Granted Patent B2

US 12,732,691 · App. 17/344,961 · Granted Sep 8, 2026

Inventors: Danian Chen (Shanghai, CN); Xiaobin Gu (Shanghai, CN); Wenzhao Liang (Shanghai, CN)

Assignee: SHANGHAI ZHANGMEN SCIENCE AND TECHNOLOGY CO., LTD.

H04N5/23222H04N1/00209H04N1/00244H04N5/23225H04N5/232939H04N2201/0084

Abstract

Claims (60)

1 . A photographing method, the method comprising:

acquiring a first image through a camera module;

determining composition prompt information suitable for the first image;

adding the composition prompt information in a display area of the first image, so that a user adjusts the camera module according to the composition prompt information;

acquiring real-time images through the camera module during the adjustment by the user, wherein the real-time images are a series of images including the first image and the second image changed from the first image;

determining and displaying scores of the real-time images to the user so as to assist the user in completing the adjustment, wherein determining the scores of the real-time images comprises calculating the scores of the real-time images according to the real-time images and a score regression model, wherein the score regression model is generated by training sample images which have been labeled with scores;

after the user completes the adjustment, acquiring the second image through the camera module;

determining photographing parameters suitable for the second image; and

photographing the second image based on the photographing parameters.

2 . The method according to claim 1 , wherein determining the composition prompt information suitable for the first image comprising:

determining scenario information and the composition mode according to the first image; and

determining the composition prompt information suitable for the first image according to the scenario information and the composition mode.

3 . The method according to claim 2 , wherein determining the scenario information and the composition mode according to the first image comprising:

determining the scenario information and the composition mode according to the first image and a recognition model, wherein the recognition model is generated by training sample images which have been labeled with scenario information and composition modes; or

transmitting the first image to a server device, and receiving the scenario information and the composition mode of the first image transmitted by the server device, wherein the server device determines the scenario information and the composition mode of the first image according to the first image and the recognition model, and wherein the recognition model is generated by training sample images which have been labeled with scenario information and composition modes.

4 . The method according to claim 3 , wherein transmitting the first image to the server device comprising:

compressing the first image, and transmitting the compressed first image to the server device, so that the server device determines the scenario information and the composition mode of the first image according to the compressed first image and the recognition model.

5 . The method according to claim 1 , wherein determining the scores of the real-time images further comprising:

transmitting the real-time images to a server device, and receiving the scores of the real-time images transmitted by the server device, wherein the server device calculates the scores of the real-time images according to the real-time images and the score regression model, and wherein the score regression model is generated by training sample images which have been labeled with scores.

6 . The method according to claim 5 , wherein transmitting the real-time images to the server device comprising:

compressing the real-time images, and transmitting the compressed real-time images to the server device, so that the server device calculates the scores of the real-time images according to the compressed real-time images and the score regression model.

7 . The method according to claim 1 , wherein the method further comprising:

determining a preset area to which the real-time image belongs based on positioning information acquired when the real-time image is acquired; and

calculating the scores of the real-time images according to the real-time images and the score regression model, comprising:

calculating the scores of the real-time images according to the real-time images and the score regression model corresponding to the preset area, wherein the score regression model is generated by training sample images which have been labeled with scores and are related to the preset area.

8 . The method according to claim 1 , wherein, after the user completes the adjustment, acquiring the second image through the camera module comprising:

determining whether the user has completed the adjustment; and

if the adjustment has been completed, performing autofocus, and acquiring a focused second image through the camera module.

9 . The method according to claim 8 , wherein determining whether the user has completed the adjustment comprising:

obtaining gyroscope information, and determining whether the user has completed the adjustment according to the gyroscope information.

10 . The method according to claim 1 , wherein determining the photographing parameters suitable for the second image comprising:

recognizing a focus area for the second image;

determining brightness of the focus area and brightness of a global area of the second image; and

determining the photographing parameters suitable for the second image according to the brightness of the focus area and the brightness of the global area of the second image.

11 . The method according to claim 10 , wherein determining the photographing parameters suitable for the second image according to the brightness of the focus area and the brightness of the global area of the second image comprising:

determining the photographing parameters suitable for the second image according to the brightness of the focus area and the brightness of the global area of the second image and a parameter statistical model, wherein the parameter statistical model is generated by training sample images which have been labeled with brightness of the focus area, brightness of the global area and photographing parameters; or

transmitting the brightness of the focus area and the brightness of the global area of the second image to a server device, and receiving the photographing parameters suitable for the second image transmitted by the server device, wherein the server device determines the photographing parameters suitable for the second image based on the brightness of the focus area and the brightness of the global area of the second image and the parameter statistical model, wherein the parameter statistical model is generated by training sample images which have been labeled with brightness of the focus area, brightness of the global area, and photographing parameters.

12 . The method according to claim 11 , wherein before determining composition prompt information suitable for the first image currently acquired through the camera module according to the first image, the method further comprises:

obtaining positioning information; and

determining whether the first image belongs to a preset area according to the positioning information, and if the first image belongs to the preset area, displaying recommended images belonging to the preset area to a user.

13 . The method according to claim 12 , wherein determining whether the first image belongs to the preset area according to the positioning information, and if the first image belongs to the preset area, displaying the recommended images belonging to the preset area to the user comprising:

transmitting location information to the server device, obtaining the recommended images belonging to the preset area from the server device, and displaying the recommended images to the user.

14 . A photographing device, wherein the device comprising a memory for storing computer program instructions and a processor for executing computer program instructions, and wherein the computer program instructions, when executed by the processor, trigger the device to perform a method comprising:

acquiring a first image through a camera module;

determining composition prompt information suitable for the first image;

adding the composition prompt information in a display area of the first image, so that a user adjusts the camera module according to the composition prompt information;

acquiring real-time images through the camera module during the adjustment by the user, wherein the real-time images are a series of images including the first image and the second image changed from the first image;

determining and displaying scores of the real-time images to the user so as to assist the user in completing the adjustment, wherein determining the scores of the real-time images comprises calculating the scores of the real-time images according to the real-time images and a score regression model, wherein the score regression model is generated by training sample images which have been labeled with scores;

after the user completes the adjustment, acquiring the second image through the camera module;

determining photographing parameters suitable for the second image; and

photographing the second image based on the photographing parameters.

15 . A non-transitory computer-readable medium having computer program instructions stored thereon, the computer-readable instructions being executable by a processor to implement a method comprising:

acquiring a first image through a camera module;

determining composition prompt information suitable for the first image;

adding the composition prompt information in a display area of the first image, so that a user adjusts the camera module according to the composition prompt information;

acquiring real-time images through the camera module during the adjustment by the user, wherein the real-time images are a series of images including the first image and the second image changed from the first image;

determining and displaying scores of the real-time images to the user so as to assist the user in completing the adjustment, wherein determining the scores of the real-time images comprises calculating the scores of the real-time images according to the real-time images and a score regression model, wherein the score regression model is generated by training sample images which have been labeled with scores;

after the user completes the adjustment, acquiring the second image through the camera module;

determining photographing parameters suitable for the second image; and

photographing the second image based on the photographing parameters.

Assignments (1)

Priority Claims (1)

Continuity (2)

References Cited (13)