Method, device, and computer program product for image recognition

Patent metadata

Field	Value
Publication number	US-2023038047-A1
Application number	US-202117405241-A
Country	US
Kind code	A1
Filing date	Aug 18, 2021
Priority date	Jul 23, 2021
Publication date	Feb 9, 2023
Grant date	—

Abstract

Embodiments of the present disclosure relate to a method, a device, and a computer program product for image recognition. In some embodiments, characterization information for a first reference image in a reference image set is generated in an image recognition engine by using a Gaussian mixture model. First reference label information for the first reference image is generated based on the characterization information for the first reference image, the first reference label information being associated with a category of a first object in the first reference image. The image recognition engine is updated by determining the accuracy of the first reference label information for the first reference image. In this way, good characterization of images and generation of reference label information for the images can be achieved, thus both improving the robustness of the generated reference label information and significantly improving the accuracy of image recognition.

First claim

What is claimed is:

1 . A method for image recognition, including:
generating, in an image recognition engine, characterization information for a first reference image in a reference image set by using a Gaussian mixture model; generating first reference label information for the first reference image based on the characterization information for the first reference image, the first reference label information being associated with a category of a first object in the first reference image; and updating the image recognition engine by determining the accuracy of the first reference label information for the first reference image.

2 . The method according to claim 1 , further including:
generating, based on a second reference image without label information in the reference image set and by means of the updated image recognition engine, second reference label information for the second reference image, the second reference label information being associated with a category of an object in the second reference image; and using the second reference image and the second reference label information for the second reference image to further update the image recognition engine.

3 . The method according to claim 1 , wherein generating the characterization information for the first reference image includes:
generating weight information for the Gaussian mixture model based on the first reference image and initial expectation information for the Gaussian mixture model; and generating the characterization information for the first reference image based on the initial expectation information and the weight information.

4 . The method according to claim 3 , wherein generating the weight information for the Gaussian mixture model includes:
generating the weight information for the Gaussian mixture model using a kernel function based on the first reference image and the initial expectation information for the Gaussian mixture model.

5 . The method according to claim 3 , wherein the initial expectation information is a multi-dimensional vector, and vectors of at least two dimensions in the multi-dimensional vector are orthogonal.

6 . The method according to claim 3 , further including:
obtaining the initial expectation information for the Gaussian mixture model based on a third reference image with label information in the reference image set and third pre-existing label information for the third reference image, the third pre-existing label information being associated with a category of a third object in the third reference image.

7 . The method according to claim 6 , further including:
generating a reconstructed image based on the initial expectation information for the Gaussian mixture model; and updating the initial expectation information based on the reconstructed image.

8 . A device for image recognition, including:
a processor, and a memory storing computer-executable instructions, wherein the computer-executable instructions, when executed by the processor, cause the device to perform actions including: generating, in an image recognition engine, characterization information for a first reference image in a reference image set by using a Gaussian mixture model; generating first reference label information for the first reference image based on the characterization information for the first reference image, the first reference label information being associated with a category of a first object in the first reference image; and updating the image recognition engine by determining the accuracy of the first reference label information for the first reference image.

9 . The device according to claim 8 , wherein the actions further include:
generating, based on a second reference image without label information in the reference image set and by means of the updated image recognition engine, second reference label information for the second reference image, the second reference label information being associated with a category of an object in the second reference image; and using the second reference image and the second reference label information for the second reference image to further update the image recognition engine.

10 . The device according to claim 8 , wherein generating the characterization information for the first reference image includes:
generating weight information for the Gaussian mixture model based on the first reference image and initial expectation information for the Gaussian mixture model; and generating the characterization information for the first reference image based on the initial expectation information and the weight information.

11 . The device according to claim 10 , wherein generating the weight information for the Gaussian mixture model includes:
generating the weight information for the Gaussian mixture model using a kernel function based on the first reference image and the initial expectation information for the Gaussian mixture model.

12 . The device according to claim 10 , wherein the initial expectation information is a multi-dimensional vector, and vectors of at least two dimensions in the multi-dimensional vector are orthogonal.

13 . The device according to claim 10 , wherein the actions further include:
obtaining the initial expectation information for the Gaussian mixture model based on a third reference image with label information in the reference image set and third pre-existing label information for the third reference image, the third pre-existing label information being associated with a category of a third object in the third reference image.

14 . The device according to claim 13 , wherein the actions further include:
generating a reconstructed image based on the initial expectation information for the Gaussian mixture model; and updating the initial expectation information based on the reconstructed image.

15 . A computer program product that is tangibly stored on a non-transitory computer-readable medium and includes machine-executable instructions, wherein the machine-executable instructions, when executed, cause a machine to perform a method for image recognition, the method including:
generating, in an image recognition engine, characterization information for a first reference image in a reference image set by using a Gaussian mixture model; generating first reference label information for the first reference image based on the characterization information for the first reference image, the first reference label information being associated with a category of a first object in the first reference image; and updating the image recognition engine by determining the accuracy of the first reference label information for the first reference image.

16 . The computer program product according to claim 15 , wherein the method further includes:
generating, based on a second reference image without label information in the reference image set and by means of the updated image recognition engine, second reference label information for the second reference image, the second reference label information being associated with a category of an object in the second reference image; and using the second reference image and the second reference label information for the second reference image to further update the image recognition engine.

17 . The computer program product according to claim 15 , wherein generating the characterization information for the first reference image includes:
generating weight information for the Gaussian mixture model based on the first referen

Assignees

• Emc Ip Holding Co Llc

Inventors

• Wang Zijia
• Ni Jiacheng
• Jia Zhen
• Yang Wenbin

Classifications

• G06V10/82 Primary

  using neural networks · CPC title

• G06V20/00 Primary

  Scenes; Scene-specific elements (control of digital cameras H04N23/60) · CPC title

• G06V20/80

  Recognising image objects characterised by unique random patterns · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06F18/214

  Generating training patterns; Bootstrap methods, e.g. bagging or boosting · CPC title