayed on a screen of the medical device controller, wherein the received image comprises content displayed on the screen at first, second, and third screen coordinates, wherein the first, second, and third screen coordinates are different from one another, and wherein the medical device controller is configured to (a) display operational data about the heart pump at the first screen coordinates or (b) display the operational data about the heart pump at the second screen coordinates; generate a mosaic image, wherein the generation of the mosaic image comprises: (a) copying a first source region, which encompasses the first screen coordinates of the received image, to a predefined destination region at fourth coordinates in the mosaic image; (b) copying a second source region, which encompasses the second screen coordinates of the received image, to a predefined destination region at fifth coordinates, different from the fourth coordinates, in the mosaic image; and (c) copying a third source region, which encompasses the third screen coordinates of the received image, to a predefined destination region at sixth coordinates, different from the fourth and fifth coordinates, in the mosaic image; after generating the mosaic image, have the mosaic image optical-character-recognized to produce text results; extract a selector text result from the text results, such that the selector text result corresponds to the sixth coordinates in the mosaic image; compare the selector text result to a predefined text; if the selector text result is found to match the predefined text, extract a selected text result from the text results, such that the selected text result corresponds to the fourth coordinates in the mosaic image; otherwise, extract the selected text result from the text results, such that the selected text result corresponds to the fifth coordinates in the mosaic image; and if the selected text result is outside a predetermined range, raise an alarm, wherein the selected text result corresponds to the operational data about the heart pump, and wherein the operational data about the heart pump comprises a placement signal, a current speed setting, a motor current value, a current blood flow rate, a minimum blood flow rate, or a maximum blood flow rate.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| US16/360,270 US10824898B2 (en) | 2019-03-21 | 2019-03-21 | Intelligent image segmentation prior to optical character recognition (OCR) |
| PCT/US2020/023899 WO2020191308A1 (en) | 2019-03-21 | 2020-03-20 | Intelligent image segmentation prior to optical character recognition (ocr) |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| NZ780583A NZ780583A (en) | 2024-04-26 |
| NZ780583B2 true NZ780583B2 (en) | 2024-07-30 |
Family
ID=
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US12293600B2 (en) | Automatic image capture system based on a determination and verification of a physical object size in a captured image | |
| EP4660974A3 (en) | Intelligent image segmentation prior to optical character recognition (ocr) | |
| US20180089536A1 (en) | Method and apparatus for processing point cloud data | |
| CN113283347A (en) | Assembly work guidance method, device, system, server and readable storage medium | |
| US11669977B2 (en) | Processing images to localize novel objects | |
| US11694331B2 (en) | Capture and storage of magnified images | |
| US20110103663A1 (en) | Apparatus, method and computer-readable storage mediums for detecting a region of interest in a medical image | |
| US11017498B2 (en) | Ground truth generation from scanned documents | |
| CN108197567A (en) | For the method, apparatus and computer-readable medium of image procossing | |
| CN114116474B (en) | Software verification method, device, electronic device and storage medium | |
| CN114140805A (en) | Image processing method, image processing device, electronic equipment and storage medium | |
| US20110206232A1 (en) | Method and apparatus for engaging functionality with a color tag | |
| WO2017182523A1 (en) | A method and a system for real-time remote support with use of computer vision and augmented reality | |
| NZ780583B2 (en) | Intelligent image segmentation prior to optical character recognition (ocr) | |
| US6895556B1 (en) | System and method for providing access to displayed data | |
| EP3709666A1 (en) | Method for fitting target object in video frame, system, and device | |
| JP4958868B2 (en) | Document feature extraction apparatus and method | |
| JP2024049723A (en) | Estimation device, model generation device, estimation method, model generation method, and program | |
| CN115797939A (en) | Two-stage italic character recognition method and device based on deep learning | |
| CN116704518A (en) | A text recognition method and device, electronic equipment, and storage medium | |
| CN113254626A (en) | Document processing method and device, electronic equipment and readable storage medium | |
| JP7831126B2 (en) | Character recognition processing system, character recognition processing method, and program | |
| JP3137859B2 (en) | Index image display method | |
| CN117557669A (en) | Methods, devices, equipment, storage media and program products for generating overhead views | |
| JP2025008014A (en) | Image processing device, image processing method, and program |