Systems and methods for detecting text of interest

Patent metadata

Field	Value
Publication number	US-12354382-B2
Application number	US-202418440810-A
Country	US
Kind code	B2
Filing date	Feb 13, 2024
Priority date	Jul 20, 2021
Publication date	Jul 8, 2025
Grant date	Jul 8, 2025

Abstract

In some embodiments, apparatuses and methods are provided herein useful to detecting text of interest. In some embodiments, there is provided a system to detect vertically oriented text of interest including at least one camera and a control circuit configured to execute a trained machine learning model to automatically detect vertically oriented text of interest on an object of interest. The trained machine learning model is at least trained on a first data set including a plurality of captured digital images each depicting the object of interest, and a second data set including a plurality of augmented digital images each depicting a captured digital image augmented with a synthetic text image including randomly generated text on a randomly selected background image.

First claim

What is claimed is:

1. A system for detecting text of interest, the system comprising:
at least one camera configured to capture one or more digital images of a scene; and
a control circuit executing a trained machine learning model configured to automatically detect vertically oriented text of interest on an object of interest depicted in a digital image of the captured one or more digital images of the scene, wherein the trained machine learning model is at least trained on a first data set comprising a plurality of captured digital images each depicting the object of interest, and a second data set comprising a plurality of augmented digital images each depicting a captured digital image augmented with a synthetic text image comprising randomly generated text on a randomly selected background image.

2. The system of claim 1 , wherein the object of interest comprises a cargo trailer for use in distribution of goods.

3. The system of claim 1 , wherein the vertically oriented text of interest comprises a corresponding identification associated with the object of interest.

4. The system of claim 1 , wherein the vertically oriented text of interest comprises text having a combination of one or more alphabet and numerical characters.

5. The system of claim 1 , wherein the synthetic text image comprises text that is randomly oriented.

6. The system of claim 1 , wherein the control circuit is further configured to:
determine a first image resolution of the captured one or more digital images;
determine that the first image resolution is less than a threshold image resolution; and
in response to the determination that the first image resolution is less than the threshold image resolution, pad the captured one or more digital images with images to match the threshold image resolution, wherein the padding of the captured one or more digital images with the images avoids stretching the captured one or more digital images to match the threshold image resolution and facilitates at least one of a first differentiation between letter O and number 0 and a second differentiation between letter I and number 1.

7. The system of claim 1 , wherein the control circuit is further configured to:
determine whether a first image resolution is equal to a threshold image resolution; and
in response to the determination that the first image resolution is not equal to the threshold image resolution, resize the captured one or more digital images on at least one of a shorter side and a longer side of the captured one or more digital images while maintaining same aspect ratio of the captured one or more digital images.

8. The system of claim 1 , wherein the trained machine learning model is further trained on a third data set comprising a plurality of captured digital images each depicting the object of interest having vertically oriented text of interest.

9. The system of claim 1 , wherein the scene comprises at least one of an entrance to a distribution center (DC), an area proximate a delivery dock in the DC, and an area designated as a check-in area for delivery vehicles going into or out of the DC.

10. The system of claim 1 , wherein the control circuit is further configured to automatically detect horizontally oriented text of interest on the object of interest depicted in the digital image of the captured one or more digital images of the scene.

11. A method for detecting text of interest, the method comprising:
capturing, by at least one camera, one or more digital images of a scene; and
executing, by a control circuit coupled to the at least one camera, a trained machine learning model to automatically detect a vertically oriented text of interest on an object of interest in the captured one or more digital images of the scene, wherein the trained machine learning model is at least trained on a first data set comprising a plurality of captured digital images each depicting the object of interest, and a second data set comprising a plurality of augmented digital images each depicting a captured digital image augmented with a synthetic text image comprising a randomly generated text on a randomly selected background image.

12. The method of claim 11 , wherein the object of interest comprises a cargo trailer for use in distribution of goods.

13. The method of claim 11 , wherein the vertically oriented text of interest comprises a corresponding identification associated with the object of interest.

14. The method of claim 11 , wherein the vertically oriented text of interest comprises text having a combination of one or more alphabet and numerical characters.

15. The method of claim 11 , wherein the synthetic text image comprises text that is randomly oriented.

16. The method of claim 11 , further comprising:
determining, by the control circuit, a first image resolution of the captured one or more digital images;
determining, by the control circuit, that the first image resolution is less than a threshold image resolution; and
in response to the determination that the first image resolution is less than the threshold image resolution, padding, by the control circuit, the captured one or more digital images with images to match the threshold image resolution, wherein the padding of the captured one or more images with the images avoids stretching the captured one or more digital images to match the threshold image resolution and at least one of facilitates a first differentiation between letter O and number 0 and a second differentiation between letter I and number 1.

17. The method of claim 11 , further comprising:
determining, by the control circuit, whether a first image resolution is equal to a threshold image resolution; and
in response to the determining that the first image resolution is not equal to the threshold image resolution, resizing, by the control circuit, the captured one or more digital images on at least one of a shorter side and a longer side of the captured one or more digital images while maintaining same aspect ratio of the captured one or more digital images.

18. The method of claim 11 , wherein the trained machine learning model is further trained on a third data set comprising a plurality of captured digital images each depicting the object of interest having vertically oriented text of interest.

19. The method of claim 11 , wherein the scene comprises at least one of an entrance to a distribution center (DC), an area proximate a delivery dock in the DC, and an area designated as a check-in area for delivery vehicles going into or out of the DC.

20. The method of claim 11 , further comprising automatically detecting, by the control circuit, horizontally oriented text of interest on the object of interest depicted in the digital image of the captured one or more digital images of the scene.

Assignees

• Walmart Apollo Llc

Inventors

• RAMASWAMY SRINIVASA Ramanujam
• Kumar Manish
• AGGARWAL Pranav

Classifications

• G06V30/1463

  Orientation detection or correction, e.g. rotation of multiples of 90 degrees · CPC title

• G06V30/1444

  Selective acquisition, locating or processing of specific regions, e.g. highlighted text, fiducial marks or predetermined fields · CPC title

• G06V20/625

  License plates · CPC title

• G06N20/00

  Machine learning · CPC title

• G06V10/762

  using clustering, e.g. of similar faces in social networks · CPC title