Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A method for extracting weak edge of cooking fume image, a cooking fume image recognition system and a cooking fume machine

An extraction method, a technique for weak edges

Inactive Publication Date: 2019-02-19
FOSHAN VIOMI ELECTRICAL TECH +1
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] At present, there are many algorithms for image edge detection and extraction, but they often rely on a large number of calculations and consume a lot of computing power to obtain more accurate edge detection results, which is not applicable to embedded image processing products.
Moreover, the traditional image edge extraction algorithm has a good effect on the strong edge with obvious gray value variation, but it is difficult to detect the weak edge of the image target area.

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
  • A method for extracting weak edge of cooking fume image, a cooking fume image recognition system and a cooking fume machine
  • A method for extracting weak edge of cooking fume image, a cooking fume image recognition system and a cooking fume machine
  • A method for extracting weak edge of cooking fume image, a cooking fume image recognition system and a cooking fume machine

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0034] Such as figure 1 As shown, a method for extracting weak edges of a lampblack image comprises the following steps:

[0035] 3-1, define a filter Y, the filter is a t*t matrix, and t is an odd number;

[0036] 3-2, make the filter Y traverse the oil fume image, when the filter Y traverses the oil fume image, it overlaps with the corresponding area in the oil fume image, and z is the mark of the corresponding area when the filter Y traverses the oil fume image;

[0037] Calculate the gray value of the oil fume image where the central pixel of the filter is located at each position and the gray value of the oil fume image where other pixels are located in the neighborhood of the central pixel, and calculate the filter at each position according to the formula (I). The edge detection value of the central pixel at the position X z ,

[0038]

[0039] f and g are the matrix numbers of pixels, 1≤f≤t, 1≤g≤t, e is the gray value of the soot image where the pixel of the filt...

Embodiment 2

[0048] A method for extracting weak edges of an oil fume image, other features are the same as those in Embodiment 1, except that the filter Y is a 3*3 matrix.

[0049] The weight coefficients of the filter Y include α 1,1 、α 1,2 、α 1,3 、α 2,1 、α 2,2 、α 2,3 、α 3,1 、α 3,2 、α 3,3 , α 1,1 、α 1,2 、α 1,3 、α 2,1 、α 2,2 、α 2,3 、α 3,1 、α 3,2 、α 3,3 All are positive integers.

[0050] Specifically, a 2,2 = 4; α 1,1 = α1,3 = α 3,1 = α 3,3 = 1; α 1,2 = α 2,1 = α 2,3 = α 3,2 =2.

[0051] In this embodiment, a 3*3 filter Y is used, which has the characteristics of small calculation amount and simple calculation.

Embodiment 3

[0053] A lampblack image recognition system, comprising an image acquisition unit and an image processing unit, the image acquisition unit is electrically connected to the image processing unit; the image processing unit extracts the edge of the lampblack image based on the weak edge extraction method of the lampblack image in embodiment 1 or 2.

[0054] The oil fume image recognition system adopts the weak edge extraction method of the oil fume image based on wavelet transform, and can obtain a relatively accurate weak edge extraction effect of the oil fume image with only a small amount of calculation, thereby facilitating further analysis and processing of the oil fume.

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

A method for extracting weak edge of cooking fume image, a cooking fume proces system and a cooking fume hood. The method comprises the following steps of: 3-1, defining a filter Y; 3-2, using that filter Y to traverse the oil fume image, and calculating the edge detection value Xz of the center pixel point of the filter at each position; 3-3, subtracting that edge detection value Xz of the centerpixel point of the filter at each position from the gray value of other pixel points in the neighborhood of the center pixel point one by one, and judging whet the absolute value of each difference value at the same position is greater than the threshold value Delta; The absolute value of the difference is more than the threshold value, and the edge points are judged and marked; 3-4, that filtertraverses the entire denoise image to obtain all the marked edge points. The invention is based on wavelet transform, and can obtain more accurate weak edge extraction effect of oil fume image withoutlarge calculation amount.

Description

technical field [0001] The invention relates to the technical field of oil fume detection, in particular to a method for extracting weak edges of an oil fume image, an oil fume image recognition system and a range hood. Background technique [0002] The edge is one of the important features of the image, and the edge refers to the set of pixels with a step change in the gray level of the surrounding pixels or a roof change. Edge detection is mainly the measurement, detection and location of grayscale changes. Edge detection and extraction is a basic problem in image processing and computer vision. The purpose of edge detection is to identify points with obvious brightness changes in digital images, so as to extract the edges of the target area and eliminate non-target areas in the image. [0003] At this stage, there are many algorithms for image edge detection and extraction, but they often rely on a large amount of calculation and consume a lot of computing power to obtai...

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): G06T7/13G06T7/168G06T5/00G06T5/20F24C15/20
CPCG06T5/20G06T7/13G06T7/168F24C15/2021G06T2207/20064G06T5/70
Inventor 陈小平陈超李思成
Owner FOSHAN VIOMI ELECTRICAL TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com