CN106204589A - A kind of fruit type quality stage division based on Digital Image Processing - Google Patents
A kind of fruit type quality stage division based on Digital Image Processing Download PDFInfo
- Publication number
- CN106204589A CN106204589A CN201610541265.1A CN201610541265A CN106204589A CN 106204589 A CN106204589 A CN 106204589A CN 201610541265 A CN201610541265 A CN 201610541265A CN 106204589 A CN106204589 A CN 106204589A
- Authority
- CN
- China
- Prior art keywords
- fruit
- image
- image processing
- type quality
- digital image
- 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
- 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
- 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
- G06T2207/30108—Industrial image inspection
- G06T2207/30128—Food products
Landscapes
- Engineering & Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
A kind of fruit type quality stage division based on Digital Image Processing, first, industrial camera is utilized to obtain the original-gray image of fruit, use filter window that gray level image is carried out enhancement process, secondly, choose suitable threshold value, greyscale image transitions step one obtained is the bianry image of the most black and white two kinds of colors, bianry image is carried out connected component labeling, a labeled connected domain represents single fruit, and while labelling, add up the geometrical characteristic of connected domain: area, finally, classification results according to the single fruit of calculated areal calculation, computer technology and Digital Image Processing basic fundamental connected component labeling method can be utilized, quickly, accurately, nondestructively fruit type quality is carried out classification, reduce labor strength, improve production efficiency, there is fruit not damaged, the feature that accuracy is high.
Description
Technical field
The present invention relates to a kind of utilize digital image processing techniques to realize the technology that fruit detects automatically, particularly to one
Fruit type quality stage division based on Digital Image Processing.
Background technology
In recent years, some areas of China start to pay attention to the selection of improved seeds, but mainly use manual grading skill and machinery
Two kinds of methods of classification.Manual grading skill is since it is desired that substantial amounts of labour force, and labor intensity is big, is reflected by individual's vision, color simultaneously
, there is the present situations such as low, the low precision of classification efficiency in the impact of the factors such as other power, emotion, degree of fatigue.Mechanical classification is mainly water
Fruit is sent to classification not only by conveyer belt or carrier chain, the hole that changed successively by size on classification parts or conveying interband
Spacing changes, it is achieved the priority of the fruit that varies in size separates, and has reached automatization and has realized the separation mesh fast and accurately of fruit
, but this mode but also exists the risk easily making fruit produce mechanical damage, causes the defect that fruit is unnecessary, thus
Affect the quality of fruit, reduce practicality.
Summary of the invention
In order to overcome above-mentioned the deficiencies in the prior art, it is an object of the invention to propose a kind of based on Digital Image Processing
Fruit type quality stage division, it is possible to utilize computer technology and Digital Image Processing basic fundamental connected component labeling method, soon
Speed, accurately, nondestructively to fruit type quality carry out classification, reduce labor strength, improve production efficiency, have fruit without
Damage, the feature that accuracy is high.
To achieve these goals, the technical solution used in the present invention is:
A kind of fruit type quality stage division based on Digital Image Processing, step is as follows:
Step one:
Utilize industrial camera to obtain the original-gray image of fruit, use filter window that gray level image is carried out at enhancing
Reason；
Step 2:
Choosing suitable threshold value, greyscale image transitions step one obtained is the binary map of the most black and white two kinds of colors
Picture；
Step 3:
Bianry image carries out connected component labeling, and a labeled connected domain represents single fruit, and same at labelling
The geometrical characteristic of Shi Tongji connected domain: area；
Step 4:
Classification results according to the single fruit of calculated areal calculation.
Described image enhancement processing is to be filtered by gray level image, with reduce dust and illumination etc. interference cause make an uproar
Sound, plays the effect strengthening fruit section feature；Concrete grammar is: from the beginning of the pixel of first, the upper left corner of image, utilizes filter
Ripple window carries out the scanning from left to right, from top to bottom of individual element, replaces by the intermediate value of the gray value of each point in window
The gray value of window center point pixel.
Described suitable threshold value is the rectangular histogram by gray level image, and threshold value is chosen between two crests.
The connected component labeling of described bianry image is to be distinguished by each fruit individuality, in order to carry out the meter of area
Calculate, compare the feature of concentration according to object pixel in image, use phase method that connected domain is carried out Fast Labeling process；I-th
Connected domain (single fruit) CiArea AiComputing formula be:
Ai=| p (x, y) | p (x, y)=i} |
Wherein: (x, y) denotation coordination is the pixel of x, y to p；
The area of single fruit is characterized by the number summation of the pixel that statistical labeling value is i.
Compared with prior art, the method have the advantages that
Owing to the present invention uses computer technology and image processing techniques, by obtaining the gray level image of fruit, and by ash
Degree image is converted to bianry image, bianry image carries out connected component labeling, thus accurately calculates given in the short period of time
The apparent parameter of fruit sample: area, it is possible to accurately, quickly, in real time to fruit carry out profile classification, it is to avoid during detection
The damage causing fruit, reduces labor strength and error rate, improves production efficiency, has fruit not damaged, accuracy
High feature.
Detailed description of the invention
Below in conjunction with embodiment, the present invention is described in further detail.
A kind of fruit type quality stage division based on Digital Image Processing, as measurand as a example by Fructus Mali pumilae, bag
Include following steps:
Step one:
The Fructus Mali pumilae of classification will send into Photo Studio in order, and utilize industrial camera to obtain the original gradation figure of Fructus Mali pumilae before classification
Picture, pixel size is 640 × 480, and in order to clearly show with Fructus Mali pumilae individuality chromatic zones, shooting background selects black background.
The filter window using size to be 5 × 5 pixels carries out enhancement process to gray level image, thin to eliminate tiny texture
Joint and noise pixel.Described image enhancement processing is to be filtered by gray level image, to reduce the interference such as dust and illumination
The noise caused, plays the effect strengthening Fructus Mali pumilae section feature；Concrete grammar is: from first, the upper left corner of image, pixel is opened
Begin, utilize filter window to carry out the scanning from left to right, from top to bottom of individual element, with in the gray value of each point in window
Value replaces the gray value of window center point pixel.
Step 2:
Choosing suitable threshold value, greyscale image transitions step one obtained is the binary map of the most black and white two kinds of colors
Picture, in order to follow-up Fructus Mali pumilae individual mark, geometrical characteristic parameter calculate.Owing to picture material is the most single, only Fructus Mali pumilae and
The background of black, so the rectangular histogram of gray level image presents obvious bimodal difference, the most corresponding Fructus Mali pumilae region and background.Herein
Choose the threshold value as binaryzation of the gray value 72 between crest, be bianry image by greyscale image transitions.
Step 3:
Bianry image carries out connected component labeling, and a labeled connected domain represents single Fructus Mali pumilae, and same at labelling
The geometrical characteristic of Shi Tongji connected domain (the most single Fructus Mali pumilae): area.
The connected component labeling of described bianry image is to be distinguished by each Fructus Mali pumilae individuality, in order to carry out follow-up area
Calculating；Compare the feature of concentration according to object pixel in image, the present invention uses phase method that connected domain is carried out Fast Labeling
Process；Described section refers to occur continuously in image the sequence that object pixel in a row is constituted；Connect further accordance with in image
Logical region is without hollow feature, and for the object pixel occurred continuously, their connectedness is very simple, and different waits price card
Relation between number also becomes simple, in labeling process, there is not the process merging equivalent labels.
I-th connected domain (single fruit) CiArea AiComputing formula be:
Ai=| p (x, y) | p (x, y)=i} |
Wherein: (x, y) denotation coordination is the pixel of x, y to p；
Utilize the feature of above-mentioned connected domain, labeling process calculates the number of the pixel of each label corresponding simultaneously, the
After single pass terminates, just count the area of each connected domain.
Step 4:
According to standard to Fructus Mali pumilae grade classification on market, taking lens is apart from tested individual distance 30 centimetres, and image divides
Resolution 640 × 480 pixel, obtains the classification results of single Fructus Mali pumilae: Fructus Mali pumilae size exists according to calculated area
Between 120000-140000 for Grade A, reference value often reduces 30000, and grade reduces one-level.The present embodiment is tested
Fructus Mali pumilae size is 126900, for Grade A.
Claims (4)
1. a fruit type quality stage division based on Digital Image Processing, it is characterised in that step is as follows:
Step one:
Utilize industrial camera to obtain the original-gray image of fruit, use filter window that gray level image is carried out enhancement process；
Step 2:
Choosing suitable threshold value, greyscale image transitions step one obtained is the bianry image of the most black and white two kinds of colors；
Step 3:
Bianry image carries out connected component labeling, and a labeled connected domain represents single fruit, and unites while labelling
The geometrical characteristic of meter connected domain: area；
Step 4:
Classification results according to the single fruit of calculated areal calculation.
A kind of fruit type quality stage division based on Digital Image Processing the most according to claim 1, its feature exists
In, described image enhancement processing is to be filtered by gray level image, the noise caused to reduce dust and illumination etc. to disturb, and rises
To the effect strengthening fruit section feature；Concrete grammar is: from the beginning of the pixel of first, the upper left corner of image, utilize filter window
Carry out the scanning from left to right, from top to bottom of individual element, replace in window by the intermediate value of the gray value of each point in window
The gray value of heart point pixel.
A kind of fruit type quality stage division based on Digital Image Processing the most according to claim 1, its feature exists
In, described suitable threshold value is the rectangular histogram by gray level image, and threshold value is chosen between two crests.
A kind of fruit type quality stage division based on Digital Image Processing the most according to claim 1, its feature exists
In, the connected component labeling of described bianry image is to be distinguished by each fruit individuality, in order to carry out the calculating of area, root
Compare the feature of concentration according to object pixel in image, use phase method that connected domain is carried out Fast Labeling process；I-th connected domain
(single fruit) CiArea AiComputing formula be:
Ai=| p (x, y) | p (x, y)=i} |
Wherein: (x, y) denotation coordination is the pixel of x, y to p；
The area of single fruit is characterized by the number summation of the pixel that statistical labeling value is i.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610541265.1A CN106204589A (en) | 2016-07-11 | 2016-07-11 | A kind of fruit type quality stage division based on Digital Image Processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610541265.1A CN106204589A (en) | 2016-07-11 | 2016-07-11 | A kind of fruit type quality stage division based on Digital Image Processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106204589A true CN106204589A (en) | 2016-12-07 |
Family
ID=57473690
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610541265.1A Pending CN106204589A (en) | 2016-07-11 | 2016-07-11 | A kind of fruit type quality stage division based on Digital Image Processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106204589A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109115775A (en) * | 2018-08-08 | 2019-01-01 | 长沙理工大学 | A kind of betel nut level detection method based on machine vision |
| CN109724152A (en) * | 2018-07-24 | 2019-05-07 | 永康市蜂蚁科技有限公司 | Heating equipment hot channel flow velocity switching system |
| CN109752391A (en) * | 2018-12-25 | 2019-05-14 | 中国农业大学 | A kind of carrot Surface Defect Recognition quantization method based on machine vision |
| CN110118775A (en) * | 2019-05-10 | 2019-08-13 | 重庆交通大学 | Plantmix's cement stabilized macadam aggregate forms rapid detection method |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914849A (en) * | 2014-04-18 | 2014-07-09 | 扬州福尔喜果蔬汁机械有限公司 | Method for detecting red date image |
-
2016
- 2016-07-11 CN CN201610541265.1A patent/CN106204589A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103914849A (en) * | 2014-04-18 | 2014-07-09 | 扬州福尔喜果蔬汁机械有限公司 | Method for detecting red date image |
Non-Patent Citations (2)
| Title |
|---|
| UNMESH SAGARE，VINAYMANDLIK: "Grading of Fruits Basis on Color Shape", 《INTERNATIONAL JOURNAL OF ENGINEERING SCIENCES & RESEARCH TECHNOLOGY》 * |
| 侯文军: "基于机器视觉的苹果自动分级方法研究", 《中国优秀博硕士学位论文全文数据库（硕士）农业科技辑》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109724152A (en) * | 2018-07-24 | 2019-05-07 | 永康市蜂蚁科技有限公司 | Heating equipment hot channel flow velocity switching system |
| CN109115775A (en) * | 2018-08-08 | 2019-01-01 | 长沙理工大学 | A kind of betel nut level detection method based on machine vision |
| CN109752391A (en) * | 2018-12-25 | 2019-05-14 | 中国农业大学 | A kind of carrot Surface Defect Recognition quantization method based on machine vision |
| CN109752391B (en) * | 2018-12-25 | 2020-06-30 | 中国农业大学 | Carrot surface defect identification and quantification method based on machine vision |
| CN110118775A (en) * | 2019-05-10 | 2019-08-13 | 重庆交通大学 | Plantmix's cement stabilized macadam aggregate forms rapid detection method |
| CN110118775B (en) * | 2019-05-10 | 2021-11-19 | 重庆交通大学 | Method for rapidly detecting composition of plant-mixed cement stabilized macadam aggregate |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105404869A (en) | Computer vision based fruit shape grading method | |
| CN106204589A (en) | A kind of fruit type quality stage division based on Digital Image Processing | |
| CN109269951A (en) | Floating tail-coal ash content, concentration, coarse granule detection method of content based on image | |
| CN104809422B (en) | QR code recognition methods based on image procossing | |
| CN105424709A (en) | Fruit surface defect detection method based on image marking | |
| KR20100015628A (en) | Lumber inspection method, device and program | |
| CN103426164B (en) | Based on scallop size computing method and the scallop sorting system of Opencv graphical analysis | |
| CN108830838A (en) | A kind of pcb board incompleteness Trigger jitter detection method of sub-pixel | |
| CN106157323B (en) | A kind of insulator division and extracting method of dynamic division threshold value and block search combination | |
| CN102974551A (en) | Machine vision-based method for detecting and sorting polycrystalline silicon solar energy | |
| CN101937563A (en) | Target detection method and equipment and image acquisition device thereof | |
| CN113034488B (en) | Visual inspection method for ink-jet printed matter | |
| CN110288561A (en) | Refractory brick surface scratch recognition methods based on frequency filtering enhancing | |
| CN103914849B (en) | A kind of detection method of red jujube image | |
| CN103914827A (en) | Method for visual inspection of shortages of automobile sealing strip profile | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN109685760A (en) | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN110687121B (en) | Intelligent online detection and automatic grading method and system for ceramic tiles | |
| Feng et al. | A separating method of adjacent apples based on machine vision and chain code information | |
| CN110108724A (en) | Strip-shaped work vision detection system | |
| CN103440629A (en) | Digital image processing method of video extensometer with automatic tracking laser marker | |
| CN111562260B (en) | Lotus root mud hole detection method and device based on machine vision | |
| CN102788806B (en) | Fruit peel defect detection method based on spheroidic brightness transformation | |
| CN107256549B (en) | Bamboo strip defect detection method based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20161207 |