CN103801520B - The automatic well-chosen stage division of shrimp and device - Google Patents
The automatic well-chosen stage division of shrimp and device Download PDFInfo
- Publication number
- CN103801520B CN103801520B CN201410040879.2A CN201410040879A CN103801520B CN 103801520 B CN103801520 B CN 103801520B CN 201410040879 A CN201410040879 A CN 201410040879A CN 103801520 B CN103801520 B CN 103801520B
- Authority
- CN
- China
- Prior art keywords
- shrimp
- image
- raw material
- channel
- rowization
- 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.)
- Active
Links
- 241000238557 Decapoda Species 0.000 title claims abstract description 228
- 239000002994 raw material Substances 0.000 claims abstract description 141
- 238000012545 processing Methods 0.000 claims abstract description 34
- 238000005070 sampling Methods 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 28
- 230000008569 process Effects 0.000 claims abstract description 17
- 241000583629 Cypridopsis vidua Species 0.000 claims abstract description 9
- 238000007664 blowing Methods 0.000 claims abstract description 5
- 238000003066 decision tree Methods 0.000 claims description 15
- TZCXTZWJZNENPQ-UHFFFAOYSA-L barium sulfate Chemical compound [Ba+2].[O-]S([O-])(=O)=O TZCXTZWJZNENPQ-UHFFFAOYSA-L 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 2
- 230000031068 symbiosis, encompassing mutualism through parasitism Effects 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 6
- 239000000178 monomer Substances 0.000 description 16
- 230000000694 effects Effects 0.000 description 13
- 239000012535 impurity Substances 0.000 description 13
- 230000001105 regulatory effect Effects 0.000 description 12
- 241000196324 Embryophyta Species 0.000 description 8
- 230000001276 controlling effect Effects 0.000 description 8
- 239000004033 plastic Substances 0.000 description 7
- 239000010410 layer Substances 0.000 description 6
- 238000007781 pre-processing Methods 0.000 description 6
- 230000011218 segmentation Effects 0.000 description 6
- 238000012549 training Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000007667 floating Methods 0.000 description 4
- 238000003306 harvesting Methods 0.000 description 4
- 239000000463 material Substances 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000009826 distribution Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 239000000523 sample Substances 0.000 description 3
- 241000251468 Actinopterygii Species 0.000 description 2
- 241001454694 Clupeiformes Species 0.000 description 2
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 2
- 235000019513 anchovy Nutrition 0.000 description 2
- 238000009360 aquaculture Methods 0.000 description 2
- 244000144974 aquaculture Species 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000007599 discharging Methods 0.000 description 2
- 235000019688 fish Nutrition 0.000 description 2
- 239000011159 matrix material Substances 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 239000000741 silica gel Substances 0.000 description 2
- 229910002027 silica gel Inorganic materials 0.000 description 2
- 229960001866 silicon dioxide Drugs 0.000 description 2
- 239000002356 single layer Substances 0.000 description 2
- 239000002351 wastewater Substances 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- DHKHKXVYLBGOIT-UHFFFAOYSA-N acetaldehyde Diethyl Acetal Natural products CCOC(C)OCC DHKHKXVYLBGOIT-UHFFFAOYSA-N 0.000 description 1
- 125000002777 acetyl group Chemical class [H]C([H])([H])C(*)=O 0.000 description 1
- 230000003213 activating effect Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000903 blocking effect Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 230000003139 buffering effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 229920001971 elastomer Polymers 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 229920001821 foam rubber Polymers 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000005571 horizontal transmission Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000017074 necrotic cell death Effects 0.000 description 1
- 230000005693 optoelectronics Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000002085 persistent effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000010865 sewage Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 239000007921 spray Substances 0.000 description 1
- 229910001220 stainless steel Inorganic materials 0.000 description 1
- 239000010935 stainless steel Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000005211 surface analysis Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses the automatic well-chosen grading plant of a seed shrimp, comprise feeding system, sort channel, adopt drawing system, hierarchy system and image processing system; Feeding system is used for exporting sort channel to by treating that the raw material shrimp of sorting is single; Sort channel is divided into the buffer channel and sampling channel that are connected successively, sampling channel is separated into multiple single-rowization passage, be provided with multiple directions adjuster in buffer channel, the raw material shrimp for being exported by feeding system is divided into single and regulates each raw material shrimp to enter the attitude of corresponding single-rowization passage; Adopt drawing system for gathering the image of raw material shrimp; Hierarchy system comprises the air nozzle corresponding with single-rowization passage, and this air nozzle is controlled by image processing system, enters different splicing grooves for blowing shrimp body; Image processing system is used for analysis chart picture, to the image grading process of each shrimp body, according to classification results, and sends the signal controlling hierarchy system.The invention also discloses the automatic well-chosen stage division of a seed shrimp.
Description
Technical field
The present invention relates to fishery wastewater technical field, particularly relate to automatic well-chosen stage division and the device of a seed shrimp.
Background technology
China, as one of the whole world six large shrimps producing countries, all will carry a large amount of raw material shrimps every year to international market.But China's raw material shrimp outlet whole price level is low, market share is few, competitiveness is not enough is the reason causing China's raw material shrimp export volume to reduce.Along with the industrial structure deepens constantly adjustment, how support shrimp field rise one after another enclose the pool cultivation, large-scale cultivation base makes workman be busy with cultivation to antenatal shrimp species and breeding, but for postpartum raw material shrimp good harvest this need most drop into a large amount of human and material resources, financial resources link but often out in the cold, cause a lot of raw material shrimp to cause the mortality of raw material shrimp not because of degree of attention in postpartum, cause serious economic loss to enterprise and raw material shrimp aquaculture industry.
For a long time, from the raw material shrimp just fished for up, the mode of selected classification raw material shrimp is all completed by the hand picked mode of workman, this mode not only inefficiency, and people is when fatigue, easily produces erroneous judgement; In today that labour is relatively deficient and expensive, use the mode of a large amount of labour selected normal shrimp from raw material shrimp out-of-date already, the equipment that our amount in need of immediate treatment is large, floor space is little, structure is simple, cost is low, automaticity is high replaces the mode of artificial work, so not only can improve accuracy rate and the efficiency of the selected classification of raw material shrimp, but also the expense of labour can be reduced, improve efficiency of having a good harvest postpartum.
Usually there is following situation in the general raw material shrimp fished for from pond: usually can be mixed into the raw material shrimp that (1) salvages because of anoxic and the raw material shrimp of necrosis, if remove not in time, easily normal shrimp is polluted, the latter is caused to go bad, be unfavorable for post-production and storage, reduce the economic worth of raw material shrimp; (2) season for a bumper harvest of general raw material shrimp normally during the broiling summer, manyly salvages disembarkation and the shrimp body floating over splendid attire raw material shrimp bucket surface is easy to be baked by hot sunlight and dead, thus can produce pollution to other normal shrimps; (3) fish in the raw material shrimp of disembarkation and be also mixed with some small weedy being not easy with the naked eye to be found by people, be easily mixed in the finished product be processed into.
Through retrieval, document " Automaticgradingandpackingofprawns " develops a kind of raw material shrimp based on computer vision packaging and grading plant.This system obtains the general image of shrimp by camera, then is calculated the parameter such as shape, the deviation angle, abdomen shell flexibility of shrimp by image information, and marks shrimp head, shrimp tail and shrimp centre position.Patent publication No. is that a kind of bottle based on machine vision technique that Japanese patent discloses of JP3603353B2 detects grading plant, utilize the outward appearance such as color, shape of machine vision technique to plurality of classes bottle to detect, online real-time grading can be carried out to bottle.Although this patent has used machine vision method to solve the recovery classification problem of waste and old bottle, this classification method of discrimination is comparatively simple, and accuracy is not high; Number of patent application is the impurity elimination sorting unit that Chinese patent provides a kind of anchovy peculiar to vessel, shrimp is processed of 201010165377.4, comprise multistage screening dish, feed hopper, shaking device and frame, it can be only limitted to anchovy and shrimp two kinds by selected species, and selected scope awaits further raising; Number of patent application be 201220713538.3 Chinese patent employ the prawn that a kind of method based on machine vision detects the different quality rank of classification, singulate induction system is wherein made up of prawn feed hopper, two vibration feed appliances, two sensors, the single-row draw-in groove of individual layer, guide groove and pose adjustment devices.In this patent, the shell of prawn is very easily pulverized, and adopts the mode of vibration feeding, and easy raw material shrimp body itself produces microlesion; Transport tape adopts horizontal transmission mode and it only has a row guide groove that material can be allowed to pass through, and treating capacity is little and speed is slower; Patent publication No. is the classification machine that the BP of GB2160653A has invented a selected raw material shrimp, by one capable of circulation, can lower, the probe be fixed on rotatable dish directly contacts raw material shrimp body, when probe has felt abnormal shrimp, damage shrimp, dystopy shrimp, can give executing agency signal, thus impurity is rejected by starting nozzle air blowing.This method can produce it because of contact shrimp body to be polluted; The height of rotating disc need regulate at any time according to the thickness of shrimp body, and automaticity is not high.
Summary of the invention
In order to overcome defect of the prior art, the present invention provides the method and apparatus that a set of raw material shrimp treating capacity is large, processing speed is fast, integrated application artificial intelligence, electronic technology, Principle of Communication, Machine Design, physics of photography and computer hardware technique carry out the selected classification of external appearance characteristic to raw material shrimp, and result accurately and reliably.
Automatic well-chosen grading plant of the present invention, mainly in the raw material shrimp season for a bumper harvest, for under being mixed with weeds, small fish, anoxic in the raw material shrimp fishing for disembarkation, bake the problem of the impurity such as shrimp, also in order to meet the needs of the selected classification of product in Product processing, a kind of automatic well-chosen stage division and device being suitable for that use in raw material shrimp aquaculture field and processing factory, that floor space is little, intensive degree the is high seed shrimp based on computer vision technique of specialized designs exploitation.
The automatic well-chosen grading plant of one seed shrimp, comprises feeding system, sort channel, adopts drawing system, hierarchy system and image processing system;
Feeding system is used for exporting sort channel to by treating that the shrimp body of sorting is single;
Sort channel is divided into the buffer channel and sampling channel that are connected successively, sampling channel is separated into multiple single-rowization passage, is provided with multiple directions adjuster and is divided into single for the shrimp exported by feeding system and regulates each shrimp body to enter the attitude of corresponding single-rowization passage in described buffer channel;
Adopting drawing system for gathering the image of shrimp body in each single-rowization passage, adopting drawing system and comprising and be positioned at sampling channel up and down and two lighting box arranging of dislocation, in each lighting box, being equipped with camera;
Hierarchy system comprises the air nozzle corresponding with each single-rowization passage, and this air nozzle is controlled by described image processing system, enters different splicing grooves for blowing the shrimp body exported by single-rowization passage;
Image processing system, for analyzing described image, to the image grading process of each shrimp body, according to classification results, and sends the signal controlling hierarchy system.
Described feeding system comprises support, rack-mount feeding box and the conveyer belt be in tilted layout, the oblique upper of this conveyer belt is provided with backgauge soft board, conveyer belt bottom is stretched in feeding box, and conveyer belt surface is provided with the draw-in groove holding single shrimp body, the side of feeding box is provided with osculum, and conveyer belt is made up of the plastic chain plate of multiple band leaking hole.
The raw material shrimp of pending selected classification is placed with in feeding box, osculum bottom it enters the sewage of feeding box with shrimp for discharging, raw material shrimp exports feeding box by the conveyer belt of persistent movement, conveyer belt is provided with draw-in groove, this draw-in groove is arranged along the width of conveyer belt, row's raw material shrimp only can be allowed in its inside, accumulation may be formed on draw-in groove for shrimp body, the raw material shrimp that backgauge soft board now can be piled up in floating draw-in groove, stop that stacking raw material shrimp passes through simultaneously, after the effect of backgauge soft board, the raw material shrimp in draw-in groove is single layer arranging distribution.
Feeding system also comprises the conveyer frames installing conveyer belt, and be coupling in the middle part of conveyer frames on support, one end of conveyer frames is supported on the bracket by height regulating rod.
In the present invention, the angle of inclination of conveyer belt can be regulated by height regulating rod, to adapt to the needs of different size or raw material shrimp species class, one end of height regulating rod is hinged on support side, the other end is bolted on support, by the cooperation position of mobile bolt and height regulating rod, carrys out the height regulating rod length between adjusting bolt and conveyer frames, realize the adjustment of conveyer frames setting angle, thus drive the angle of inclination regulating conveyer belt.
Selecting of conveyer belt, comparatively large on the impact of whole selected grading plant, traditional conveyer belt is quality of rubber materials, and draw-in groove is straight forming in conveyer belt process; But in the present invention, the conveyer belt of preferred use is made up of the plastic chain plate of multiple band leaking hole, connected by rotating shaft between adjacent two plastic chain plates, every block plastic chain plate is provided with a spacing lug, be described draw-in groove between adjacent two spacing lugs, raw material shrimp is single to be distributed in draw-in groove, simultaneously on raw material shrimp with moisture, can pass through leaking hole, reduce the moisture entering sort channel.
Sort channel is divided into the buffer channel and sampling channel that are connected successively, and two sections of passages are all in tilted layout, and the angle of inclination of sampling channel is greater than the angle of inclination of buffer channel.Buffer channel has cushioning effect, and the raw material shrimp preventing conveyer belt from exporting directly enters in sampling channel, to slow down the sliding speed of raw material shrimp, is convenient to the IMAQ adopting drawing system; Simultaneously, direction adjuster in buffer channel has compartmentation, each raw material shrimp is made to enter a single-rowization passage, can also the utilization orientation adjuster attitude that regulates raw material shrimp to slide in single-rowization passage, keep the cardinal principle posture gathering image Raw shrimp, be convenient to comparison and the analysis of image processing system.
Wherein, direction adjuster comprises the locating piece be arranged in buffer channel, and locating piece is fixed with guide plate towards one end of feeding system, and this guide plate has the guiding surface acting on raw material shrimp.Buffer channel is partitioned into monomer passage by locating piece, each monomer passage is corresponding with single-rowization passage, guide plate is arranged on the end of locating piece, this guide plate comprises two pieces of monomer guide plates of integrative-structure, two pieces of monomer guide plates are in a certain angle, every block monomer guide plate has a guiding surface, guide plate is used for the raw material shrimp that separately conveyer belt exports, raw material shrimp monomer is made to enter in different single-rowization passages respectively, raw material shrimp passes by between the guiding surface of monomer passage both sides, and guiding surface has the effect regulating raw material shrimp attitude.
Spacing block is fixed with between adjacent two single-rowization passages; the spacing block end being positioned at single-rowization passage feed end is wedge shape; the wedge shaped tip of spacing block may be used for regulating the cruising attitude of raw material shrimp in single-rowization passage; width and the raw material shrimp size of each single-rowization passage adapt, and impel it singulate further.
Adopt drawing system comprise to be fixed on above sampling channel and below passage and inwall scribble barium sulfate lighting box, be arranged in the light source in lighting box and be positioned at the camera at lighting box top, and be also provided with the sensor be connected with image processing system in each single-rowization passage, for responding to the shrimp body that single-rowization passage passes through, and send the signal that the described camera of control carries out image taking.
Simultaneously, the input of each single-rowization passage and output are fixed with first sensor and the second sensor respectively, two sensors all access described image processing system, first sensor controls for sending the signal that camera carries out image taking, and the second sensor sends the signal opening air nozzle; First sensor is for responding to the raw material shrimp entering single-rowization passage, first sensor is after raw material shrimp touches, send and control the signal that camera carries out image taking, second sensor is for responding to the raw material shrimp skidding off single-rowization passage, after second sensor is touched, according to the classification results of image processing module, control the magnetic valve corresponding with substandard products and start, the trigger signal opens solenoid valve that magnetic valve sends according to the second sensor, control air nozzle blows raw material shrimp and enters substandard products splicing groove.
If only install separately the lighting box of, only can gather shrimp body direct picture to analyze, blind area is existed for the analysis of back side tool shrimp body defective, therefore, for identification is more accurate, reduce error, the base plate that the present invention arranges sampling channel is transparence, and up and down lighting box is set respectively at sampling channel, and upper and lower two lighting box are staggeredly arranged, and prevent from disturbing each other, and according to the sliding speed of shrimp body, there is certain shooting between camera in two lighting box to postpone, make the position of shrimp body substantially be in image medium position.Camera is all controlled by the signal that sensor sends, and makes two cameras successively can gather the image of raw material shrimp front and back, and this raw material shrimp image of full surface analysis also provides grade discrimination, makes the selected classification of shrimp more accurate.
In the present invention, also be provided with the bracing frame installing sort channel, the bracing frame being positioned at sort channel output is provided with the first baffle plate and second baffle, first baffle plate acts on the raw material shrimp freely glided by each single-rowization passage, second baffle is arc and acts on the raw material shrimp of being blown by air nozzle, and the face that the first baffle plate and second baffle contact with raw material shrimp is equipped with supple buffer layer.
After being analyzed by image processing system, raw material shrimp sort channel skidded off is divided into raw material and impurity or certified products and substandard products two class, wherein certified products skids off rear free-falling along passage, by falling in certified products splicing groove after the first baffle, impurity to skid off after track under the blowing of air nozzle, to fall on second baffle and to fall in substandard products splicing groove along second baffle, realizing the selected classification of raw material shrimp quality; Two baffle plates are equipped with supple buffer layer, and this cushion can be foam-rubber cushion or silicagel pad, to reduce the collsion damage of raw material shrimp.
Present invention also offers the automatic well-chosen stage division of a seed shrimp, comprise the following steps:
1) feeding system exports sort channel to by single for shrimp body, and each shrimp body slides with the single-rowization passage of the attitude adapted in sort channel;
2) image of collected by camera shrimp body is utilized, and utilize image processing system to carry out pretreatment to the image collected, obtain the area-of-interest in raw material shrimp image, gray level co-occurrence matrixes information in raw material shrimp of extracting, as textural characteristics, uses decision tree classifier to classify to the textural characteristics extracted;
3) hierarchy system is according to described classification results, and control air nozzle blows the raw material shrimp skidded off by single-rowization passage and enters different splicing grooves.
In step 2) in, use 9 × 9 windows to carry out mean filter process to raw material shrimp image, to each point gray value that each point average gray in 9 × 9 neighborhoods around each pixel of this image replaces this image original in Image semantic classification; Region of interesting extraction process is as follows:
If the visual field actual (tube) length of camera is x, wide is y, and raw material shrimp actual (tube) length that image occupies is x
1, wide is y
1, according to formula:
Can calculate the size of area-of-interest, wherein, l represents the length of area-of-interest, and w represents the wide of area-of-interest.
In step 2) in, area-of-interest is used to gray scale symbiosis battle array extracts entropy, angle second moment, contrast are divided and the feature of the moment of inertia, again according to 15 °, 30 °, 45 °, 60 °, 90 °, 120 °, 150 °, 180 ° eight direction calculating mean entropies and, average angle second moment and, average contrast divide and, average inertia square and, specific formula for calculation is:
Mean entropy and:
Average angle second moment and:
Average contrast divide and:
Average inertia square and:
Wherein ENT, ASM, IDM, GXJ represent that entropy, angle second moment, contrast are divided and the moment of inertia respectively, the mean entropy calculated by above-mentioned formula and, average angle second moment and, average contrast divide and, average inertia square and, be described textural characteristics.
According to textural characteristics obtained above, use decision tree classifier to carry out Decision Classfication to the textural characteristics best embodying original image, travel through whole decision tree, when leaf node is " just ", corresponding is certified products; When leaf node is " bearing ", corresponding is substandard products.
Compared with prior art, the beneficial effect that the present invention has is:
The mode that this device employs single material loading instead of traditional vibrations feeding style, and not easily prawn body causes damage; Utilize the difference of the speed of shrimp in sort channel and the speed on buffer board that raw material shrimp can be made to form singulate effect; Downslide slideway adopts two lighting box designs can obtain the full superficial makings information of shrimp, and more comprehensively, accuracy of identification is higher for feature.The design of multi-channel mode, multipair sensor and multiple nozzle makes each passage independently can carry out respective operation, and treating capacity increases and speed is accelerated; The corresponding image processing algorithm of adjustable adapts to the change of detected object; Whole system overcomes the few shortcoming of traditional mechanical type classifying equipoment Testing index, and accuracy of detection is higher simultaneously, and human-computer interaction interface is friendly, and be applicable to operative, intelligence degree is high.
Accompanying drawing explanation
Fig. 1 is system architecture schematic diagram of the present invention;
Fig. 2 is side view in Fig. 1;
Fig. 3 is the structural representation of feeding system in Fig. 1;
Fig. 4 is the local structural graph of backgauge soft board in Fig. 3;
Fig. 5 is the structural representation of sort channel;
Fig. 6 is the structural representation of two pieces of baffle plates;
Fig. 7 is PC-AVR host-guest architecture figure;
Fig. 8 is the workflow diagram of system;
Fig. 9 is image capture module flow chart;
Figure 10 is decision tree classification flow process.
Detailed description of the invention
Below using raw material shrimp as selected classification object, in conjunction with Figure of description, a point automatic well-chosen grading plant for invention is described in further detail.
As depicted in figs. 1 and 2, in the present embodiment, the automatic well-chosen grading plant of a seed shrimp, comprises feeding system, sort channel, adopts drawing system, hierarchy system and image processing system.
Feeding system is used for exporting sort channel to by treating that the raw material shrimp of sorting is single, and specifically as shown in Figure 3, it comprises support 1 to the structure of feeding system, and the conveyer belt 4 being arranged on the feeding box 2 on support 1 and being in tilted layout, stretches in feeding box 2 bottom this conveyer belt 4.
Place in feeding box 2 and need the raw material shrimp of sorting, side is provided with osculum 3, for discharging the waste water entering feeding box with shrimp; Conveyer belt 4 is for constantly exporting the raw material shrimp in feeding box 2, it is arranged on corresponding conveyer frames 5, the both sides of support 1 are fixed with installing plate 7, conveyer frames 5 both sides are provided with the rotating shaft be rotatably assorted with installing plate 7, the both sides of conveyer frames 5 are also hinged with height regulating rod 6, this height regulating rod 6 is bolted on support 1, and the inclination of the adjustable conveyer frames 5 of height regulating rod 6, realizes the adjustment at conveyer belt 4 angle of inclination.
The surface of conveyer belt 4 is provided with the draw-in groove holding raw material shrimp, and this draw-in groove is arranged along the width of conveyer belt 4, and the degree of depth of draw-in groove is no more than the average thickness of raw material shrimp, and the width of shrimp body and draw-in groove adapts, and the raw material shrimp namely in each draw-in groove is single layer arranging distribution.As shown in Figure 4, the top of conveyer belt 4 is furnished with backgauge soft board 23, this backgauge soft board 23 is bolted on support bar 25, the two ends of support bar 25 are fixed on the base 24 of conveyer frames 5 both sides, and the end face of base 24 is provided with U-lag, and support bar 25 end is bolted in U-lag, the end of backgauge soft board 23, is along the surface pressing close to conveyer belt 4, its effect be by overlap on a moving belt 4 raw material shrimp floating, prevent raw material shrimp from piling up on the transport belt 4, be convenient to single-rowization of follow-up raw material shrimp.
Sort channel is engaged on the output at conveyer belt 4 top, for accepting the raw material shrimp exported by conveyer belt 4, its concrete structure as shown in Figure 5, comprise the buffer channel 8 and sampling channel 12 that are connected successively, two sections of passages are all in tilted layout, and the angle of inclination of sampling channel 12 is greater than the angle of inclination of buffer channel 8, angle of inclination is here the angle between horizontal plane.
The raw material shrimp that buffer channel 8 falls for receiving conveyer belt 4, slows down the speed namely entered in sampling channel, and buffer channel 8 is also provided with both direction adjuster, for the pose adjustment of raw material shrimp, and the raw material shrimp that conveyer belt exports is carried out monomer separately; Direction adjuster comprises the locating piece 9 be arranged in buffer channel 8, and locating piece 9 is fixed with guide plate 10 towards one end of feeding system, and this guide plate 10 has the guiding surface acting on raw material shrimp; Buffer channel 8 for installing and fixed guide plate 10, and is divided into multiple monomer passage by locating piece 9; Guide plate 10 comprises the monomer guide plate of two pieces of integrative-structures, and two pieces of monomer guide plate groups are at a certain angle, the tip of angle is towards conveyer belt 4, there is the effect that guiding separates shrimp body, single raw material shrimp passes through by between the monomer guide plate of each monomer passage both sides, the monomer guide plate adjustable of monomer passage both sides, by the attitude of raw material shrimp, makes shrimp body enter in sampling channel 12 to be fixed on attitude.
The base plate of sampling channel 12 is fixed with two spacing blocks 11, sampling channel 12 is separated into three single-rowization passages, each single-rowization passage receives the raw material shrimp that corresponding monomer passage skids off respectively, and spacing block 11 end of sampling channel 12 feed end is wedge shape, two inclined-planes of tapered end also have the effect of guiding and pose adjustment, shrimp body is guided to enter in corresponding single-rowization passage, and suitably correct the cruising attitude of raw material shrimp in single-rowization passage, be convenient to the IMAQ of camera 21 and follow-up graphical analysis.
Buffer channel 8 is hinged on conveyer frames 5 top by rotating shaft 20, sampling channel 12 is arranged on bracing frame 14, and each single-rowization passage both sides are all provided with sensor 26, for responding to the raw material shrimp passed through, sampling channel 12 has transparent base plate simultaneously, and it is all provided with up and down and adopts drawing system.
As shown in Figure 5, adopt drawing system and comprise lighting box 13, light source 22 and camera 21.Lighting box 13 is fixed on bracing frame 14, two lighting box 13 difference arranged in dislocation are at sampling channel 12 upper and lower, the inwall of lighting box 13 scribbles barium sulfate, uniformity and the intensity of illumination of light source 22 irradiation can be increased, light source 22 is fixed on the inwall surrounding of lighting box 13, is specially the annular light source be fixed on inwall.The two ends up and down of sampling channel 12 are provided with sensor 26 and sensor 30, wherein camera 21 is controlled by sensor 26, when raw material shrimp touches the sensor 26 of single-rowization passage both sides, sensor 26 sends signal to image processing system, image processing system receives this unblanking camera 21 and gathers image, and image is analyzed, the instruction controlling hierarchy system is then sent according to analysis result.The raw material shrimp that sensor 30 skids off for responding to each single-rowization passage, the magnetic valve controlling air nozzle 27, after the instruction receiving hierarchy system, is in holding state, when raw material shrimp activating sensor 30, send the signal starting magnetic valve, open air nozzle 27 and blow raw material shrimp.Adopting in figure process, for reducing external environment to the impact of raw material shrimp image, the side that sampling channel 12 is relative with each lighting box 13 is provided with background board 29, for isolating external environment.
Hierarchy system comprises and is positioned at sampling channel 12 output bracing frame 14 and is provided with cross bar 15, this cross bar 15 is fixed with three air nozzles 27, and be provided with the magnetic valve controlling each air nozzle 27, the corresponding single-rowization passage of each air nozzle 27, and magnetic valve is controlled by described image processing system.After being analyzed by image processing system, raw material shrimp sort channel skidded off is divided into raw material and impurity or certified products and substandard products two class, wherein certified products skids off rear free-falling along passage, for impurity, image processing system sends control instruction, after corresponding magnetic valve receives instruction, open air nozzle 27, change the track that impurity skids off single-rowization passage, impurity and certified products are fallen in different splicing grooves, realizes the selected classification of raw material shrimp.
Simultaneously, as shown in Figure 6, bracing frame 14 is also provided with the first baffle plate 16 and second baffle 17, first baffle plate 16 is positioned on the fall trajectory of certified products shrimp, and second baffle 17 is positioned on the fall trajectory of impurity or substandard products, after certified products collides the first baffle plate 16, fall in certified products splicing groove 19, impurity or substandard products, under the effect of air nozzle 27 air-flow, fall on second baffle 17, and then landing is in substandard products splicing groove 18.For reducing damage during raw material shrimp collision baffle plate, the face that two baffle plates contacts with raw material shrimp is all with supple buffer layer 28, and can be spongy layer or layer of silica gel etc., meanwhile, each splicing groove be all contained with water, the quality of further maintenance raw material shrimp.
In the present embodiment, the computer in image processing system is connected with camera by cable interface, and computer interface RS-233 is connected with the electromagnetic valve controlling system controlling three magnetic valves by USB converter.
Wherein, the camera 23 serial DMK-23G618 area array cameras that adopt German imaging company to produce; Camera lens is the model that Chinese Wei Tu vision Science and Technology Ltd. produces is VT-LEM0618-MP3; Conveyer belt is the acetal plastic carrier bar that white has leaking hole and draw-in groove; Electromagnetic valve controlling system is AVR; Buffer channel is stainless steel; Sensor in single-rowization passage is laser type sensor, concrete adopt Japanese Omron company to produce optoelectronic switch that a pair model is respectively E3Z-T61-D and E3Z-T61-L.
The selected hierarchy system of this cover raw material shrimp adopts the primary and secondary structure of PC-AVR, and its structure as shown in Figure 7.In feeding system, conveyer belt 4 inclination angle can regulate, to adapt to different shrimp body thickness.Conveyer belt 4 continually can serve draw-in groove by several rows of for raw material shrimp, and the raw material shrimp of batch is upwards transmitted with single form; Three raw material shrimps can be placed at most in each draw-in groove, due to the difference of shrimp body size, another draw-in groove may form accumulation; If there are several raw material shrimps to be accumulated in together, then backgauge soft board 23 floating for the raw material shrimp of overlap, will make the effect that only there is single shrimp in each draw-in groove.Raw material shrimp can be made to form singulate effect by the wedge shaped tip of draw-in groove, direction adjuster and spacing block 11.Buffer channel 8 plays the effect of buffering to the raw material shrimp rising to peak preparation whereabouts.Be fixed on the direction adjuster on buffer channel 8, the stance adjustment of raw material shrimp is consistent at downslide traffic direction with it to cephlad-caudal.There is certain angle of inclination in sampling channel 12 and ground, raw material shrimp can move downward under gravity gradually.The inclination angle of buffer channel 8 can regulate, the angle theta of sampling channel 12
2indirectly can determine the tiltangleθ of buffer channel 8
1, θ
1be greater than the angle of friction of shrimp and buffer channel 8 storeroom, must θ be ensured
1< θ
2the speed that raw material shrimp just can be made to glide on buffer channel 8 is less than its speed on sampling channel 12, at this moment just can ensure that raw material shrimp is unlikely to pile up in sampling channel 12, impel the singulation of shrimp.
Before whole system brings into operation, first to carry out image registration to adopting drawing system: the position, middle three onesize round plastic balls being fixed on two lighting box up and down perpendicular to inclined-plane, open the camera 21 be connected with PC, open the annular light source of the side that to coexist with camera 21 simultaneously, round plastic ball is arranged in immediately below camera 21 just and is that four faces are symmetrical in the position that camera 21 shows.Regulate camera inherent parameters, comprise aperture, the time postponing exposure, frame per second, shutter opening time and gain.In the present system when these parameters are adjusted to following numerical value, the photo of camera shooting is the most clear: aperture f/16, wherein f represents the diameter of the effective aperture of camera, postpones time for exposure 50000us, frame per second 120fps, shutter opening time 1/2000s, gain-adjusted 17.86db.At this moment PC can show the situation of adopting in drawing system in real time, prepares to adopt figure.
In the present embodiment, the course of work of device as shown in Figure 8, when raw material shrimp is through sensor 26, a pulse daley signal can be produced, when arriving immediately below camera 21 Deng raw material shrimp, camera 21 accept sensor produce triggering signal take pictures, using image transmitting give as the image processing module in the image processing system of host computer, below each step be all mutually related, previous step processing result image supplies next step and uses, as shown in Figure 9.
1, the hard trigger module flow process of camera: because three pairs of laser flip flops have been installed in the upside of lighting box up, the downside of below lighting box there are also installed three pairs of laser flip flops, but their effect is different: the former is used to trigger camera and adopts figure, the latter is used to trigger magnetic valve and opens air nozzle.A pair trigger Laser emission mouth is just to putting under normal circumstances, mutually send laser, as long as have object through launching by blocking laser, trigger can produce an electric pulse instantaneously to the single-chip microcomputer of camera or connected electromagnetic valve, and the time that the signal passing to camera can postpone according to it is selected the moment of moment and the exposure of taking to catch image to pass to after PC is for further processing; The signal passing to single-chip microcomputer can Controlling solenoid valve according to result.
2, image pre-processing module flow process: because extraneous factor is comparatively large to the interference of camera attribute own, we need to use the image noise reduction in image pre-processing module and spinning solution necessarily to process the image obtained.If original image G (m, n) represents, use 9 × 9 windows to carry out mean filter process to image, the gray value replacing this image original with the average gray of each point in 9 × 9 neighborhood of pixels, the image after process is used
represent:
Wherein, S is the set of the point set coordinate in point (m, n) neighborhood, but does not wherein comprise (m, n) point, and M is the sum of set internal coordinate point.
Image
in the gray value of each pixel determine by the average gray of several pixel in the neighborhood of specifying being included in (m, n).When raw material shrimp image departs from calibrating position, the angle departing from calibration chart picture according to distorted image utilizes linear interpolation method infinitely to approach the pixel of distorted image Plays image along its angle offset clockwise or counterclockwise, thus makes its result just be positioned at the center position of camera.
3, target area segmentation block process: region of interesting extraction segmentation is carried out to the image after image pre-processing module process.In this module, the minimum enclosed rectangle that in region of interest domain representation entire image, prawn occurs.If the visual field actual (tube) length of camera is x, wide is y, and image Raw actual (tube) length that shrimp occupies is x
1, wide is y
1from the attribute of camera own, the image pixel abscissa span of its shooting is [0,640], and ordinate span is [0,480], first take multiple raw material shrimp images in advance, add up the image pixel area mean value that its Raw shrimp occupies, i.e. interested pixel region, be set to the length that l × w(l represents interested pixel region, w represents the wide of interested pixel region) pass through formula:
The scope of area-of-interest can be calculated, because the abscissa of this viewing field of camera scope is three passages just, actual area-of-interest transverse axis can be calculated by formula (2), longitudinal axis range be respectively [0, x] and
actual area-of-interest length and width be respectively x and
minimum target image is comprised in this regional extent.
Trisection segmentation is carried out to the target image that this width comprises three single width raw material shrimp images below, because the actual length and width in the visual field of camera is x and y, actual (tube) length that raw material shrimp occupies, wide for x
1and y
1, therefore can calculate actual area-of-interest transverse axis according to (1), longitudinal axis excursion is respectively:
with
actual area-of-interest length and width is respectively
with
therefore the redundancy of initial feed shrimp image is removed, and comprises minimum list raw material shrimp image only in this regional extent.
4, gray level co-occurrence matrixes computing module:
Gray level co-occurrence matrixes is exactly the common method that a kind of spatial correlation characteristic by studying gray scale describes texture, it to be used for describing from certain angle and specific range direction two pixels from this pixel to the probability of one other pixel, the integrated information of the reflection direction of image, interval, amplitude of variation and speed.This module employs the feature of following conventional gray level co-occurrence matrixes: entropy, angle second moment, contrast are divided and the moment of inertia.
(1), entropy (ENT)
ENT is the tolerance of the information content that image has, and is the tolerance of a randomness, reflects the randomness of pixel value in raw material shrimp image.If image rill depth information does not exist, then in gray level co-occurrence matrixes, element is almost nil, and entropy is close to zero; If when in gray level co-occurrence matrixes, all values is all equal, entropy gets maximum; If when the value in gray level co-occurrence matrixes is very uneven, entropy is very little.
(2), angle second moment (ASM)
ASM is the quadratic sum of gray level co-occurrence matrixes element value, can be called energy again, reflects raw material shrimp gradation of image and to be evenly distributed degree and texture fineness.When being distributed on leading diagonal in element set in co-occurrence matrix, illustrate that the intensity profile of raw material shrimp image is comparatively even, macroscopic view, fineness and the ASM of image texture distribution are closely bound up: ASM is larger, and image texture degree is thicker; Otherwise image texture degree is thinner.
(3), contrast is divided (IDM)
IDM is that metric space gray level co-occurrence matrixes element is expert at or similarity degree on column direction, and its value size reflects the correlation of local gray-value in raw material shrimp image.If gray level co-occurrence matrixes diagonal element have higher value, contrast divides value will be larger.When matrix element value even equal time, contrast score value is larger; Otherwise contrast score value is less.
(4), the moment of inertia (GXJ)
GXJ is the total amount of image compared with zonule grey scale change, reflects the readability of raw material shrimp image and the degree of the texture rill depth.Texture rill is darker, and GXJ is just large, and it is more comprehensive that raw material shrimp superficial makings information embodies; Otherwise raw material shrimp image is fuzzyyer.
Single width raw material shrimp after image pre-processing module and target area segmentation resume module, k represents gray level, and (i, j) is pixel coordinate, and I (i, j) represents then have following definition by the probability that i and j calculates by horizontal direction:
Entropy:
Angle second moment:
Contrast is divided:
The moment of inertia:
Calculated for pixel values direction in single width raw material shrimp image after image pre-processing module and target area segmentation resume module is brought in formula (3), formula (4), formula (5) and formula (6) according to 15 °, 30 °, 45 °, 60 °, 90 °, 120 °, 150 °, 180 ° eight directions, we can calculate the entropy of each width raw material shrimp image, angle second moment, contrast are divided and the moment of inertia, corresponding four matrixes of result of each angle calculation, being first averaging summation again to them can obtain:
Mean entropy and:
Average angle second moment and:
Average contrast divide and:
Average inertia square and:
The mean entropy obtained by above-mentioned formulae discovery and, average angle second moment and, average contrast divide and, average inertia square and, be required textural characteristics.
5, decision tree classifier module
Decision tree (ID3) is a forecast model, and he can a kind of mapping relations between representative object attribute and object value.In decision tree, each node represents certain object, certain possible property value that each diverging paths then represents, the value of each leaf node then corresponding object represented by from root node to the path that this leaf node experiences.Decision tree only has single output, if for there being plural number to export, can setting up independently decision tree and exporting to process difference.
Through first three step can obtain each mean entropy corresponding to width raw material shrimp image and, average angle second moment and on average contrast divide and, average inertia square and, we are using these four values as the characteristic value of classified image, when the various parameter of camera all mixes up, adopt figure online, altogether acquire N width image, its Raw shrimp image is designated as " just " (certified products), non-raw material shrimp image is designated as " bearing " (substandard products), the first half image is used for training pattern, later half image is used as inspection set, the robustness of verification model.Any one data characteristics screening scope all can be selected as the top being positioned at tree, is performed enters next condition case statement when each node satisfies condition feature, if meet leaf node condition to provide rank judgement; If do not met, continue to perform downwards, until leaf node condition meets this characteristic value.The training process of decision tree is as follows: the first width raw material shrimp image of collected by camera is after Image semantic classification and region of interesting extraction, and mean entropy and (ENT`), average angle second moment and (ASM`), average contrast is divided and (IDM`), average inertia square and (GXJ`) are set to a successively
11, a
12, a
13, a
14; The mean entropy of the second width raw material shrimp image and, average angle second moment and, average contrast divide and, average inertia square and be set to a successively
21, a
22, a
23, a
24.Make ENT` as the top of this decision tree, its span is [a
21, a
11], ASM` is as first leaf left sibling, and its span is [a
22, a
12], ASM` is as first right node of leaf, and its span is [a
42, a
32] ... by that analogy, complete when last the n-th/2 width image is collected, IDM` is as Far Left leaf node, and span is
rank below it provides, and is all certified products; ENT` is as rightmost leaf node, and its span is
rank below it provides, and is also all certified products, now declares that training pattern has been set up.The concrete result of decision as shown in Figure 10, wherein [a
21, a
11], [a
41, a
31]
[a
22, a
12], [a
42, a
32]
[a
23, a
13], [a
43, a
33]
[a
24, a
14], [a
44, a
34]
represent respectively training pattern institute be met mean entropy corresponding to characteristic attribute and, average angle second moment and, on average contrast divide and, average inertia square and the span of textural characteristics, can find out and be given to left branch when each node satisfies condition feature, otherwise be assigned to right branch.After training pattern is set up, use camera hard trigger module collecting test image, will repeat above image pre-processing module-target area segmentation module-gray level co-occurrence matrixes computing module successively for each test sample book, now system can provide best classification grade by automatic analysis.
Start below to carry out the image measurement stage, the image that each width camera gathers after pretreatment and region of interesting extraction, calculate mean entropy and, average angle second moment and, average contrast divide and, judge that whether their feature is at [a
21, a
11], [a
41, a
31]
[a
22, a
12], [a
42, a
32]
[a
23, a
13], [a
43, a
33]
[a
24, a
14], [a
44, a
34]
within interval, namely allow their numerical value from the top of the decision-tree model just now set up successively downward traversal, satisfy condition the rank that just corresponding imparting leaf node is corresponding, and rank exists " just " and " bearing " two kinds possibility, correspond to certified products splicing groove and substandard products splicing groove respectively; When not satisfying condition, continue traversal, through satisfy condition till, final leaf node corresponding to qualified region can be considered to final result.
6, display module
Result can be real-time show in display module, the display comprising characteristic value: mean entropy and, average angle second moment and, average contrast divide and, average inertia square and, image total amount, certified products shrimp quantity, substandard products shrimp quantity, training is modeled as power, test success rate.
Can obtain classification results by the image processing module of design, result passes to the executing agency's delivery nozzle control instruction in image processing system, and then control three magnetic valves open or close.Because the position of nozzle and raw material shrimp terminal position very close, when raw material shrimp runs to below shower nozzle, magnetic valve is opened, and nozzle is blown instantaneously.For certified products shrimp, air nozzle keeps closing, and certified products shrimp falls into after colliding the first plate washer 16 in certified products splicing groove 19, for impurity, spray the effect of air-flow at air nozzle 27 under, change the fall trajectory of impurity, fall into after making it touch second baffle 18 in substandard products splicing groove.
Claims (9)
1. the automatic well-chosen grading plant of a seed shrimp, is characterized in that, comprises feeding system, sort channel, adopts drawing system, hierarchy system and image processing system;
Feeding system is used for exporting sort channel to by treating that the shrimp body of sorting is single;
Sort channel is divided into the buffer channel (8) and sampling channel (12) that are connected successively, sampling channel (12) is separated into multiple single-rowization passage, described buffer channel is provided with multiple directions adjuster in (8), and the shrimp for being exported by feeding system is divided into single and regulates each shrimp body to enter the attitude of corresponding single-rowization passage;
Adopting drawing system for gathering the image of shrimp body in each single-rowization passage, adopting drawing system and comprising and be positioned at sampling channel (12) up and down and dislocation two lighting box (13) of arranging, in each lighting box, being equipped with camera (21);
Hierarchy system comprises the air nozzle (27) corresponding with each single-rowization passage, and this air nozzle (27) is controlled by described image processing system, enters different splicing grooves for blowing the shrimp body exported by single-rowization passage;
Image processing system, for analyzing described image, to the image grading process of each shrimp body, according to classification results, and sends the signal controlling hierarchy system.
2. the automatic well-chosen grading plant of shrimp as claimed in claim 1, it is characterized in that, described buffer channel (8) and sampling channel (12) are all in tilted layout, and the angle of inclination of sampling channel (12) is greater than the angle of inclination of buffer channel (8).
3. the automatic well-chosen grading plant of shrimp as claimed in claim 1, it is characterized in that, described direction adjuster comprises the locating piece (9) be arranged in buffer channel (8), locating piece (9) is fixed with guide plate (10) towards one end of feeding system, and this guide plate (10) has the guiding surface acting on shrimp body.
4. the automatic well-chosen grading plant of shrimp as claimed in claim 1, it is characterized in that, light source (22) is installed in described lighting box (13), the inwall of lighting box (13) scribbles barium sulfate, and is provided with black background plate (29) above or below the sampling channel corresponding with each lighting box (13).
5. the automatic well-chosen grading plant of shrimp as claimed in claim 1, it is characterized in that, the input of each single-rowization passage and output are fixed with first sensor (26) and the second sensor (30) respectively, two sensors all access described image processing system, first sensor (26) controls for sending the signal that camera (21) carries out image taking, and the second sensor (30) sends the signal opening air nozzle (27).
6. the automatic well-chosen grading plant of shrimp as claimed in claim 1, it is characterized in that, also be provided with the bracing frame (14) installing sort channel, the bracing frame (14) being positioned at sort channel output is provided with the first baffle plate (16) and second baffle (17), first baffle plate (16) acts on the shrimp body freely glided by each single-rowization passage, second baffle (17) is for arc and act on the shrimp body blown by air nozzle (27), and the face that the first baffle plate (16) and second baffle (17) contact with shrimp body is equipped with supple buffer layer (28).
7. the automatic well-chosen stage division of a seed shrimp, is characterized in that, comprise the following steps:
1) feeding system exports sort channel to by single for shrimp body, and each shrimp body slides with the single-rowization passage of the attitude adapted in sort channel;
2) image of collected by camera shrimp body is utilized, and utilize image processing system to carry out pretreatment to the image collected, obtain the area-of-interest in raw material shrimp image, gray level co-occurrence matrixes information in raw material shrimp of extracting, as textural characteristics, uses decision tree classifier to classify to the textural characteristics extracted;
In step 2) in, area-of-interest is used to gray scale symbiosis battle array extracts entropy, angle second moment, contrast are divided and the feature of the moment of inertia, again according to 15 °, 30 °, 45 °, 60 °, 90 °, 120 °, 150 °, 180 ° eight direction calculating mean entropies and, average angle second moment and, average contrast divide and, average inertia square and, specific formula for calculation is:
Mean entropy and:
Average angle second moment and:
Average contrast divide and:
Average inertia square and:
Wherein ENT, ASM, IDM, GXJ represent that entropy, angle second moment, contrast are divided and the moment of inertia respectively, the mean entropy calculated by above-mentioned formula and, average angle second moment and, average contrast divide and, average inertia square and, be described textural characteristics;
3) hierarchy system is according to described classification results, and control air nozzle blows the raw material shrimp skidded off by single-rowization passage and enters different splicing grooves.
8. the automatic well-chosen stage division of shrimp as claimed in claim 7, it is characterized in that, in step 2) in, 9 × 9 windows are used to carry out mean filter process to raw material shrimp image, to each point gray value that each point average gray in 9 × 9 neighborhoods around each pixel of this image replaces this image original in Image semantic classification; Region of interesting extraction process is as follows:
If the visual field actual (tube) length of camera is x, wide is y, and raw material shrimp actual (tube) length that image occupies is x
1, wide is y
1, according to formula:
can calculate the size of area-of-interest, wherein, l represents the length of area-of-interest, and w represents the wide of area-of-interest.
9. the automatic well-chosen stage division of shrimp as claimed in claim 7, is characterized in that, according to described textural characteristics, decision tree classifier is used to carry out Decision Classfication to the textural characteristics best embodying original image, travel through whole decision tree, when leaf node is " just ", corresponding is certified products; When leaf node is " bearing ", corresponding is substandard products.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410040879.2A CN103801520B (en) | 2014-01-27 | 2014-01-27 | The automatic well-chosen stage division of shrimp and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410040879.2A CN103801520B (en) | 2014-01-27 | 2014-01-27 | The automatic well-chosen stage division of shrimp and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103801520A CN103801520A (en) | 2014-05-21 |
| CN103801520B true CN103801520B (en) | 2015-11-25 |
Family
ID=50699185
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410040879.2A Active CN103801520B (en) | 2014-01-27 | 2014-01-27 | The automatic well-chosen stage division of shrimp and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103801520B (en) |
Families Citing this family (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3133927A4 (en) * | 2014-04-24 | 2017-10-18 | Laitram, L.L.C. | Shrimp processing system and methods |
| CN104174598A (en) * | 2014-09-01 | 2014-12-03 | 安徽唯嵩光电科技有限公司 | Sorting machine for sorting hard materials and sorting method thereof |
| CN105344613B (en) * | 2015-11-26 | 2018-01-26 | 浙江大学 | A kind of Brazilian pine nut list granulating device |
| CN105293149A (en) * | 2015-11-26 | 2016-02-03 | 倪煌斌 | Conveying table for collected paper piles |
| CN108072668A (en) * | 2016-11-18 | 2018-05-25 | 中国科学院沈阳自动化研究所 | Bullet open defect automatic recognition system based on Photoelectric Detection |
| SG11202000222TA (en) * | 2017-07-10 | 2020-02-27 | Arlanxeo Deutschland Gmbh | Inspection apparatus and method for visual inspecting elastic particles |
| CN107444855B (en) * | 2017-09-01 | 2023-01-17 | 深圳市艾克斯自动化技术开发有限公司 | Multi-row conveying and directional arranging machine |
| EP3681293A4 (en) | 2017-09-05 | 2021-08-18 | Laitram, LLC | Singulation and separation system for a shrimp processor |
| CN107661864B (en) * | 2017-11-27 | 2019-04-02 | 江苏食品药品职业技术学院 | Cray classified screening device based on Machine Vision Detection |
| KR102109698B1 (en) * | 2017-12-08 | 2020-05-12 | 한국로봇융합연구원 | Object auto sorting, classifying system using image processing algorithm |
| CN108921057B (en) * | 2018-06-19 | 2021-06-01 | 厦门大学 | Convolutional neural network-based prawn form measuring method, medium, terminal equipment and device |
| CN109092702A (en) * | 2018-08-10 | 2018-12-28 | 河南科技大学 | A kind of agaricus bisporus primary election stage division and device |
| CN109169465B (en) * | 2018-09-04 | 2021-08-03 | 中国水产科学研究院黄海水产研究所 | System and method for intelligently measuring growth parameters of underwater live prawns |
| CN109829465B (en) * | 2019-01-03 | 2023-03-24 | 上海交通大学 | Method for searching optimum sucking position of prawn and identifying tail limb characteristics |
| CN110385277A (en) * | 2019-08-30 | 2019-10-29 | 贵州大学 | A kind of apple sorting equipment and its method for sorting |
| CN112907503B (en) * | 2020-07-24 | 2024-02-13 | 嘉兴学院 | Penaeus vannamei Boone quality detection method based on self-adaptive convolutional neural network |
| CN112077012A (en) * | 2020-08-31 | 2020-12-15 | 林海云 | Pepper piling-prevention sorting equipment |
| CN112474388B (en) * | 2020-10-27 | 2022-08-09 | 天津合荣钛业有限公司 | Reduced titanium distributor and sub-packaging machine applying same |
| CN112841099A (en) * | 2021-03-19 | 2021-05-28 | 东营市阔海水产科技有限公司 | Detection apparatus for detect shrimp head pathological change based on image |
| CN113857065A (en) * | 2021-11-01 | 2021-12-31 | 合肥泰禾智能科技集团股份有限公司 | Sorting mechanism and sorting device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5346424A (en) * | 1993-08-20 | 1994-09-13 | Horng Shen Machinery Co., Ltd. | Automatic size-grading and shrimp peeling machinery |
| CN201108008Y (en) * | 2007-11-12 | 2008-09-03 | 彭德权 | Fish and shrimp automatic numerical control grading screen grader |
| CN201470593U (en) * | 2009-08-14 | 2010-05-19 | 江苏九寿堂生物制品有限公司 | Lobster grading machine |
| CN202918945U (en) * | 2012-11-22 | 2013-05-08 | 福建省丰盛食品有限公司 | Sorting device for shrimps |
| CN203018326U (en) * | 2012-12-21 | 2013-06-26 | 浙江大学 | Prawn quality detecting-grading device based on machine vision technology |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2772903B2 (en) * | 1993-07-15 | 1998-07-09 | 静男 疋田 | Wind-screening device for dried whitebait |
| KR100639257B1 (en) * | 2005-02-14 | 2006-10-26 | 김윤호 | Grader for shrimps |
-
2014
- 2014-01-27 CN CN201410040879.2A patent/CN103801520B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5346424A (en) * | 1993-08-20 | 1994-09-13 | Horng Shen Machinery Co., Ltd. | Automatic size-grading and shrimp peeling machinery |
| CN201108008Y (en) * | 2007-11-12 | 2008-09-03 | 彭德权 | Fish and shrimp automatic numerical control grading screen grader |
| CN201470593U (en) * | 2009-08-14 | 2010-05-19 | 江苏九寿堂生物制品有限公司 | Lobster grading machine |
| CN202918945U (en) * | 2012-11-22 | 2013-05-08 | 福建省丰盛食品有限公司 | Sorting device for shrimps |
| CN203018326U (en) * | 2012-12-21 | 2013-06-26 | 浙江大学 | Prawn quality detecting-grading device based on machine vision technology |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103801520A (en) | 2014-05-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103801520B (en) | The automatic well-chosen stage division of shrimp and device | |
| CN106733701B (en) | Potato multi-stage combination dysnusia detecting system and detection method | |
| Lv et al. | Cascade network for detection of coal and gangue in the production context | |
| Faillettaz et al. | Imperfect automatic image classification successfully describes plankton distribution patterns | |
| CN101398898B (en) | Plant leaf identification method based on manifold learning | |
| CN107316289A (en) | Crop field spike of rice dividing method based on deep learning and super-pixel segmentation | |
| CN103323455A (en) | Tobacco leaf grading method based on reflection, perspective and microscopic images | |
| Thakur et al. | An innovative approach for fruit ripeness classification | |
| CN111080691A (en) | Infrared hot spot detection method and device for photovoltaic module | |
| CN103033512A (en) | Device and method for recognizing hatching egg incubation based on hyperspectrum | |
| CN107358176A (en) | Sorting technique based on high score remote sensing image area information and convolutional neural networks | |
| CN111968081B (en) | Automatic fish shoal counting method and device, electronic equipment and storage medium | |
| CN110741783B (en) | Seed cleaning device and air vibration disc type seedling raising and seeding machine and automatic seed cleaning system thereof | |
| CN104070016A (en) | Granular agricultural material real-time detecting and grading device and granular agricultural material real-time detecting and grading method | |
| CN103177266A (en) | Intelligent stock pest identification system | |
| CN111438072A (en) | Product letter sorting equipment weighs | |
| CN103646251B (en) | Apple postharvest field classification detection method and system based on embedded technology | |
| CN110125044A (en) | A kind of apple sorting equipment based on binocular vision | |
| Zhou et al. | Research on cucumber downy mildew detection system based on SVM classification algorithm | |
| CN113313692A (en) | Automatic banana young plant identification and counting method based on aerial visible light image | |
| CN102680488B (en) | Device and method for identifying massive agricultural product on line on basis of PCA (Principal Component Analysis) | |
| CN110689059A (en) | Automatic garbage sorting method | |
| Wu et al. | Fast location and classification of small targets using region segmentation and a convolutional neural network | |
| Li et al. | Seeding detection and distribution evaluation using the developed automatic maize seeding machine | |
| Zhang et al. | Online Recognition of Small Vegetable Seed Sowing 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 | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |