Digital image processing method and digital image processing device

A technology of digital images and processing methods, applied in the computer field, can solve the problems of skin texture differences, inability to display processing effects in real time, and inability to realize automatic processing, and achieve the effect of inconspicuous traces

Active Publication Date: 2015-07-29
TENCENT TECH (SHENZHEN) CO LTD
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] The disadvantage of the first type of method is that it causes changes in the skin texture in the digital image of the face, making the skin texture difference between the processed area and the unprocessed area obvious, and the traces of artificial processing are obvious.
[0007] The di

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
  • Digital image processing method and digital image processing device
  • Digital image processing method and digital image processing device
  • Digital image processing method and digital image processing device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0051] In this embodiment, the processing of the R channel of the digital image is taken as an example for description, and the manner of processing the G channel and the B channel of the digital image is the same. In this embodiment, the dark circle and its surrounding area in the face image are taken as the image to be processed.

[0052] Such as figure 2 As shown, the R channel of the image to be processed is used as the source image (denoted as Image), and the following steps are performed for the source image Image:

[0053]Step 201: Perform Gaussian blur processing with a large radius on the source image Image to obtain a blurred image (denoted as ImageA). The radius of Gaussian blur processing here is generally 10 to 16 pixels

[0054] After processing in this step, the display effect of the blurred image ImageA is: the R value of the pixel whose original R value is larger than the surrounding area will become smaller, and the R value of the pixel whose original R va...

Embodiment 2

[0082] This embodiment introduces a specific digital image processing device, such as Figure 4 It is a schematic diagram of the structure of the device, including:

[0083] At least one processor 401 , at least one memory 402 , at least one network interface 403 , at least one input device 404 (such as a mouse, keyboard, etc.), at least one output device 405 (such as a display screen), and at least one communication bus 406 .

[0084] Wherein, the network interface 403 may include a standard wired interface, a wireless interface (such as a WI-FI interface), and the like.

[0085] The communication bus 406 is used to implement connection communication between these components.

[0086] The memory 402 may be a high-speed RAM memory, or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory 402 may also be at least one storage device located far away from the aforementioned processor 401 . Such as Figure 4 As shown, the memory ...

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 a digital image processing method and a digital image processing device. The digital image processing method comprises that the following steps are carried out respectively in allusion to a primary color channel of an image to be processed to acquire a processed image. The steps comprise that the primary color channel of the image to be processed acts as a source image, and Gaussian Blur processing is carried out on the source image to acquire a blur effect image; a difference image is generated through the blur effect image and the source image; and more than one time of low-pass filtering is carried out on the difference image, all filtering result acquired after low-pass filtering and the source image are overlaid, and the overlapping mode is that a primary color channel component value of each pixel in all of the filtering results and a primary color channel component value of the pixel in the source image are added in allusion to each pixel; wherein the radius of low-pass filtering is less than the radius of Gaussian Blur processing, and the radiuses of each time of low-pass filtering are different when the number of low-pass filtering times is greater than one. According to the invention, beautification processing in allusion to digital images can be realized quickly and automatically, and the processing trace is not obvious.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a digital image processing method and device. Background technique [0002] At present, people's demand for digital image processing, especially for digital image beautification of people is increasing day by day. With the increase of this demand, some methods for beautifying people's images, especially facial images, have appeared. These methods broadly fall into two categories: [0003] The first category is to improve local image brightness. Because the color of spots, dark circles, etc. is relatively dark, the brightness presented on the digital image of the person's face is low, and the purpose of beautifying the digital image of the person can be achieved by increasing the brightness of the corresponding area. [0004] The second category is sample-based image inpainting. Take the image area with smooth skin on the face image as a sample, and repair spots, eye ...

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
IPC IPC(8): G06T5/00
Inventor 蒋兴华
Owner TENCENT TECH (SHENZHEN) 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