CN109990741A - Chinese chestnut detection system based on image processing techniques - Google Patents
Chinese chestnut detection system based on image processing techniques Download PDFInfo
- Publication number
- CN109990741A CN109990741A CN201711494789.0A CN201711494789A CN109990741A CN 109990741 A CN109990741 A CN 109990741A CN 201711494789 A CN201711494789 A CN 201711494789A CN 109990741 A CN109990741 A CN 109990741A
- Authority
- CN
- China
- Prior art keywords
- image
- chinese chestnut
- unit
- chestnut
- calibration plate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/28—Measuring arrangements characterised by the use of optical techniques for measuring areas
- G01B11/285—Measuring arrangements characterised by the use of optical techniques for measuring areas using photoelectric detection means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The Chinese chestnut detection system based on image processing techniques that the invention discloses a kind of, including image acquisition unit, image processing unit and image identification unit, described image acquiring unit is for obtaining Chestnut Image and calibration plate image, and by Chestnut Image and calibration plate image transmitting to image processing unit;Described image processing unit is used to carrying out the Chestnut Image into gradation conversion, binaryzation, removal noise and edge detection, obtains the edge contour image of Chinese chestnut;Described image recognition unit is used to calculate the projected pixel of Chinese chestnut according to the edge contour image, calibration plate sum of all pixels is calculated according to calibration plate image, the ratio of Chinese chestnut projected pixel, calibration plate sum of all pixels and calibration plate actual size is calculated to the projected area and defect area of Chinese chestnut.The detection system can detect the external sort of Chinese chestnut automatically, can detect the shape size of Chinese chestnut, defect area size, detection efficiency is fast, accuracy is high.
Description
Technical field
The present invention relates to a kind of Chinese chestnut Quality Detection technical field, in particular to a kind of Chinese chestnut based on image processing techniques
Detection system.
Background technique
China is export of farm produce big country, and Chinese chestnut occupies very big ratio in agricultural products in China outlet, to the product of agricultural product
Quality detection is most important, detect Chinese chestnut size and whether it is defective be basis that Chinese chestnut is classified automatically, how Chinese chestnut is carried out
Rapidly and accurately non-destructive testing is research emphasis.
Summary of the invention
In view of this, the technical problem to be solved in the present invention is that providing a kind of Chinese chestnut detection based on image processing techniques
System detects Chinese chestnut external sort by image processing techniques automatically, and detection efficiency is high, accuracy is high.
The present invention solves above-mentioned technical problem by following technological means:
The Chinese chestnut detection system based on image processing techniques that the present invention provides a kind of, including image acquisition unit, image
Processing unit and image identification unit, described image acquiring unit is for obtaining Chestnut Image and calibration plate image, and by Chinese chestnut
Image and calibration plate image transmitting are to image processing unit;Described image processing unit is used to the Chestnut Image carrying out gray scale
Conversion, binaryzation, removal noise and edge detection, obtain the edge contour image of Chinese chestnut;Described image recognition unit is used for root
The projected pixel that Chinese chestnut is calculated according to the edge contour image calculates calibration plate sum of all pixels according to calibration plate image, by Chinese chestnut
The ratio of projected pixel, calibration plate sum of all pixels and calibration plate actual size calculates the projected area and defect area of Chinese chestnut.
Further, described image processing unit includes gradation conversion unit, what the gradation conversion unit was used to will acquire
Chestnut Image is converted to gray level image.
Further, described image processing unit further includes binaryzation converting unit, and the binaryzation converting unit is used for will
Greyscale image transitions are binary image.
Further, described image processing unit further includes noise removing unit, and the noise removing unit is used for two-value
Change image and carries out smothing filtering removal noise.
Further, described image processing unit further includes edge detection unit, and the edge detection unit will be for that will remove
The binary image of noise carries out edge extracting using Canny operator, obtains edge contour image.
Beneficial effects of the present invention:
It is high to obtain clarity by image acquisition unit for Chinese chestnut detection system based on image processing techniques of the invention
Chestnut Image obtains edge contour image after being handled Chestnut Image, obtain Chinese chestnut projection image according to edge contour image
The size of the sum of all pixels of projected pixel sum combination calibration plate and calibration plate is calculated from the formula Chinese chestnut throwing by plain sum
The size of shadow area and defect area.The detection system can detect the external sort of Chinese chestnut automatically, can detect the shape of Chinese chestnut
Size, defect area size, detection efficiency is fast, accuracy is high.
Detailed description of the invention
The invention will be further described with reference to the accompanying drawings and examples.
Fig. 1 is the functional block diagram of the Chinese chestnut detection system embodiment of the invention based on image processing techniques.
Specific embodiment
Below with reference to attached drawing, the present invention is described in detail.
As shown in Figure 1, showing a kind of reality of Chinese chestnut detection system based on image processing techniques of offer of the invention
Example, including image acquisition unit, image processing unit and image identification unit are applied, described image acquiring unit is for obtaining Chinese chestnut
Image and calibration plate image, and by Chestnut Image and calibration plate image transmitting to image processing unit;Described image processing unit
For the Chestnut Image to be carried out gradation conversion, binaryzation, removal noise and edge detection, the edge contour figure of Chinese chestnut is obtained
Picture;Described image recognition unit is used to calculate the projected pixel of Chinese chestnut according to the edge contour image, according to calibration plate image
Calibration plate sum of all pixels is calculated, the ratio of Chinese chestnut projected pixel, calibration plate sum of all pixels and calibration plate actual size is calculated
The projected area and defect area of Chinese chestnut.The Chinese chestnut detection system of image processing techniques of the invention, passes through image acquisition unit
Chestnut Image to be detected and calibration plate image are obtained, image acquisition unit includes light source, CCD camera, camera lens and image pick-up card.
Light source range of exposures is in CCD camera coverage, and with the irradiation of front field type, uniform illumination cannot generate shade, prevent mirror
Face reflection, furthermore it is reflected into the light of the Chinese chestnut overwhelming majority in CCD camera, the Chestnut Image clarity obtained in this way is high, mentions
The acquisition quality of hi-vision directly determines the quality of testing result.In order to improve the accuracy of detection Chinese chestnut projected area size,
Using the calibration plate of known dimensions as reference target, first by the bat of Chinese chestnut to be measured and calibration plate in an image, then into
Row segmentation, since the size dimension of calibration plate is it is known that calculate sum of all pixels according to calibration plate image, further according to the side of Chestnut Image
Edge contour images calculate Chinese chestnut projected pixel sum, can calculate Chinese chestnut projected area and defect area according to formula.
Image processing unit includes gradation conversion unit, the Chestnut Image conversion that the gradation conversion unit is used to will acquire
For gray level image.Image processing unit further includes binaryzation converting unit, and the binaryzation converting unit is used for gray level image
Be converted to binary image.Described image processing unit further includes noise removing unit, and the noise removing unit is used for two
Value image carries out smothing filtering and removes noise.Described image processing unit further includes edge detection unit, the edge detection
The binary image that unit is used to remove noise carries out edge extracting using Canny operator, obtains edge contour image.Using
Median filtering method carries out denoising to acquired image, its advantage is that inhibit not make edge blurry while noise, and gram
It takes image detail caused by linear filter to obscure, its principle is all pixels in the wicket centered on certain point
Gray scale sequentially arranges by size, takes intermediate value as the gray value of the point, to achieve the purpose that filter noise.Canny operator is endeavoured
Solves noise problem bring speckle phenomena using dual threshold method in finding image gradient local maximum.
Chinese chestnut detection system based on image processing techniques acquires Chestnut Image and calibration plate figure by image acquisition unit
As after, then Chestnut Image is handled, obtains the edge contour image of Chinese chestnut, image identification unit is according to edge contour image
Calculate the projected pixel sum R of Chinese chestnut1, calibration plate sum of all pixels R2With calibration plate actual size C2Calculate Chinese chestnut projected area and
Defect area size C1, calculation formula C1=(R1/R2)C2。
Chinese chestnut detection system provided by the invention based on image processing techniques, obtains clarity by image acquisition unit
High Chestnut Image obtains edge contour image after being handled Chestnut Image, obtain Chinese chestnut according to edge contour image and throw
The size of the sum of all pixels of projected pixel sum combination calibration plate and calibration plate is calculated from the formula plate by shadow sum of all pixels
The size of chestnut projected area and defect area.The detection system can detect the external sort of Chinese chestnut automatically, can detect Chinese chestnut
Shape size, defect area size, detection efficiency is fast, accuracy is high.
Finally, it is stated that the above examples are only used to illustrate the technical scheme of the present invention and are not limiting, although referring to compared with
Good embodiment describes the invention in detail, those skilled in the art should understand that, it can be to skill of the invention
Art scheme is modified or replaced equivalently, and without departing from the objective and range of technical solution of the present invention, should all be covered at this
In the scope of the claims of invention.
Claims (5)
1. a kind of Chinese chestnut detection system based on image processing techniques, which is characterized in that including image acquisition unit, image procossing
Unit and image identification unit, described image acquiring unit is for obtaining Chestnut Image and calibration plate image, and by Chestnut Image
With calibration plate image transmitting to image processing unit;Described image processing unit is used to the Chestnut Image carrying out gray scale to turn
It changes, binaryzation, remove noise and edge detection, obtain the edge contour image of Chinese chestnut;Described image recognition unit is used for basis
The edge contour image calculates the projected pixel of Chinese chestnut, calculates calibration plate sum of all pixels according to calibration plate image, Chinese chestnut is thrown
The ratio of image element, calibration plate sum of all pixels and calibration plate actual size calculates the projected area and defect area of Chinese chestnut.
2. the Chinese chestnut detection system described in claim 1 based on image processing techniques, which is characterized in that described image processing is single
Member includes gradation conversion unit, and the Chestnut Image that the gradation conversion unit is used to will acquire is converted to gray level image.
3. the Chinese chestnut detection system based on image technique as claimed in claim 2, which is characterized in that described image processing unit
It further include binaryzation converting unit, the binaryzation converting unit is used to greyscale image transitions be binary image.
4. the Chinese chestnut detection system based on image technique as claimed in claim 3, which is characterized in that described image processing unit
It further include noise removing unit, the noise removing unit is used to carry out smothing filtering to binary image to remove noise.
5. the Chinese chestnut detection system based on image technique as claimed in claim 4, which is characterized in that described image processing unit
Further include edge detection unit, the edge detection unit be used to remove the binary image of noise using Canny operator into
Row edge extracting obtains edge contour image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711494789.0A CN109990741A (en) | 2017-12-31 | 2017-12-31 | Chinese chestnut detection system based on image processing techniques |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711494789.0A CN109990741A (en) | 2017-12-31 | 2017-12-31 | Chinese chestnut detection system based on image processing techniques |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109990741A true CN109990741A (en) | 2019-07-09 |
Family
ID=67110837
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711494789.0A Pending CN109990741A (en) | 2017-12-31 | 2017-12-31 | Chinese chestnut detection system based on image processing techniques |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109990741A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111521128A (en) * | 2020-04-15 | 2020-08-11 | 中国科学院海洋研究所 | Shellfish external form automatic measurement method based on optical projection |
-
2017
- 2017-12-31 CN CN201711494789.0A patent/CN109990741A/en active Pending
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111521128A (en) * | 2020-04-15 | 2020-08-11 | 中国科学院海洋研究所 | Shellfish external form automatic measurement method based on optical projection |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP5443435B2 (en) | Tire defect detection method | |
US10453195B2 (en) | Method of detecting tissue area of interest in digital pathology imaging by executing computer-executable instructions stored on a non-transitory computer-readable medium | |
KR101011515B1 (en) | Method of object recognition in image data using combined edge magnitude and edge direction analysis techniques | |
CN104075965B (en) | A kind of micro-image grain graininess measuring method based on watershed segmentation | |
WO2019032101A1 (en) | Image processing techniques for plunger depth measurement | |
CN110108711A (en) | The vision detection system of annulus side wall defect | |
US9881367B1 (en) | Image processing techniques for plunger depth measurement | |
CN110490826B (en) | Fog drop sample image processing method in camera | |
CN107742307A (en) | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method | |
JP6598850B2 (en) | Image processing apparatus, image processing method, and image processing program | |
CN110570412B (en) | Part error vision judgment system | |
CN109990742A (en) | Chinese chestnut detection method based on image processing techniques | |
CN113706566B (en) | Edge detection-based perfuming and spraying performance detection method | |
CN111122590A (en) | Ceramic surface defect detection device and detection method | |
WO2020059448A1 (en) | Depth acquisition device, depth-acquiring method and program | |
CN109990741A (en) | Chinese chestnut detection system based on image processing techniques | |
CN101915823B (en) | Ultraviolet detection method for shell bacteria-carrying eggs and device thereof | |
CN114688969A (en) | Optical lens size detection device and method | |
CN113256591A (en) | Device and method for rapidly detecting defects of wide glass | |
WO2010133099A1 (en) | Target detecting method and system and stereovision system | |
CN112833821A (en) | Differential geometric three-dimensional micro-vision detection system and method for high-density IC welding spots | |
CN117036259A (en) | Metal plate surface defect detection method based on deep learning | |
CN110009597A (en) | A kind of plum quality detecting method | |
CN115272173A (en) | Tin ball defect detection method and device, computer equipment and storage medium | |
CN115423861A (en) | Gas leakage detection method and device, equipment and storage medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
WD01 | Invention patent application deemed withdrawn after publication | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190709 |