CN102654463A - Watermelon quality NDT (non-destructive testing) method and device - Google Patents
Watermelon quality NDT (non-destructive testing) method and device Download PDFInfo
- Publication number
- CN102654463A CN102654463A CN2012101101373A CN201210110137A CN102654463A CN 102654463 A CN102654463 A CN 102654463A CN 2012101101373 A CN2012101101373 A CN 2012101101373A CN 201210110137 A CN201210110137 A CN 201210110137A CN 102654463 A CN102654463 A CN 102654463A
- Authority
- CN
- China
- Prior art keywords
- watermelon
- measured
- sample
- volume
- quality
- 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
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Processing (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of melon and fruit type detection, and discloses a watermelon quality NDT (non-destructive testing) method and device. The watermelon quality NDT method comprises the following steps of: selecting a plurality of sample watermelons, respectively measuring the initial volume of each sample watermelon by adopting a water drainage method, acquiring sample watermelon image information and transmitting the information to a computer by utilizing a CCD (charge coupled device) camera, calculating the length, the width and the height of each sample watermelon after processing image information, and establishing a volume model of each watermelon to be tested, wherein the volume model is as follows: V=4/3*K*a*b*c; fitting a K-value according the initial volume, the length, the width and the height of each sample watermelon, measuring the volume of each watermelon to be tested according the volume model, measuring the quality of each watermelon, calculating the density according to the quality and the volume, and finally judging the quality of the watermelon to be tested. According to the invention, a digital image processing technique, a transmission system and a computer control technique are combined, watermelon quality non-destructive classification and identification are realized, the operation is simple and the detection performance is stable.
Description
Technical field
The present invention relates to a kind of melon and fruit class detection technique, particularly relate to a kind of quality of watermelon lossless detection method and device.
Background technology
What the method for tradition discriminating quality of watermelon was commonly used is to judge quality through the sound that beats watermelon, and this method depends on operator's experience fully, and discriminating speed is slow, and is prone to watermelon is caused damage.Some comparatively objective and easy methods are carried out the discriminating of quality of watermelon below having worked out at present:
1, labeling acts: adopt same label to pasting with a collection of watermelon, after a period of time, the sampling Detection of cutting open a watermelon quality of watermelon belongs to and diminishes detection method, and adopts the testing result of the methods of sampling unstable;
2, unit weight method: measure watermelon volume and quality, through its quality of the different judgement of density with the kind watermelon.The unit weight method is measured the watermelon volume with the watermelon drainage, complicated operation, and since contact watermelon when measuring be prone to watermelon is caused damage;
3, resistance method: the resistivity through measuring watermelon is judged quality of watermelon, and electric current can cause damage to watermelon;
4, electronic equipment is distinguished method: the resonant frequency through measuring watermelon is judged quality of watermelon, collects sound through microphone, after handling through amplification, filtering etc., provides measurement result, and these class methods still need contact watermelon, are prone to watermelon is caused damage.
Summary of the invention
The technical matters that (one) will solve
The technical matters that the present invention will solve is how a kind of simple to operate, quality of watermelon lossless detection method and device of detecting stable performance is provided.
(2) technical scheme
In order to solve the problems of the technologies described above, the present invention provides a kind of quality of watermelon lossless detection method, comprising: S1, choose a plurality of sample watermelons, adopt drainage to measure the initial volume of each sample watermelon respectively; S2, the sample watermelon is transported to the control platform on the acquisition platform through induction system; Through the position of computer regulated control platform with adjusting sample watermelon; Utilize acquisition platform top camera acquisition sample watermelon image information and be transferred to computing machine, computing machine calculates length, width and the height of sample watermelon after with said Image Information Processing; S3, set up the volume-based model of watermelon to be measured: V=4/3 * K * a * b * c; Wherein, V is the volume of watermelon to be measured; A, b, c are respectively length, width and the height of sample watermelon or watermelon to be measured, and K is a constant, according to the length of the initial volume of step S1 and step S2, width, highly simulate the K value; S4, change the sample watermelon into watermelon to be measured and repeating step S2, measure length, width and the height of watermelon to be measured,, calculate the volume V of watermelon to be measured according to volume-based model V=4/3 * K * a * b * c; S5, measure the quality of watermelon to be measured, and the density that calculates watermelon to be measured according to quality and the volume V of watermelon to be measured, the last quality of judging this watermelon to be measured according to density.
Wherein, Said video camera adopts two ccd video cameras; Said two ccd video cameras lay respectively at the control platform directly over and oblique upper, be connected with said computing machine through second image processing system respectively, by the position of said two ccd video cameras of said computer regulated; Be positioned at the ccd video camera of control directly over the platform and be used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, be positioned at the image information on the short transverse that the ccd video camera of controlling the platform oblique upper is used to gather sample watermelon or watermelon to be measured.
Wherein, first image processing system in the said computing machine comprises image input/output module, pre-processing module, characteristic extracting module and model building module; Said image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; Said pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; The edge graph that said characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates length, width and the height of closed sides; Said model building module is used to the volume setting up volume-based model and calculate watermelon to be measured according to characteristic.
Wherein, said pre-processing module adopts the adaptive threshold method that the image information of sample watermelon or watermelon to be measured is isolated from complex background, and adopts median filtering method to eliminate isolated noise spot.
Wherein, Said characteristic extracting module adopts morphology opening and closing operation method to carry out the filling in bianry image cavity and adopts SEQUENTIAL ALGORITHM to extract the limit characteristic; And adopt Shamos to ask the method for convex polygon diameter to calculate the diameter of closed sides, be length, width and the height of sample watermelon or watermelon to be measured.
Wherein, the match of said model building module employing Hough transformation obtains the key parameter K value of volume-based model, and calculates the volume of watermelon to be measured according to said volume-based model.
The present invention also provides a kind of quality of watermelon the cannot-harm-detection device, comprises computing machine and the induction system that is connected with said computing machine, acquisition platform and camera system; Said acquisition platform is provided with the control platform; Said control platform is connected with computing machine; Said induction system is used for sample watermelon or watermelon to be measured are transported to the control platform; Said camera system is positioned at the top of acquisition platform, is used to gather the image information of sample watermelon or watermelon to be measured and is transferred to computing machine; Said computing machine is regulated the position of camera system according to received image information, and calculates length, width and the height of sample watermelon or watermelon to be measured, sets up volume-based model and the volume that calculates watermelon to be measured simultaneously.
Wherein, said camera system comprises light source and two ccd video cameras; Said two ccd video cameras lay respectively at control platform directly over and oblique upper; Be connected with said computing machine through second image processing system respectively; Be positioned at the ccd video camera of control directly over the platform and be used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, be positioned at the image information on the short transverse that the ccd video camera of controlling the platform oblique upper is used to gather sample watermelon or watermelon to be measured; Said light source is fixed on the top of said control platform through the light source bracing frame.
Wherein, said computing machine comprises the control system and first image processing system; Said control system is used to carry out steering order; Said first image processing system is connected with camera system; Calculate length, width and the height of sample watermelon or watermelon to be measured after being used for the image information of sample watermelon or watermelon to be measured handled, and set up volume-based model and calculate the volume of watermelon to be measured.
Wherein, said first image processing system comprises image input/output module, pre-processing module, characteristic extracting module and model building module; Said image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; Said pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; The edge graph that said characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates length, width and the height of closed sides; Said model building module is used for the key parameter of match volume-based model according to characteristic and calculates the volume of watermelon to be measured according to volume-based model.
(3) beneficial effect
A kind of quality of watermelon lossless detection method and device that technique scheme provides; Adopt the complex art of digital camera Flame Image Process, transmission system and Computer Control Technology; Harmless classification and identification have been realized to the watermelon product; This device is simple to operate, the detection stable performance, and can obtain great amount of images information fast, robust.
Description of drawings
Fig. 1 is the structural representation of quality of watermelon the cannot-harm-detection device of the present invention;
Fig. 2 is the fundamental diagram of the present invention's first image processing system;
Fig. 3 is the workflow diagram of quality of watermelon the cannot-harm-detection device of the present invention.
Wherein, 1, computing machine; 2, acquisition platform; 2a, control platform; 3a, transfer station; 3b, direct current generator; 4a, light source; 4b, ccd video camera; 4c, ccd video camera; 4d, light source bracing frame; 5, second image processing system.
Embodiment
Below in conjunction with accompanying drawing and embodiment, specific embodiments of the invention describes in further detail.Following examples are used to explain the present invention, but are not used for limiting scope of the present invention.
Like Fig. 1 and Fig. 3, a kind of quality of watermelon lossless detection method of the present invention comprises:
S1, choose a plurality of sample watermelons, adopt drainage to measure the initial volume of each sample watermelon respectively; The initial volume of these a plurality of sample watermelons is made as V respectively
L1, V
L2, V
L3... V
Ln
S2, the sample watermelon is transported to the control platform on the acquisition platform through induction system; Regulate control platform 2a to regulate the position of sample watermelon through computing machine 1; Utilize acquisition platform 2 tops camera acquisition sample watermelon image information and be transferred to computing machine 1, computing machine 1 calculates length, width and the height of sample watermelon after with this Image Information Processing; Be specially: the sample watermelon is placed on the transfer station 3a of induction system; Transfer station 3a is provided with direct current generator 3b; This direct current generator 3b is connected with the control system of computing machine 1, and computing machine 1 is controlled direct current generator 3b and to drive transfer station 3a the sample watermelon sent into control platform 2a after the image information of handling current sample watermelon, and the image information of the camera acquisition sample watermelon of acquisition platform 2 tops also is transferred to computing machine 1; The position that computing machine 1 is regulated video camera according to this image information is to regulate its focal length; Obtain distinct image information, wherein, length is the size of the major axis of sample watermelon; Width is the size of the minor axis of sample watermelon, highly is the size of another minor axis vertical with this minor axis; Also can regulate acquisition platform 2 through computing machine 1 simultaneously, Spin Control platform 2a makes the major axis of watermelon with the spindle parallel of controlling platform or overlap;
S3, set up the volume-based model of watermelon to be measured: V=4/3 * K * a * b * c; Wherein, V is the volume of watermelon to be measured, and a, b, c are respectively length, width and the height of sample watermelon or watermelon to be measured, and K is a constant; The K value is the key parameter of this volume-based model, according to the length of the initial volume of step S1 and step S2, width, highly simulate the K value; Be specially: the initial volume of a plurality of sample watermelons of being measured by step S1 is respectively V
L1, V
L2, V
L3... V
Ln, substitution formula V=4/3 * K * a * b * c draws corresponding K
1, K
2, K
3... K
n, by K
1, K
2, K
3... K
nSimulate the K value, then set up volume-based model V=4/3 * K * a * b * c;
S4, change the sample watermelon into watermelon to be measured and repeating step S2, measure length, width and the height of watermelon to be measured,, calculate the volume V of watermelon to be measured according to volume-based model V=4/3 * K * a * b * c; Be specially: watermelon to be measured is sent into control platform 2a through induction system; Camera acquisition is to the image information of this watermelon to be measured and be transferred to computing machine 1; The position that computing machine 1 can be regulated video camera according to this image information is to regulate its focal length; Obtain distinct image information, regulate acquisition platform 2 through computing machine 1, Spin Control platform 2a makes the major axis of watermelon to be measured with the spindle parallel of controlling platform 2a or overlap; Computing machine 1 calculates length, width and the height of this watermelon to be measured according to this image information, and calculates the volume of this watermelon to be measured according to volume-based model V=4/3 * K * a * b * c that step S3 is set up;
S5, measure the quality of watermelon to be measured, and the density that calculates watermelon to be measured according to quality and the volume V of watermelon to be measured, the last quality of judging this watermelon to be measured according to density.
After current watermelon completion detection to be measured, next one watermelon to be measured is placed on the induction system, repeating step S4 and S5 circulate successively and accomplish up to detecting.
The present invention adopts the complex art of digital camera Flame Image Process, transmission system and Computer Control Technology; Harmless classification and identification have been realized to the watermelon product; This device is simple to operate, the detection stable performance, and can obtain great amount of images information fast, robust.
Preferably; Like Fig. 1, the video camera of present embodiment adopts two CCD (being charge coupled cell, English Charge-coupled Device by name) video camera 4b, 4c; These two ccd video camera 4b, 4c lay respectively at control platform 2a directly over and oblique upper; Be connected with computing machine 1 through second image processing system 5 respectively, by the position of computing machine 1 these two ccd video camera 4b of adjusting, 4c, the two ends of second image processing system 5 are provided with the IEEE1394 standard interface; Computing machine 1 is regulated the position of these two ccd video camera 4b, 4c to regulate its focal length according to received image information, obtain distinct image information; The ccd video camera 4b that is positioned at directly over the control platform 2a is used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, is positioned at the image information on the short transverse that the ccd video camera 4c that controls the platform oblique upper is used to gather sample watermelon or watermelon to be measured.Wherein, in order to improve image definition, also be provided with light source 4a, this light source 4a is the LED planar light source, is fixed on the top of control platform 2a through light source bracing frame 4d; Second image processing system 5 adopts DSP high speed image disposal system.
Preferably, like Fig. 2, first image processing system in the computing machine of present embodiment comprises image input/output module, pre-processing module, characteristic extracting module and model building module.
Wherein, The image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; These data are the quality qualification result; Comprise the length, width of sample watermelon or watermelon to be measured after COMPUTER CALCULATION, highly and the volume and the density that comprise watermelon to be measured.
Wherein, pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; Detailed process is: this pre-processing module adopts the adaptive threshold method that the image information of sample watermelon or watermelon to be measured is divided into bianry image from complex background; Adopt the effect of adaptive threshold method to be: when background changes; Like illumination unevenness, have that burst noise, background grey scale change are big, shade influence etc.; Single threshold value can not be cut apart well, adopts the method for adaptive threshold, makes and cuts apart robust more; The calculation and thinking of this adaptive threshold method is: be divided into the zonule to image, to each zonule, the self-adaptation selected threshold is cut apart; Bianry image after will cutting apart then adopts median filtering method to carry out pre-service, and this is because image can receive the interference of noise source in gatherer process, if without denoising, can bring influence to follow-up feature extraction; Median filtering method is a kind of based on the theoretical nonlinear smoothing technology that can effectively suppress noise of sequencing statistical; Its ultimate principle is to replace the gray-scale value of any in digital picture or the Serial No. with the Mesophyticum of gray-scale value in the neighborhood of this point; The approaching actual value of pixel value around letting, thus isolated noise spot eliminated, can accomplish squelch, filtering impulse disturbances and image scanning noise; It is fuzzy to overcome the image detail that linear filter brings again, keeps the image side information.
Wherein, the edge graph that characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates length, width and the height of closed sides; Detailed process is: characteristic extracting module adopts morphology opening and closing operation method to carry out the filling in bianry image cavity and adopts SEQUENTIAL ALGORITHM to extract connected region; Because the bianry image after the background segment; There is the cavity; Directly extract connected region and can cause error, therefore, adopt the opening and closing operation method of mathematical morphology to fill the bianry image cavity; Follow the tracks of the limit of connected region simultaneously; Extract the limit characteristic; Ask the method for convex polygon diameter to calculate the closed sides diameter with Shamos; Image information on the length direction of gathering according to video camera calculates the size of the major axis of sample watermelon or watermelon to be measured, and adjustment acquisition platform 2, and the major axis that makes the watermelon sample is with the spindle parallel of controlling platform 2a or overlap; Handle the sample watermelon of camera acquisition or the image information of watermelon to be measured then, ask the method for convex polygon diameter to calculate the key parameter of closed sides (being length, width and the height of sample watermelon or watermelon to be measured) with Shamos.
Wherein, model building module is used for the key parameter K value of match volume-based model according to characteristic and calculates the volume of watermelon to be measured according to volume-based model; This model building module employing Hough transformation match obtains the key parameter K value of volume-based model, and calculates the volume of watermelon to be measured according to volume-based model.
Like Fig. 1, a kind of quality of watermelon the cannot-harm-detection device of the present invention comprises computing machine 1 and the induction system that is connected with this computing machine 1, acquisition platform 2 and camera system; Acquisition platform 2 is provided with control platform 2a; This control platform 2a is connected with computing machine 1; Induction system is used for sample watermelon or watermelon to be measured are transported to control platform 2a; Camera system is positioned at the top of acquisition platform 2, is used to gather the image information of sample watermelon or watermelon to be measured and is transferred to computing machine 1; Computing machine 1 is regulated the position of camera system according to received image information, and calculates length, width and the height of sample watermelon or watermelon to be measured, sets up volume-based model V=4/3 * K * a * b * c and the volume V that calculates watermelon to be measured simultaneously.Wherein, induction system comprises transfer station 3a and direct current generator 3b, drives transfer station 3a through direct current generator 3b sample watermelon or watermelon to be measured are transmitted.
The camera system of present embodiment comprises light source 4a and two ccd video camera 4b, 4c; These two ccd video camera 4b, 4c lay respectively at control platform 2a directly over and oblique upper; Be connected with computing machine through second image processing system 5 respectively; Regulate the position of these two ccd video camera 4b, 4c by computing machine 1; The two ends of second image processing system 5 are provided with the IEEE1394 standard interface, and computing machine 1 is regulated the position of these two ccd video camera 4b to regulate its focal length according to received image information, obtain distinct image information; The ccd video camera 4b that is positioned at directly over the control platform 2a is used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, is positioned at the image information on the short transverse that the ccd video camera 4c that controls platform 2a oblique upper is used to gather sample watermelon or watermelon to be measured; Light source 4a is the LED planar light source, and is fixed on the top of control platform 2a through light source bracing frame 4d; Second image processing system 5 adopts DSP high speed image disposal system.
The computing machine of present embodiment comprises the control system and first image processing system; Control system is connected with control platform 2a with direct current generator 3b, is used to carry out steering order, drives the rotation of direct current generator 3b and the rotation of drive controlling platform 2a; First image processing system is connected with two ccd video camera 4b, 4c; Calculate length, width and the height of sample watermelon or watermelon to be measured after being used for the image information of sample watermelon or watermelon to be measured handled, and set up volume-based model and calculate the volume of watermelon to be measured.
Like Fig. 2, wherein, first image processing system comprises image input/output module, pre-processing module, characteristic extracting module and model building module; The image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; Pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; The edge graph that characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates closed sides
Key parameter (being length, width and height); Model building module is used for the key parameter K value of match volume-based model according to characteristic and calculates the volume of watermelon to be measured according to volume-based model.
The present invention has versatility to the quality identification of melon and fruit, massive agricultural products; The Quality Detection of other melon and fruit and massive agricultural products can be with reference to the method for this embodiment; Concrete stripping and slicing characteristic to the melon and fruit of surveying, massive agricultural products; Change correlation parameter, just can detect new melon and fruit, stripping and slicing quality.
The above only is a preferred implementation of the present invention; Should be pointed out that for those skilled in the art, under the prerequisite that does not break away from know-why of the present invention; Can also make some improvement and replacement, these improvement and replacement also should be regarded as protection scope of the present invention.
Claims (10)
1. a quality of watermelon lossless detection method is characterized in that, comprising:
S1, choose a plurality of sample watermelons, adopt drainage to measure the initial volume of each sample watermelon respectively;
S2, the sample watermelon is transported to the control platform on the acquisition platform through induction system; Through the position of computer regulated control platform with adjusting sample watermelon; Utilize acquisition platform top camera acquisition sample watermelon image information and be transferred to computing machine, computing machine calculates length, width and the height of sample watermelon after with said Image Information Processing;
S3, set up the volume-based model of watermelon to be measured: V=4/3 * K * a * b * c; Wherein, V is the volume of watermelon to be measured; A, b, c are respectively length, width and the height of sample watermelon or watermelon to be measured, and K is a constant, according to the length of the initial volume of step S1 and step S2, width, highly simulate the K value;
S4, change the sample watermelon into watermelon to be measured and repeating step S2, measure length, width and the height of watermelon to be measured,, calculate the volume V of watermelon to be measured according to volume-based model V=4/3 * K * a * b * c;
S5, measure the quality of watermelon to be measured, and the density that calculates watermelon to be measured according to quality and the volume V of watermelon to be measured, the last quality of judging this watermelon to be measured according to density.
2. quality of watermelon lossless detection method as claimed in claim 1; It is characterized in that; Said video camera adopts two ccd video cameras; Said two ccd video cameras lay respectively at the control platform directly over and oblique upper, be connected with said computing machine through second image processing system respectively, by the position of said two ccd video cameras of said computer regulated; Be positioned at the ccd video camera of control directly over the platform and be used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, be positioned at the image information on the short transverse that the ccd video camera of controlling the platform oblique upper is used to gather sample watermelon or watermelon to be measured.
3. quality of watermelon lossless detection method as claimed in claim 1 is characterized in that, first image processing system in the said computing machine comprises image input/output module, pre-processing module, characteristic extracting module and model building module; Said image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; Said pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; The edge graph that said characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates length, width and the height of closed sides; Said model building module is used to the volume setting up volume-based model and calculate watermelon to be measured according to characteristic.
4. quality of watermelon lossless detection method as claimed in claim 3; It is characterized in that; Said pre-processing module adopts the adaptive threshold method that the image information of sample watermelon or watermelon to be measured is isolated from complex background, and adopts median filtering method to eliminate isolated noise spot.
5. quality of watermelon lossless detection method as claimed in claim 3; It is characterized in that; Said characteristic extracting module adopts morphology opening and closing operation method to carry out the filling in bianry image cavity and adopts SEQUENTIAL ALGORITHM to extract the limit characteristic; And adopt Shamos to ask the method for convex polygon diameter to calculate the diameter of closed sides, be length, width and the height of sample watermelon or watermelon to be measured.
6. quality of watermelon lossless detection method as claimed in claim 3 is characterized in that, the match of said model building module employing Hough transformation obtains the key parameter K value of volume-based model, and calculates the volume of watermelon to be measured according to said volume-based model.
7. quality of watermelon the cannot-harm-detection device is characterized in that, comprises computing machine and the induction system that is connected with said computing machine, acquisition platform and camera system; Said acquisition platform is provided with the control platform; Said control platform is connected with computing machine; Said induction system is used for sample watermelon or watermelon to be measured are transported to the control platform; Said camera system is positioned at the top of acquisition platform, is used to gather the image information of sample watermelon or watermelon to be measured and is transferred to computing machine; Said computing machine is regulated the position of camera system according to received image information, and calculates length, width and the height of sample watermelon or watermelon to be measured, sets up volume-based model and the volume that calculates watermelon to be measured simultaneously.
8. quality of watermelon the cannot-harm-detection device as claimed in claim 7 is characterized in that, said camera system comprises light source and two ccd video cameras; Said two ccd video cameras lay respectively at control platform directly over and oblique upper; Be connected with said computing machine through second image processing system respectively; Be positioned at the ccd video camera of control directly over the platform and be used to gather the length of sample watermelon or watermelon to be measured and the image information on the Width, be positioned at the image information on the short transverse that the ccd video camera of controlling the platform oblique upper is used to gather sample watermelon or watermelon to be measured; Said light source is fixed on the top of said control platform through the light source bracing frame.
9. quality of watermelon the cannot-harm-detection device as claimed in claim 7 is characterized in that, said computing machine comprises the control system and first image processing system; Said control system is used to carry out steering order; Said first image processing system is connected with camera system; Calculate length, width and the height of sample watermelon or watermelon to be measured after being used for the image information of sample watermelon or watermelon to be measured handled, and set up volume-based model and calculate the volume of watermelon to be measured.
10. quality of watermelon the cannot-harm-detection device as claimed in claim 9 is characterized in that, said first image processing system comprises image input/output module, pre-processing module, characteristic extracting module and model building module; Said image input/output module is used for the image information and the data of input and output sample watermelon or watermelon to be measured; Said pre-processing module is used for the visual information projection of sample watermelon or watermelon to be measured is carried out pre-service to gray space; The edge graph that said characteristic extracting module is used to extract sample watermelon or watermelon to be measured is as information, and calculates length, width and the height of closed sides; Said model building module is used for the key parameter of match volume-based model according to characteristic and calculates the volume of watermelon to be measured according to volume-based model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101101373A CN102654463A (en) | 2012-04-13 | 2012-04-13 | Watermelon quality NDT (non-destructive testing) method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012101101373A CN102654463A (en) | 2012-04-13 | 2012-04-13 | Watermelon quality NDT (non-destructive testing) method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102654463A true CN102654463A (en) | 2012-09-05 |
Family
ID=46730121
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012101101373A Pending CN102654463A (en) | 2012-04-13 | 2012-04-13 | Watermelon quality NDT (non-destructive testing) method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102654463A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103630074A (en) * | 2013-11-29 | 2014-03-12 | 北京京东尚科信息技术有限公司 | Method and device for measuring minimum package volume of object |
| CN104266935A (en) * | 2014-10-22 | 2015-01-07 | 合肥星服信息科技有限责任公司 | Multi-functional portable balance for determining maturity of watermelon |
| CN104627591A (en) * | 2015-02-05 | 2015-05-20 | 苏州得尔达国际物流有限公司 | Intelligent warehousing ex-warehouse risk control system |
| CN104764402A (en) * | 2015-03-11 | 2015-07-08 | 广西科技大学 | Visual inspection method for citrus size |
| CN105806743A (en) * | 2016-04-28 | 2016-07-27 | 西北农林科技大学 | Multi-view apple moldy core detection device and method |
| CN107899966A (en) * | 2017-12-06 | 2018-04-13 | 罗凯缤 | The shaddock quality sorting unit of view-based access control model technology |
| CN108057638A (en) * | 2017-12-06 | 2018-05-22 | 中国计量大学 | The shaddock quality sorting machine of view-based access control model technology |
| CN108097603A (en) * | 2017-12-06 | 2018-06-01 | 中国计量大学 | The shaddock quality method for separating of view-based access control model technology |
| CN109141234A (en) * | 2018-08-09 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of intelligent article recognition methods and device |
| CN109520888A (en) * | 2018-12-29 | 2019-03-26 | 浙江理工大学 | A kind of cheese denseness on-line detection device |
| CN110455679A (en) * | 2019-07-28 | 2019-11-15 | 张季敏 | A kind of Density Detection device and method thereof for flexible manufacturing system |
| CN113051992A (en) * | 2020-11-16 | 2021-06-29 | 泰州无印广告传媒有限公司 | Uniform speed identification system applying transparent card slot |
| EP4137804A1 (en) | 2021-08-20 | 2023-02-22 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method and system for the manual quality testing of fruit and vegetables and other foodstuffs |
| DE102021211546A1 (en) | 2021-08-20 | 2023-02-23 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung eingetragener Verein | Process and system for manual quality control of fruit and vegetables and other foodstuffs |
| CN115836976A (en) * | 2023-02-23 | 2023-03-24 | 四川新荷花中药饮片股份有限公司 | Production method of intelligent control system for production of toxic decoction pieces in Araceae |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907453A (en) * | 2010-07-23 | 2010-12-08 | 北京农业信息技术研究中心 | Online measurement method and device of dimensions of massive agricultural products based on machine vision |
-
2012
- 2012-04-13 CN CN2012101101373A patent/CN102654463A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907453A (en) * | 2010-07-23 | 2010-12-08 | 北京农业信息技术研究中心 | Online measurement method and device of dimensions of massive agricultural products based on machine vision |
Non-Patent Citations (5)
| Title |
|---|
| ALI BULENT KOC: "Determination of watermelon volume using ellipsoid approximation and image processing", 《POSTHARVEST BIOLOGY AND TECHNOLOGY》, vol. 45, 31 December 2007 (2007-12-31) * |
| KORO KATO: "Electrical Density Sorting and Estimation of Soluble Solids Content of watermelon", 《J.AGRIC.ENGNG RES.》, vol. 67, 31 December 1997 (1997-12-31) * |
| M. KHOJASTEHNAZHAND ET AL.: "Determination of orange volume and surface area using image processing technique", 《INT.AGROPHYSICS》, vol. 23, 31 December 2009 (2009-12-31), pages 237 - 242 * |
| M.OMID ET AL.: "Estimating volume and mass of citrus fruits by image processing technique", 《JOURNAL OF FOOD ENGINEERING》, vol. 100, 31 December 2010 (2010-12-31), pages 315 - 321 * |
| 周平 等: "基于机器视觉的鸡蛋体积与表面积计算方法", 《农业机械学报》, vol. 41, no. 5, 31 May 2010 (2010-05-31) * |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103630074A (en) * | 2013-11-29 | 2014-03-12 | 北京京东尚科信息技术有限公司 | Method and device for measuring minimum package volume of object |
| CN103630074B (en) * | 2013-11-29 | 2016-09-21 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus of Measuring Object minimum package volume |
| CN104266935A (en) * | 2014-10-22 | 2015-01-07 | 合肥星服信息科技有限责任公司 | Multi-functional portable balance for determining maturity of watermelon |
| CN104627591A (en) * | 2015-02-05 | 2015-05-20 | 苏州得尔达国际物流有限公司 | Intelligent warehousing ex-warehouse risk control system |
| CN104764402A (en) * | 2015-03-11 | 2015-07-08 | 广西科技大学 | Visual inspection method for citrus size |
| CN105806743A (en) * | 2016-04-28 | 2016-07-27 | 西北农林科技大学 | Multi-view apple moldy core detection device and method |
| CN108097603A (en) * | 2017-12-06 | 2018-06-01 | 中国计量大学 | The shaddock quality method for separating of view-based access control model technology |
| CN108057638A (en) * | 2017-12-06 | 2018-05-22 | 中国计量大学 | The shaddock quality sorting machine of view-based access control model technology |
| CN107899966A (en) * | 2017-12-06 | 2018-04-13 | 罗凯缤 | The shaddock quality sorting unit of view-based access control model technology |
| CN109141234A (en) * | 2018-08-09 | 2019-01-04 | 郑州云海信息技术有限公司 | A kind of intelligent article recognition methods and device |
| CN109520888A (en) * | 2018-12-29 | 2019-03-26 | 浙江理工大学 | A kind of cheese denseness on-line detection device |
| CN110455679A (en) * | 2019-07-28 | 2019-11-15 | 张季敏 | A kind of Density Detection device and method thereof for flexible manufacturing system |
| CN113051992A (en) * | 2020-11-16 | 2021-06-29 | 泰州无印广告传媒有限公司 | Uniform speed identification system applying transparent card slot |
| CN113051992B (en) * | 2020-11-16 | 2022-01-18 | 山东米捷软件有限公司 | Uniform speed identification system applying transparent card slot |
| EP4137804A1 (en) | 2021-08-20 | 2023-02-22 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V. | Method and system for the manual quality testing of fruit and vegetables and other foodstuffs |
| DE102021211546A1 (en) | 2021-08-20 | 2023-02-23 | Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung eingetragener Verein | Process and system for manual quality control of fruit and vegetables and other foodstuffs |
| CN115836976A (en) * | 2023-02-23 | 2023-03-24 | 四川新荷花中药饮片股份有限公司 | Production method of intelligent control system for production of toxic decoction pieces in Araceae |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102654463A (en) | Watermelon quality NDT (non-destructive testing) method and device | |
| CN101907453B (en) | Online measurement method and device of dimensions of massive agricultural products based on machine vision | |
| CN107782733B (en) | Image recognition nondestructive detection device and method for metal surface defects | |
| CN105654461B (en) | A kind of machine vision detection method of multiple fission conductor conductor spacer fracture | |
| CN106548182A (en) | Based on deep learning and the causal analytic pavement distress survey method and device of master | |
| CN106372638A (en) | Method and system for identifying brand and model of electronic equipment | |
| CN110694921B (en) | Vegetable sorting system and control method thereof | |
| CN103487729A (en) | Electrical equipment defect detection method based on fusion of ultraviolet video and infrared video | |
| CN105388162A (en) | Raw material silicon wafer surface scratch detection method based on machine vision | |
| CN104056790A (en) | Intelligent potato sorting method and apparatus | |
| CN106645180A (en) | Method for checking defects of substrate glass, field terminal and server | |
| CN205330670U (en) | Coal petrography recognition device based on study of dependence tolerance | |
| CN105549486A (en) | Tobacco topping sprouting inhibition detection control system based on machine vision | |
| CN106339722A (en) | Line knife switch state monitoring method and device | |
| CN114029237A (en) | Real-time sorting system and method for surface defects of aluminum profiles | |
| CN104048966A (en) | Big-law-based cloth cover defect detection and classification method | |
| CN109509173A (en) | A kind of method of counting and counting device of bacterial clump | |
| CN113655002A (en) | Recycled aggregate quality detection system with mortar on surface based on hyperspectral technology | |
| CN102680488B (en) | Device and method for identifying massive agricultural product on line on basis of PCA (Principal Component Analysis) | |
| CN110197483A (en) | Deep basal pit crack detection method based on vision signal | |
| CN106778409A (en) | A kind of code figure detection method and detecting system | |
| CN112800909A (en) | Self-learning type tobacco shred sundry visual image detection method | |
| CN208805156U (en) | A kind of battery on-line measuring device based on machine vision technique | |
| CN112258398A (en) | Conveyor belt longitudinal tearing detection device and method based on TOF and binocular image fusion | |
| CN204143498U (en) | A kind of point based on machine vision opens system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20120905 |