Method and device for detecting object in image

A target detection and image technology, applied in the field of image processing, can solve the problems of high chip application cost, complex high-frequency detection scheme, detection of image text, details or edge interference, etc., to achieve accurate acquisition, low application cost, and processing algorithm simple effect

Inactive Publication Date: 2017-02-22
LETV HLDG BEIJING CO LTD +1
View PDF7 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to solve the above problems, an embodiment of the present invention provides a method for detecting an object in an image and a device for detecting an object in an image, so as to solve the problem that the existing high-frequency detection schemes are relatively complicated, and the application cost on the chip is high, and the high-frequency During the detection process, the noise in the image will also be detected, which will cause interference to the text, details or edges in the detection 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
  • Method and device for detecting object in image
  • Method and device for detecting object in image
  • Method and device for detecting object in image

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0047] For the detection of the target in the image, different detection algorithms correspond to specific color spaces. In the embodiment of the present invention, the technical solutions provided are implemented based on the RGB color space. see figure 1 , which is a flowchart of a method for detecting an object in an image provided by an embodiment of the present invention, the method specifically includes:

[0048] S01. Extract grayscale information of pixels in an image, where the pixels include pixels to be detected and pixels adjacent to the pixels to be detected;

[0049] Each digital image is composed of pixels. In the RGB color space, a pixel is represented by three color channels of red, green, and blue (RGB). Each color channel constitutes a sub-pixel, and the pixels behind each sub-pixel Light sources can all exhibit different brightness levels. The gray scale represents the level of different brightness from the darkest to the brightest. The color change of each ...

Embodiment 2

[0069] In the embodiment of the present invention, such as image 3 As shown, based on the foregoing embodiments, according to the obtained gray scale difference, when the first gray scale difference is smaller than the first preset threshold, the method further includes:

[0070] S04. Perform secondary detection on the pixel to be detected;

[0071] Due to the fact that there is not much difference between the grayscale of the pixel of the text in the image and the grayscale of the background pixel, the first grayscale difference is smaller than the first preset threshold, so it is necessary to further perform a secondary detection and judgment on the detected pixel to confirm that the pixel to be detected Whether the pixel is the target pixel to achieve fine detection.

[0072] The specific process of the secondary detection is carried out according to the following scheme, refer to Figure 4 :

[0073] S041. Select pixels other than the pixels to be detected in the image...

Embodiment 3

[0106] The embodiment of the present invention also provides a target detection device in an image, including an information acquisition unit 01, a gray scale difference acquisition unit 02, and a judgment unit 03, such as Figure 9 shown, where:

[0107] The information acquiring unit 01 is used for extracting gray scale information of pixels in an image, the pixels include a pixel to be detected and pixels adjacent to the pixel to be detected.

[0108] Specifically, the information acquiring unit 01 needs to acquire the gray scale information of the RGB sub-pixel of the pixel to be detected, and the gray scale information of the RGB sub-pixel of the pixel directly adjacent to the pixel to be detected.

[0109] The gray scale difference acquisition unit 02 is configured to acquire a first gray scale difference, where the first gray scale difference is the maximum value of the gray scale differences between the pixel to be detected and the adjacent pixel.

[0110] Optionally,...

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 belongs to the field of image processing, and relates to a method and device for detecting an object in an image. The method comprises the steps: extracting the gray scale information of pixels in the image, wherein the pixels comprise a to-be-detected pixel and pixels adjacent to the to-be-detected pixels; obtaining a first gray scale difference value, wherein the first gray scale difference value is the maximum value of the gray scale difference values of the to-be-detected pixel and the adjacent pixels; comparing the first gray scale difference value with a first threshold value, and judging that the to-be-detected pixel is the target pixel if the first gray scale difference value is greater than the first threshold value. The device comprises an information obtaining unit, a gray scale difference value obtaining unit, and a judgment unit. According to the embodiment of the invention, the method and device can precisely obtain the detail of the object in the image, and filter out the interference from the noise points in the image. An object detection processing algorithm is simple, and is low in the cost of application in a chip.

Description

technical field [0001] The embodiments of the present invention belong to the field of image processing, and in particular relate to a method for detecting an object in an image and a device for detecting an object in an image. Background technique [0002] In image processing, the places where the brightness or grayscale changes sharply in the image are called high-frequency components, such as text, details, and edge parts in the image; otherwise, they are called low-frequency components, such as large areas of color blocks in the image are low-frequency components. Components, that is, there are high-frequency components and low-frequency components in an image. In the process of target detection in the image, it is necessary to detect the high-frequency components in the image, especially the text, details or edges in the image, so as to distinguish them from other areas of the image and prevent the detected text, Details or edges become blurred. [0003] In the proces...

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): G06K9/46
CPCG06V10/44
Inventor 朱江
Owner LETV HLDG BEIJING 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