CN103824224A - Fruit size grading method based on shape from shading - Google Patents
Fruit size grading method based on shape from shading Download PDFInfo
- Publication number
- CN103824224A CN103824224A CN201410067427.3A CN201410067427A CN103824224A CN 103824224 A CN103824224 A CN 103824224A CN 201410067427 A CN201410067427 A CN 201410067427A CN 103824224 A CN103824224 A CN 103824224A
- Authority
- CN
- China
- Prior art keywords
- fruit
- shape
- shading
- image
- carried out
- 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
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a fruit size grading method based on shape from shading. Firstly, an original image of a tested fruit is obtained through a CCD camera, and by means of a digital image processing technique, the image is pre-processed; secondly, by means of the shape from shading method, three-dimensional reconstruction is carried out on the fruit, curve fitting is carried out on the surface of the three-dimensional object which is reconstructed so as to avoid influences of light on the object, errors of three-dimensional reconstruction are reduced, and the size of the reconstructed object is calculated; ultimately, a large number of samples are used for training, and by means of the algorithm, fruit size grading is achieved. According to the method, fruits can be graded according to sizes; the method has the advantages of being automatic, lossless and high in accuracy; if the method is applied to the field of agricultural production, the problem of how to accurately and conveniently grade the fruits after production can be well solved, commercialization processing capacity of the fruits is improved, incomes of fruit growers are increased, economic development is promoted, and the method has large market potential.
Description
Technical field
The present invention relates to a kind of method of utilizing digital image processing techniques to realize the automatic Non-Destructive Testing of quality of agricultural product, be specifically related to a kind of fruit size fractionation method from shape from shading.
Background technology
China is a Production of fruit big country, realizes quickly and accurately detection and the classification processing of fruit, is important measures that improve fruit economy benefit, strengthen Competitiveness of Chinese Industries.
Traditional fruit size fractionation is manual grading skill, relies on skilled labor's experience to estimate the size that judges fruit, is difficult to guarantee accuracy and the validity of classification results, can not meet the demand in market.The existing fruit size fractionation method based on computer vision, adopt conventional Digital Image Processing algorithm, by the fruit image collecting being carried out to the processing such as pre-service, fruit Region Segmentation, feature detection, calculate fruit footpath, characteristic parameter with fruit footpath as fruit size, determine the actual measured value of fruit through system calibrating, finally realize the classification of fruit size by above-mentioned measured value.The method complex disposal process, calculated amount is large, and the execution time is longer, and has certain deviation for some complex-shaped, irregular fruit size fractionation results, has limited to a certain extent its actual promotion and application at agricultural production.
Conventionally fruit footpath is the standard of weighing fruit size, and volume also can be used as criterion fruit is carried out to size fractionation.Therefore the fruit size fractionation based on computer vision, first can carry out three-dimensional reconstruction to the image collecting, and then volume calculated is carried out the size fractionation of fruit by the volume of fruit.Shape from shading (SFS) method is to change according to the light and shade on objects in images surface, recovers the relative height of body surface each point, recovers the height of object according to the half-tone information of imaging surface, thereby rebuilds the 3D shape of object.Utilize shape from shading method to carry out the size fractionation of fruit, can reduce the complexity of traditional images Processing Algorithm, improve fruit grading efficiency.
Summary of the invention
In order to overcome the shortcoming of above-mentioned prior art, the object of the present invention is to provide a kind of fruit size fractionation method based on shape from shading, be treated to background with the fruit later stage classification in research quality of agricultural product detection field, can reduce image and process complexity, improve the efficiency of classification.
To achieve these goals, the technical solution used in the present invention is:
A fruit size fractionation method based on shape from shading, comprises the steps:
First, obtain the original image of tested fruit by CCD camera, utilize digital image processing techniques to carry out pre-service to image;
Secondly, by shape from shading method, fruit is carried out to three-dimensional reconstruction, the impact for fear of illumination on object, carries out curve fitting to the three-dimensional object surface after rebuilding, and reduces the error of three-dimensional reconstruction, and the object after rebuilding is carried out to volume calculating;
Finally, use great amount of samples to train, utilize above-mentioned algorithm, realize the classification to fruit size.
The original image that described CCD camera obtains tested fruit is left view and right view, and described pre-service refers to carries out filtering and gray processing processing to image.
Describedly by the detailed process that shape from shading method is carried out three-dimensional reconstruction to fruit be:
First, left and right after treatment gray processing view and background are cut apart, background gray levels is set to 0;
Secondly, according to the half-tone information of image, introduce the Smoothing Constraint condition of body surface, solve the Grad of body surface;
Finally obtain the height value of object by Grad, and then obtain the three-dimensional structure of object.
Compared with prior art, the invention has the beneficial effects as follows:
Experimental result shows, the fruit size fractionation method based on shape from shading the present invention relates to, can realize the classification to fruit size, has automatically, harmless, the high feature of accuracy.If apply the present invention to agricultural production, can solve preferably fruit postpartum accurately, classification easily processes problem, thereby improve the commercialization processing power of fruit, increase orchard worker's income, promote economic development, there is very large market potential.
Accompanying drawing explanation
Fig. 1 is fruit size fractionation method processing flow chart of the present invention.
Embodiment
The present invention is using apple as measurand, and as shown in Figure 1, concrete implementation step is as follows for treatment scheme:
Step1, system is calibrated, calculating pixel equivalent ε, obtains the physical size of unit picture element representative.
Step2, obtain left view and the right view of tested apple by CCD camera.
Step3, left view and right view are carried out to filtering processing.
Step4, filtered image is carried out to gray processing processing.
Step5, left and right view and the background of Apple image are cut apart, background gray levels is set to 0.
Step6, employing shape from shading method are carried out three-dimensional reconstruction to left view, and the apple surface coordinate points after left view is rebuild carries out curve fitting.
The actual voxel piece number comprising in Step7, statistics left view three-dimensional model space.
Step8, employing shape from shading method are carried out three-dimensional reconstruction to right view, and the apple surface coordinate points after right view is rebuild carries out curve fitting.
The actual voxel piece number comprising in Step9, statistics right view three-dimensional model space.
Step10, the actual voxel piece number comprising in view three-dimensional model space, left and right is summed to sum.
Step11, utilize pixel equivalent, volume is sum × ε
3, the volume in image coordinate system is scaled to actual measurement volume.
Step12, train by great amount of samples, observe the regularity of distribution of above-mentioned bulking value, obtain weighing the threshold value of apple order of magnitude.
Step13, output fruit size fractionation result.
Wherein:
Right view three-dimensional reconstruction detailed process:
Step1: be z=z (x, y) by the representation of a surface of right view, surface graded is (p, q),
the normal vector of curved surface is (p, q ,-1), and the estimation gradient of light source direction is (p
s, q
s).
Step2: know according to shape from shading method assumed condition, the gradation of image value E of body surface point is expressed as:
Step3: introduce integrability constraint condition and solve surface graded (p, q).
Step4: obtain z (x, y) according to (p, q).For any (x, the y) in fruit image, coordinate figure is (x, y, z (x, y)), and then obtains the three-dimensional structure of fruit right view.
Claims (3)
1. the fruit size fractionation method based on shape from shading, is characterized in that, comprises the steps:
First, obtain the original image of tested fruit by CCD camera, utilize digital image processing techniques to carry out pre-service to image;
Secondly, by shape from shading method, fruit is carried out to three-dimensional reconstruction, the impact for fear of illumination on object, carries out curve fitting to the three-dimensional object surface after rebuilding, and reduces the error of three-dimensional reconstruction, and the object after rebuilding is carried out to volume calculating;
Finally, use great amount of samples to train, utilize above-mentioned algorithm, realize the classification to fruit size.
2. the fruit size fractionation method based on shape from shading according to claim 1, is characterized in that, the original image that described CCD camera obtains tested fruit is left view and right view, and described pre-service refers to carries out filtering and gray processing processing to image.
3. the fruit size fractionation method based on shape from shading according to claim 2, is characterized in that, describedly by the detailed process that shape from shading method is carried out three-dimensional reconstruction to fruit is:
First, left and right after treatment gray processing view and background are cut apart, background gray levels is set to 0;
Secondly, according to the half-tone information of image, introduce the Smoothing Constraint condition of body surface, solve the Grad of body surface;
Finally obtain the height value of object by Grad, and then obtain the three-dimensional structure of object.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410067427.3A CN103824224A (en) | 2014-02-26 | 2014-02-26 | Fruit size grading method based on shape from shading |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410067427.3A CN103824224A (en) | 2014-02-26 | 2014-02-26 | Fruit size grading method based on shape from shading |
Publications (1)
Publication Number | Publication Date |
---|---|
CN103824224A true CN103824224A (en) | 2014-05-28 |
Family
ID=50759272
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410067427.3A Pending CN103824224A (en) | 2014-02-26 | 2014-02-26 | Fruit size grading method based on shape from shading |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103824224A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104330066A (en) * | 2014-10-21 | 2015-02-04 | 陕西科技大学 | Irregular object volume measurement method based on Freeman chain code detection |
CN106228612A (en) * | 2016-07-11 | 2016-12-14 | 浙江大学 | Utilize the method and apparatus that System of Rotating about Fixed Axis profile diagram rebuilds Rhizoma Solani tuber osi three-dimensional surface |
CN110751620A (en) * | 2019-08-28 | 2020-02-04 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
CN111299186A (en) * | 2020-02-21 | 2020-06-19 | 杨伟 | Fruit grading method, device and equipment |
CN113240706A (en) * | 2021-04-12 | 2021-08-10 | 湖北工业大学 | Intelligent tracking detection method for molten iron tailings in high-temperature environment |
CN113926725A (en) * | 2021-10-26 | 2022-01-14 | 东北大学秦皇岛分校 | Coal and gangue rapid sorting device and method based on density estimation |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735340A (en) * | 2012-06-11 | 2012-10-17 | 陕西科技大学 | Fruit color grading method based on compressive sensing |
CN102750547A (en) * | 2012-06-11 | 2012-10-24 | 陕西科技大学 | Fruit size grading method based on compressed sensing |
CN103278090A (en) * | 2013-05-14 | 2013-09-04 | 陕西科技大学 | Visual measurement method for volume of irregular object |
CN103471989A (en) * | 2013-01-08 | 2013-12-25 | 刘学峰 | Optical vector modeling based non-visual imaging method |
-
2014
- 2014-02-26 CN CN201410067427.3A patent/CN103824224A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735340A (en) * | 2012-06-11 | 2012-10-17 | 陕西科技大学 | Fruit color grading method based on compressive sensing |
CN102750547A (en) * | 2012-06-11 | 2012-10-24 | 陕西科技大学 | Fruit size grading method based on compressed sensing |
CN103471989A (en) * | 2013-01-08 | 2013-12-25 | 刘学峰 | Optical vector modeling based non-visual imaging method |
CN103278090A (en) * | 2013-05-14 | 2013-09-04 | 陕西科技大学 | Visual measurement method for volume of irregular object |
Non-Patent Citations (1)
Title |
---|
周竹 等: "基于机器视觉的马铃薯自动分级方法", 《农业工程学报》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104330066A (en) * | 2014-10-21 | 2015-02-04 | 陕西科技大学 | Irregular object volume measurement method based on Freeman chain code detection |
CN104330066B (en) * | 2014-10-21 | 2017-02-01 | 陕西科技大学 | Irregular object volume measurement method based on Freeman chain code detection |
CN106228612A (en) * | 2016-07-11 | 2016-12-14 | 浙江大学 | Utilize the method and apparatus that System of Rotating about Fixed Axis profile diagram rebuilds Rhizoma Solani tuber osi three-dimensional surface |
CN106228612B (en) * | 2016-07-11 | 2019-01-29 | 浙江大学 | The method and apparatus for rebuilding potato three-dimensional surface using System of Rotating about Fixed Axis profile diagram |
CN110751620A (en) * | 2019-08-28 | 2020-02-04 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
CN110751620B (en) * | 2019-08-28 | 2021-03-16 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
CN111299186A (en) * | 2020-02-21 | 2020-06-19 | 杨伟 | Fruit grading method, device and equipment |
CN113240706A (en) * | 2021-04-12 | 2021-08-10 | 湖北工业大学 | Intelligent tracking detection method for molten iron tailings in high-temperature environment |
CN113926725A (en) * | 2021-10-26 | 2022-01-14 | 东北大学秦皇岛分校 | Coal and gangue rapid sorting device and method based on density estimation |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN103824224A (en) | Fruit size grading method based on shape from shading | |
CN107424143B (en) | Mining belt conveyor coal quantity detection method based on binocular stereoscopic vision depth perception | |
CN104156536B (en) | The visualization quantitatively calibrating and analysis method of a kind of shield machine cutter abrasion | |
CN103822581B (en) | A kind of irregularly shaped object volume measuring method based on compressed sensing | |
CN104156967B (en) | A kind of fetus neck hyaline layer image partition method, device and ultrasonic image-forming system | |
CN109360246B (en) | Stereoscopic vision three-dimensional displacement measurement method based on synchronous subarea search | |
CN102682446A (en) | Method and apparatus for generating a dense depth map using an adaptive joint bilateral filter | |
CN107578403A (en) | The stereo image quality evaluation method of binocular view fusion is instructed based on gradient information | |
CN103278090A (en) | Visual measurement method for volume of irregular object | |
CN103808265B (en) | Method, device and system for measuring oilseed rape laminae and forms of sclerotium scabs synchronously | |
CN108280852B (en) | Door and window point cloud shape detection method and system based on laser point cloud data | |
CN108805980B (en) | Horse body ruler measurement system based on 3D and data correction method | |
Tu et al. | Automatic measurement algorithm of scoliosis Cobb angle based on deep learning | |
CN108596975A (en) | A kind of Stereo Matching Algorithm for weak texture region | |
CN104408709B (en) | A kind of irregular quick antidote of linear array CCD camera gradation of image | |
CN104075965A (en) | Method for measuring granularity of microscopic image particles segmented on basis of watershed | |
Mirzaalian Dastjerdi et al. | Measuring surface area of skin lesions with 2D and 3D algorithms | |
CN104574312A (en) | Method and device of calculating center of circle for target image | |
CN104732520A (en) | Cardio-thoracic ratio measuring algorithm and system for chest digital image | |
CN104952109A (en) | Harris-based spine feature point automatic recognizing method | |
CN115861409B (en) | Soybean leaf area measuring and calculating method, system, computer equipment and storage medium | |
CN103514599B (en) | A kind of segmentation of the image optimum based on neighborhood total variation scale selection method | |
CN103308000A (en) | Method for measuring curve object on basis of binocular vision | |
CN104952068B (en) | A kind of vertebra characteristic point automatic identifying method | |
WO2015040547A1 (en) | Method and system for spine position detection |
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 |
Application publication date: 20140528 |
|
WD01 | Invention patent application deemed withdrawn after publication |