Unlock instant, AI-driven research and patent intelligence for your innovation.

Image anomaly detection method and device, terminal equipment and readable storage medium

A technology of image abnormality and detection method, which is applied in the field of image processing, can solve problems affecting imaging effects, abnormal black spots or white spots, lens dust adhesion, etc., and achieve the effect of improving user experience

Pending Publication Date: 2022-07-29
ONEPLUS TECH SHENZHEN
View PDF0 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Since the production line cannot be completely dust-free, it is inevitable that there may be dust attached to the lens, which will cause some abnormal black spots or white spots in the lens imaging, which will affect the imaging effect
However, there is no better way in the prior art to detect dust and other stolen objects in the camera module, and give the position information, area size, etc. in the image

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 anomaly detection method and device, terminal equipment and readable storage medium
  • Image anomaly detection method and device, terminal equipment and readable storage medium
  • Image anomaly detection method and device, terminal equipment and readable storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0059] Please refer to figure 1 This embodiment proposes an image anomaly detection method, which can be used for factory inspection of the imaging quality of a shooting lens of a terminal device such as a mobile phone, tablet, etc., especially for the image obtained due to dust adhesion on the lens. like figure 2 the white area shown, etc. This method can well detect whether there is a problem of dust adhesion, as well as the specific location of abnormal areas after dust imaging, so as to facilitate subsequent image restoration to solve imaging quality problems, etc.

[0060] It should be understood that the black / white area described in this embodiment is not limited to an image with a grayscale of 255 or 0, and may also refer to a situation where the texture and color of the pixels in the abnormal area are inconsistent with surrounding pixels. The image abnormality detection method will be described below.

[0061] Step S110 , performing color space conversion on the t...

Embodiment 2

[0099] Please refer to Image 6 , this embodiment proposes an image abnormality processing method. For example, when there are some black / white abnormal areas in the image, such as texture, color, etc., are processed by the image abnormality processing method. Improve the efficiency of image exception processing, etc.

[0100] Step S210, when it is detected that the input image includes an abnormal area, calculate the texture matching degree and the color matching degree between the abnormal area and the local area surrounding the abnormal area.

[0101] Exemplarily, a partial image including an abnormal area may be intercepted from the input target image, and the partial image is composed of the abnormal area and a partial area surrounding the abnormal area. Wherein, the local area refers to a pixel area with normal imaging and located around the abnormal point.

[0102] In this embodiment, by judging whether the texture and color between the abnormal area and the surroundi...

Embodiment 3

[0133] Please refer to Figure 12 , this embodiment proposes an image repair method for repairing an abnormal area in an image. Exemplarily, the image inpainting method includes:

[0134]Step S410, on the boundary of the abnormal area in the target image, take the pixel on the boundary as the center, select a pixel block, calculate the filling priority of the pixel based on the relevant information of the pixel block, and traverse all the pixels on the boundary. point to get the filling priority of each pixel on the border.

[0135] In this embodiment, for the input target image including the abnormal area, the position information and area size of the abnormal area can be obtained, including the position of the boundary, etc., and the area in the image except the abnormal area that displays normal (that is, normal area). It is worth noting that the abnormal area can be black / white spots, reflected light spots, etc. appearing in the image that will affect the display effect...

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 embodiment of the invention provides an image anomaly detection method and device, terminal equipment and a readable storage medium. The method comprises the steps of performing color space conversion on a target image and performing pixel enhancement processing on the converted image to obtain an enhanced image; carrying out plane coordinate axis integral projection on the enhanced image to obtain an integral projection waveform under each coordinate axis; and when at least two adjacent wave crests exist in each integral projection waveform, determining the position of a marking box where the abnormal region in the target image is located according to the corresponding wave crest coordinates in the integral projection waveform under each coordinate axis. According to the invention, abnormal area detection is carried out on the image shot by the lens, so that the method can be used for detecting and positioning whether some black / white abnormal areas appear in the imaging image due to the fact that dust is attached to the shooting lens of the terminal equipment.

Description

technical field [0001] The present application relates to the technical field of image processing, and in particular, to an image abnormality detection method, apparatus, terminal device and readable storage medium. Background technique [0002] Usually, a hand-held terminal such as a mobile phone needs to perform a factory test of the lens imaging before leaving the factory to ensure the quality of the lens imaging. Since it is impossible for the production line to be absolutely dust-free, it is inevitable that there may be dust adhesion in the lens, which will lead to some abnormal black or white spots in the imaging of the lens, which will affect the imaging effect. However, in the prior art, there is no better way to detect dirt such as dust in the camera module, and give the position information, area size, etc. in the image. SUMMARY OF THE INVENTION [0003] In view of this, in order to overcome the deficiencies in the prior art, the present application provides an ...

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): G06T7/00G06T7/40G06T7/73G06T5/00G06V10/75G06K9/62
CPCG06T7/0004G06T7/40G06T7/73G06T2207/10004G06T2207/10024G06T2207/20192G06T2207/30108G06T5/73
Inventor 王亮白宏益
Owner ONEPLUS TECH SHENZHEN