IP Library Granted Patent US 11,532,307
Granted Patent B2
US 11,532,307 · App. 16/615,255 · Granted Dec 20, 2022

Image processing apparatus and method

Inventors: Tianshi Chen (Shanghai, CN); Shuai Hu (Shanghai, CN); Xiaobing Chen (Shanghai, CN)
Assignee: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD
G10L15/26G10L15/063G10L15/1815G10L15/22G10L2015/223
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,532,307
App. No.
16/615,255
Granted
Dec 20, 2022
Kind
B2
Abstract

The present disclosure discloses an image processing device including: a receiving module configured to receive a voice signal and an image to be processed; a conversion module configured to convert the voice signal into an image processing instruction and determine a target area according to a target voice instruction conversion model, in which the target area is a processing area of the image to be processed; and a processing module configured to process the target area according to the image processing instruction and a target image processing model. The examples may realize the functionality of using voice commands to control image processing, which may save users' time spent in learning image processing software prior to image processing, and improve user experience.

Claims (53)

1. An image processing device, comprising:

a receiving circuit configured to receive a voice signal and an image to be processed;

a conversion circuit configured to convert the voice signal into an image processing instruction and obtain a target area according to a target voice instruction conversion model, wherein the target area is a processing area of the image to be processed; and

a processing circuit configured to:

obtain M image processing instructions from a storage device in a preset time window, wherein M is an integer greater than 1;

delete image processing instructions with identical functionalities in the M image processing instructions to obtain N image processing instructions, wherein N is an integer smaller than M; and

process the target area according to the image processing instruction converted from the voice signal, the N image processing instructions obtained from the storage device and a target image processing model.

2. The image processing device of claim 1 , wherein the conversion circuit is configured to:

convert the voice signal into text information through a voice recognition technology,

convert the text information into the image processing instruction through a natural language processing technology and the target voice instruction conversion model, and

divide the image to be processed into areas according to granularity of semantic areas in the image processing instruction and an image recognition technology, and obtain the target area.

3. The image processing device of claim 1 , wherein the conversion circuit is further configured to:

convert the voice signal into the image processing instruction through the voice recognition technology, a semantic understanding technology, and the target voice instruction conversion model, and

divide the image to be processed into areas according to the granularity of semantic areas in the image processing instruction and the image recognition technology, and obtain the target area.

4. The image processing device of claim 1 , wherein the image processing device further includes:

the storage device configured to store the text information, the image processing instruction, or the target area.

5. The image processing device of claim 1 , wherein the conversion circuit is configured to:

implement adaptive training on a voice instruction conversion model to obtain the target voice instruction conversion model.

6. The image processing device of claim 1 , wherein the image processing device further includes:

a training circuit configured to convert the voice signal into the prediction instruction according to the voice instruction conversion model, determine the correlation coefficients between the prediction instruction and the corresponding instruction set, and optimize the voice instruction conversion model according to the correlation coefficients between the prediction instruction and the corresponding instruction set to obtain the target voice instruction conversion model.

7. The image processing device of claim 1 , wherein the image processing device is configured to:

implement adaptive training on the image processing model to obtain the target image processing model.

8. The image processing device of claim 7 , wherein the image processing device is further configured to:

process the image to be processed according to the image processing model to obtain the predicted image;

determine correlation coefficients between the predicted image and the corresponding target image; and

optimize the image processing model according to the correlation coefficients between the predicted image and the corresponding target image to obtain the target image processing model.

9. An image processing method including:

receiving a voice signal and an image to be processed,

converting a voice signal into an image processing instruction and to obtain a target area according to a target voice instruction conversion model, wherein the target area is a processing area of the image to be processed,

obtain M image processing instructions from a storage device in a preset time window, wherein M is an integer greater than 1,

delete image processing instructions with identical functionalities in the M image processing instructions to obtain N image processing instructions, wherein N is an integer smaller than M, and

processing the target area according to the image processing instruction converted from the voice signal, the N image processing instructions obtained from the storage device, and the target image processing model.

10. The method of claim 9 , wherein the converting of the voice signal into the image processing instruction and the obtaining of the target area according to the target voice instruction conversion model includes:

converting the voice signal into text information through a voice recognition technology,

converting the text information into the image processing instruction through a natural language processing technology and the target voice instruction conversion model, and

dividing the image to be processed into areas according to granularity of semantic areas in the image processing instruction and an image recognition technology and obtaining the target area.

11. The method of claim 9 , wherein the converting of the voice signal into the image processing instruction and the target area according to the target voice instruction conversion model includes:

converting the voice signal into the image processing instruction through the voice recognition technology, a semantic understanding technology, and the target voice instruction conversion model, and

dividing the image to be processed into areas according to the granularity of semantic areas in the image processing instruction and the image recognition technology and obtaining the target area.

12. The method of claim 9 , wherein the method further includes:

storing the text information, the image processing instruction, or the target area.

13. The method of claim 9 , wherein prior to the receiving of the voice signal and the image to be processed, the method further includes:

implementing an adaptive training on the voice instruction conversion model to obtain the target voice instruction conversion model.

14. The method of claim 13 , wherein the implementing of the adaptive training on the voice instruction conversion model to obtain the target voice instruction conversion model includes:

converting the voice signal into the prediction instruction according to the voice instruction conversion model;

determining the correlation coefficients between the prediction instruction and the corresponding instruction set; and

optimizing the voice instruction conversion model according to the correlation coefficients between the prediction instruction and the corresponding instruction set to obtain the target voice instruction conversion model.

15. The method of claim 9 , wherein prior to the receiving of the voice signal and the image to be processed, the method further includes:

implementing the adaptive training on the image processing model to obtain the target image processing model.

16. The method of claim 15 , wherein the implementing of the adaptive training on the image processing model to obtain the target image processing model includes:

processing the image to be processed according to the image processing model to obtain the predicted image;

determining the correlation coefficients between the predicted image and the corresponding target image; and

optimizing the image processing model according to the correlation coefficients between the predicted image and the corresponding target image to obtain the target image processing model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 20, 2019
From: CHEN, TIANSHI; HU, SHUAI; CHEN, XIAOBING
To: SHANGHAI CAMBRICON INFORMATION TECHNOLOGY CO., LTD
Reel/Frame 051064/0562 →
Priority Claims (3)
CN 201710913131.2 · Sep 29, 2017 · national
CN 201710913272.4 · Sep 29, 2017 · national
CN 201711121244.5 · Nov 14, 2017 · national
Continuity (1)
Related Publication 20200168227A1 · May 28, 2020