Search

CN-121999343-A - System and method for configuring an imaging tool using a generative AI

CN121999343ACN 121999343 ACN121999343 ACN 121999343ACN-121999343-A

Abstract

Systems and methods for controlling an imaging tool associated with performing an imaging task are disclosed. An example method may include a model receiving image data including at least one image including text and control data associated with an imaging tool, the control data indicating a description of an imaging task, a plurality of settings of the imaging tool associated with performing the imaging task, and a schema to configure tool configuration data of the plurality of settings. The method may include generating tool configuration data for the imaging tool by the model, the tool configuration data indicating one or more values corresponding to at least a portion of the plurality of settings. The method may include configuring an imaging tool using the tool configuration data.

Inventors

  • M. M. Degen

Assignees

  • 斑马技术公司

Dates

Publication Date
20260508
Application Date
20251103
Priority Date
20241101

Claims (15)

  1. 1. A method for configuring an imaging tool associated with performing an imaging task, the method comprising: Receiving at the model: image data comprising at least one image, wherein the at least one image comprises text, and Control data associated with the imaging tool, wherein the control data indicates: a description of the task of imaging is given, A plurality of settings of the imaging tool associated with performing the imaging task, and A scheme for configuring tool configuration data for the plurality of settings; generating the tool configuration data for the imaging tool via the model, wherein the tool configuration data indicates one or more values corresponding to at least a portion of the plurality of settings, and The imaging tool is configured using the tool configuration data.
  2. 2. The method of claim 1, wherein generating the tool configuration data comprises: based on the image data, eliminating at least one setting of the plurality of settings configured by the tool configuration data, and/or A range of values of the one or more values corresponding to at least the portion of the plurality of settings is limited based on the image data.
  3. 3. The method of claim 1, further comprising: An indication of the imaging tool of a plurality of imaging tools is received, wherein receiving at least the control data at the model is responsive to receiving the indication of the imaging tool.
  4. 4. The method of claim 1, wherein the plurality of settings are associated with performing optical character recognition on an image and include one or more of a confidence measure, an average character height, a color of text, a contrast threshold, a character width, a character range, a region of interest, a character string match, or text optimization.
  5. 5. The method of claim 1, further comprising a base model configured to generate a plurality of configuration data sets corresponding to a plurality of tools, wherein: the plurality of configuration data sets includes the tool configuration data, The plurality of tools includes the imaging tool, Fine tuning of the base model generates the model, The fine tuning configures the model to generate the tool configuration data for the imaging tool, and The fine tuning results in the model having better execution in generating the tool configuration data for the imaging tool relative to execution of the base model in generating the tool configuration data for the imaging tool.
  6. 6. The method of claim 1, wherein the model comprises one or more of a neural network, a generative model, or a language model.
  7. 7. The method of claim 1, wherein the control data comprises one or more hints configured for the model.
  8. 8. The method of claim 1, wherein the model is configured for determining a region of interest (ROI) and/or generating the tool configuration data based on the ROI in the at least one image.
  9. 9. The method of claim 1, further comprising: performing the imaging task on a set of test images including test image data using the imaging tool configured with the tool configuration data; determining whether execution of the imaging task implements one or more metrics associated with the imaging task; In response to implementing the one or more metrics, Generating imager configuration data for configuring an operating parameter of an imaging device, the imager configuration data being based on the tool configuration data, and Providing the imager configuration data to the imaging device, and In response to not implementing the one or more metrics, the tool configuration data is modified via the model to improve the performance of the imaging task on the set of test images using the imaging tool.
  10. 10. The method of claim 9, wherein the model iteratively modifies the tool configuration data until the imaging tool implements the one or more metrics.
  11. 11. A system for configuring an imaging tool associated with performing an imaging task, the system comprising: a model stored on one or more memories; one or more processors, and The one or more memories store processor-executable instructions that, when executed by the one or more processors, cause the system to: Receiving at the model: image data comprising at least one image, wherein the at least one image comprises text, and Control data associated with the imaging tool, wherein the control data indicates: a description of the task of imaging is given, A plurality of settings of the imaging tool associated with performing the imaging task, and A scheme for configuring tool configuration data for the plurality of settings, Generating, via the model, the tool configuration data for the imaging tool, wherein the tool configuration data indicates one or more values corresponding to at least a portion of the plurality of settings, and The imaging tool is configured using the tool configuration data.
  12. 12. The system of claim 11, wherein generating the tool configuration data further comprises instructions that, when executed, cause the system to: based on the image data, eliminating at least one setting of the plurality of settings configured by the tool configuration data, and/or A range of values of the one or more values corresponding to at least the portion of the plurality of settings is limited based on the image data.
  13. 13. The method of claim 11, further comprising a base model configured to generate a plurality of configuration data sets corresponding to a plurality of tools, wherein: the plurality of configuration data sets includes the tool configuration data, The plurality of tools includes the imaging tool, Fine tuning of the base model generates a model, The fine tuning configures the model to generate the tool configuration data for the imaging tool, and The fine tuning results in the model having better execution in generating the tool configuration data for the imaging tool relative to execution of the base model in generating the tool configuration data for the imaging tool.
  14. 14. The system of claim 11, further comprising instructions that, when executed, cause the system to: performing the imaging task on a set of test images including test image data using the imaging tool configured with the tool configuration data; determining whether execution of the imaging task implements one or more metrics associated with the imaging task; In response to implementing the one or more metrics, Generating imager configuration data for configuring an operating parameter of an imaging device, the imager configuration data being based on the tool configuration data, and Providing the imager configuration data to the imaging device, and In response to not implementing the one or more metrics, the tool configuration data is modified via the model to improve the performance of the imaging task on the set of test images using the imaging tool.
  15. 15. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, cause the one or more processors to: Receiving at the model: image data comprising at least one image, wherein the at least one image comprises text, and Control data associated with an imaging tool, wherein the control data indicates: description of the task of imaging, A plurality of settings of the imaging tool associated with performing the imaging task, and A scheme for configuring tool configuration data for the plurality of settings; generating the tool configuration data for the imaging tool via the model, wherein the tool configuration data indicates one or more values corresponding to at least a portion of the plurality of settings, and The imaging tool is configured using the tool configuration data.

Description

System and method for configuring an imaging tool using a generative AI Background The background description provided herein is for the purpose of generally presenting the context of the disclosure. Work of the presently named inventors, to the extent it is described in this background section, as well as aspects of the description that may not otherwise qualify as prior art at the time of filing, are neither expressly nor impliedly admitted as prior art against the present disclosure. An application for performing imaging tasks on an image, such as a machine vision tool for optical character recognition or bar code decoding, may have many settings configured for the application for performing imaging tasks. Some examples of settings may include determining a region of interest of an image to analyze to perform a particular imaging task, an average character height of text to identify in the image, a contrast of text or other symbology in the image, a color of the text to identify, and so forth. The values of the application settings are not always self-evident or easily determinable, which may present difficulties to the application user when configuring the settings and/or result in settings that may not be suitable for a given subject image and/or imaging task. The miss-test procedure to reach the appropriate application settings can be frustrating and time consuming for the user, and also unnecessarily consume computing resources (e.g., processing cycles, memory, power, etc.) in testing the various application settings on the subject image. Accordingly, there is an opportunity for configuring an imaging tool to generate artificial intelligence. Disclosure of Invention In one aspect, a method for configuring an imaging tool associated with performing an imaging task may include receiving image data including at least one image at a model, wherein the at least one image includes text, and control data associated with the imaging tool, wherein the control data indicates a description of the imaging task, a plurality of settings of the imaging tool associated with performing the imaging task, and a scheme of configuring tool configuration data for the plurality of settings, generating tool configuration data for the imaging tool via the model, wherein the tool configuration data indicates one or more values corresponding to at least a portion of the plurality of settings, and configuring the imaging tool using the tool configuration data. In variations of this aspect, generating the tool configuration data may include eliminating at least one of a plurality of settings configured by the tool configuration data based on the image data and/or limiting a range of values of one or more values corresponding to at least a portion of the plurality of settings based on the image data. In another variation of this aspect, the method may include receiving an indication of an imaging tool of the plurality of imaging tools, wherein receiving at least the control data at the model is responsive to receiving the indication of the imaging tool. In yet another variation of this aspect, the tool configuration data may include a JSON file. In yet another variation of this aspect, the plurality of settings may be associated with performing optical character recognition on the image. In variations of this aspect, the plurality of settings may include one or more of a confidence measure, an average character height, a color of text, a contrast threshold, a character width, a character range, a region of interest, a string match, or text optimization. In another variation of this aspect, the method may include a base model configured to generate a plurality of configuration data sets corresponding to a plurality of tools, wherein the plurality of configuration data sets includes tool configuration data, the plurality of tools includes imaging tools, a trim generation model of the base model, the trim generation model to generate tool configuration data for the imaging tools, and execution of the tool configuration data for the imaging tools relative to the base model, the trim resulting in a better execution of the model in generating tool configuration data for the imaging tools. In yet another variation of this aspect, the model includes one or more of a neural network, a generative model, or a language model. In yet another variation of this aspect, the control data may include one or more hints configured for the model. In a variation on this aspect, the model may be configured to determine a region of interest (ROI) based on the ROI in the at least one image and/or generate the tool configuration data. In another variation of this aspect, a method may include performing an imaging task on a set of test images including test image data using an imaging tool configured with tool configuration data, determining whether execution of the imaging task implements one or more metrics associated with the imaging task, generating, i