Image processing method, device and system and electronic equipment

An image processing and image technology, applied in the field of image processing, can solve the problem of no spectacle lens reflection

Pending Publication Date: 2020-06-23
MEGVII BEIJINGTECH CO LTD
View PDF5 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At present, there are many works dedicated to solving the problem of glass reflection. However, when taking selfies in night scenes, the reflection of glasses lenses is stronger than that of ordinary glass reflections, which requires a special processing algorithm. Method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing method, device and system and electronic equipment
  • Image processing method, device and system and electronic equipment
  • Image processing method, device and system and electronic equipment

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] First, refer to figure 1An example electronic device 100 for implementing an image processing method, apparatus and system, and electronic device according to an embodiment of the present invention will be described.

[0035] Such as figure 1 Shown is a schematic structural diagram of an electronic device. The electronic device 100 includes one or more processors 102, one or more storage devices 104, an input device 106, an output device 108, and an image acquisition device 110. These components pass through a bus system 112 and / or other forms of connection mechanisms (not shown). It should be noted that figure 1 The components and structure of the electronic device 100 shown are only exemplary, not limiting, and the electronic device may also have other components and structures as required.

[0036] The processor 102 can be implemented in at least one hardware form of a digital signal processor (DSP), a field programmable gate array (FPGA), and a programmable logic...

Embodiment 2

[0043] This embodiment provides an image processing method, which can be executed by the aforementioned electronic device, see figure 2 The flow chart of the image processing method shown, the method mainly includes the following steps S202 to S204:

[0044] Step S202, performing region segmentation on the target image to obtain target regions in the target image.

[0045] The above-mentioned target image may be an image with a reflective area or a blurred area of ​​glasses. For example, the target image may be a night scene image, and the glasses lens of the portrait in the night scene image is caused by luminous objects such as mobile phone screens, computer screens, street lamps, or billboards. If there is a reflective area, or the target image can be blurred in some areas due to lens displacement or shaking during shooting. In order to eliminate the reflective area or blurred area in the target image, the neural network model obtained in advance can be used to segment th...

Embodiment approach 1

[0053] Embodiment 1: In this implementation, the region to be segmented is located according to the detected key points, and then the region to be segmented is segmented to the target region. Specifically, it can be executed with reference to the following steps (1) to (2):

[0054] Step (1): Use the key point detection model to perform key point detection on the target image, and determine the region to be segmented in the target image.

[0055] The above-mentioned key point detection model can be obtained by pre-training, and the key point detection model obtained by inputting the target image into pre-training is used to detect the key points in the target image (this key point can be the area to be segmented) by using the key point detection model obtained by pre-training key points) detection to obtain each key point on the target image related to the region to be segmented, and the region to be segmented in the target image can be determined according to the region where ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention provides an image processing method, device and system, and electronic equipment, and relates to the technical field of image processing, and the method comprises the steps: carrying outthe region segmentation of a target image, and obtaining a target region in the target image; and inputting the target image and the target area of the target image into an image processing model, sothat the image processing model performs image processing on the target area of the target image to obtain a processed image corresponding to the target image. According to the invention, the reflection of the spectacle lens in the selfie image caused by the luminous object during selfie in the night scene can be effectively removed, and the photographing quality at night and the user experienceare improved.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method, device and system, and electronic equipment. Background technique [0002] Spectacle lens reflections are caused by the reflection of light from environmental objects or mobile phone screens onto the spectacle lenses. In fact, common glass transparent objects will map environmental objects to the glass when taking pictures, which will affect the shooting effect, especially when taking selfies in night scenes, there may be reflections from the mobile phone screen on the glasses lenses, and these reflection colors block the eyes , which is quite different from the background and is relatively bright, which greatly affects the perception of the photo. As the proportion of people who use glasses increases, the demand for glasses reflection removal in night scene photography is also increasing. Therefore, glasses reflection removal has gra...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T5/00G06T7/11G06T7/187G06K9/00G06K9/34G06K9/62G06N3/04G06N3/08
CPCG06T5/005G06T5/003G06T7/11G06T7/187G06T2207/10004G06T2207/10016G06T2207/20081G06T2207/20084G06T2207/30201G06N3/084G06V40/172G06V10/267G06N3/045G06F18/241
Inventor 张亚驰刘一胶王竞晖刘江宇
Owner MEGVII BEIJINGTECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap