CN104636737A - Fish body fresh degree recognition system - Google Patents
Fish body fresh degree recognition system Download PDFInfo
- Publication number
- CN104636737A CN104636737A CN201510103973.2A CN201510103973A CN104636737A CN 104636737 A CN104636737 A CN 104636737A CN 201510103973 A CN201510103973 A CN 201510103973A CN 104636737 A CN104636737 A CN 104636737A
- Authority
- CN
- China
- Prior art keywords
- fish body
- flake
- fish
- freshness
- mean value
- 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.)
- Granted
Links
- 241000251468 Actinopterygii Species 0.000 claims abstract description 177
- 238000012545 processing Methods 0.000 claims abstract description 24
- 238000006243 chemical reaction Methods 0.000 claims description 34
- 238000001914 filtration Methods 0.000 claims description 30
- 238000001514 detection method Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 20
- 230000008569 process Effects 0.000 claims description 20
- 238000000605 extraction Methods 0.000 claims description 9
- 239000006059 cover glass Substances 0.000 claims description 3
- 239000000203 mixture Substances 0.000 claims description 3
- 238000000926 separation method Methods 0.000 claims description 3
- 235000013305 food Nutrition 0.000 description 20
- 235000021393 food security Nutrition 0.000 description 7
- 230000036541 health Effects 0.000 description 4
- 235000016709 nutrition Nutrition 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 230000001066 destructive effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000002372 labelling Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000001473 noxious effect Effects 0.000 description 3
- 235000005911 diet Nutrition 0.000 description 2
- 230000037213 diet Effects 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 244000005700 microbiome Species 0.000 description 2
- 238000009659 non-destructive testing Methods 0.000 description 2
- 231100000252 nontoxic Toxicity 0.000 description 2
- 230000003000 nontoxic effect Effects 0.000 description 2
- 231100000614 poison Toxicity 0.000 description 2
- 230000007096 poisonous effect Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 206010016952 Food poisoning Diseases 0.000 description 1
- 208000019331 Foodborne disease Diseases 0.000 description 1
- 230000001154 acute effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 235000008429 bread Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000020930 dietary requirements Nutrition 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 235000013332 fish product Nutrition 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 230000005180 public health Effects 0.000 description 1
- 238000012113 quantitative test Methods 0.000 description 1
- 210000000697 sensory organ Anatomy 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Image Analysis (AREA)
- Farming Of Fish And Shellfish (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a fish body fresh degree recognition system, which comprises image pickup equipment, fresh degree recognition equipment and main control equipment, wherein the image pickup equipment is used for shooting a fish body to be detected to obtain a fish body image, the fresh degree recognition equipment is connected with the image pickup equipment and is used for carrying out image processing on the fish body image, the main control equipment is connected with the fresh degree recognition equipment, and the fresh degree of the fish body to be detected is determined on the basis of the image processing result of the fresh degree recognition equipment. Through the fish body fresh degree recognition system, a plurality of features relevant to the fresh degree of the fish body to be detected can be fast and accurately detected, so that the fresh degree of the fish body can be determined under the condition without damaging the fish body.
Description
Technical field
The present invention relates to fish health check-up and test field, particularly relate to a kind of fish body freshness recognition system.
Background technology
" bread is the staff of life ", visible food is to the importance of people's daily life.Along with the raising of expanding economy and people's living standard, people are not only whether meet dietary requirements to the concern of food, more focus on the security of food.
In order to obtain the security performance being about to edible various food, in succession developing various checkout equipment, whether there is various noxious material and various nutritional labeling for detecting food.These checkout equipments accurately and timely can analyze food whether suitable people's feed, certain take care of yourself effect for the safe diet of people and healthy living serve.
But, the food inspection equipment of prior art is mainly concentrated is that the noxious material of food and nutritional labeling detect, freshness for nontoxic edible food lacks effective means of identification, such as to often edible fish body, even if having, also be that the sense organ being limited in by people carries out evaluating or by chemical detection mode, microorganism detection mode and physical detection mode are carried out destructiveness and are detected, but artificial evaluation method subjectivity is strong, error is large, and cannot quantitative test, and chemical detection mode, microorganism detection mode and physical detection mode are destructive strong again, detection efficiency is not high.
Therefore, need a kind of new fish body freshness identifying schemes, substitute traditional artificial cognition pattern or destructive recognition mode, Non-Destructive Testing can be carried out with electronic recognition pattern to fish body, and precision and the speed of identification can be ensured simultaneously.
Summary of the invention
In order to solve the problem, the invention provides a kind of fish body freshness recognition system, image acquisition and image procossing is carried out based on flake and fish body body surface two region the most responsive to freshness, build a set of fish body freshness Identification platform comprising various processing element targetedly, realize the non-destructive identification to fish body freshness, whole recognition system travelling speed is fast, and the data provided are more accurate.
According to an aspect of the present invention, provide a kind of fish body freshness recognition system, comprise picture pick-up device, freshness identification equipment and master control equipment, described picture pick-up device is used for taking to obtain fish volume image to detected fish body, described freshness identification equipment is connected with described picture pick-up device, for carrying out image procossing to described fish volume image, described master control equipment is connected with described freshness identification equipment, and the processing result image based on described freshness identification equipment determines the freshness of detected fish body.
More specifically, in described fish body freshness recognition system, also comprise: detect casing, comprise wedge shape platform, circular housing and gear train, described wedge shape platform is for placing detected fish body, described gear train is for being sent to described wedge shape platform by detected fish body from detection case external body, and described circular housing is for holding described wedge shape platform, servicing lighting, is arranged in described detection casing, the top of described wedge shape platform, and for providing floor light for the shooting of described picture pick-up device, brightness and the brightness of described servicing lighting surrounding environment of described floor light light are inversely proportional to, power-supply unit, under the control of described master control equipment, for each consuming parts of described recognition system provides electric power supply, memory device, for prestoring flake gray scale upper limit threshold and flake gray scale lower threshold, the numerical value of described flake gray scale upper limit threshold and flake gray scale lower threshold is all between 0-255, for by the flake in image and background separation, described memory device has also prestored the fish body freshness table of comparisons, the described fish body freshness table of comparisons with fish body freshness for index, save the benchmark fish body characteristics vector that the fish body freshness of each grade is corresponding respectively, described benchmark fish body characteristics vector is by benchmark flake L component mean value, benchmark flake a component mean value, benchmark flake b component mean value, benchmark body surface L component mean value, benchmark body surface a component mean value and benchmark body surface b component mean value composition, the benchmark flake L component mean value that the fish body freshness of each grade is corresponding, benchmark flake a component mean value, benchmark flake b component mean value is by each color component mean value benchmark fish eye images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion, the benchmark body surface L component mean value that the fish body freshness of each grade is corresponding, benchmark body surface a component mean value and benchmark body surface b component mean value are by each color component mean value benchmark fish body surface images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion, display device, is connected with described master control equipment, for showing the grade of the fish body freshness of detected fish body, described picture pick-up device comprises front cover glass, camera lens, filter and image-forming electron unit, and for taking to obtain fish volume image to detected fish body, the resolution of described fish volume image is 1920 × 1080, and described image-forming electron unit is CMOS vision sensor, described freshness identification equipment is connected respectively with described memory device and described picture pick-up device, comprises the sub-device of medium filtering, the sub-device of gray processing process, eyes image splits sub-device, surface images splits sub-device, the sub-device of color space conversion and the sub-device of feature extraction, the sub-device of described medium filtering is connected with described picture pick-up device, for carrying out the medium filtering process of 5 × 5 filter windows to described fish volume image, to obtain filtering fish volume image, the sub-device of described gray processing process is connected with the sub-device of described medium filtering, carries out gray processing process to filtering fish volume image, to obtain gray scale fish volume image, described eyes image is split sub-device and is connected respectively with described picture pick-up device, the sub-device of described gray processing process and described memory device, the pixel of gray-scale value between flake gray scale upper limit threshold and flake gray scale lower threshold in gray scale fish volume image is identified as detected flake pixel, all detected flake pixels are formed a detected flake grayscale sub-image, and in described fish volume image, is partitioned into corresponding flake subimage based on the relative position of described detected flake grayscale sub-image in described gray scale fish volume image, described surface images is split sub-device and is connected with the sub-device of described medium filtering, according to the size of fish body boundary rectangle in filtering fish volume image, in filtering fish volume image, fish body is drawn according to preset ratio and get one piece of rectangular area to obtain body surface subimage, described preset ratio is the ratio of drawing rectangular area and the fish body boundary rectangle got, the sub-device of described color space conversion and described eyes image are split sub-device and described surface images and are split sub-device and be connected respectively, flake subimage and body surface subimage are carried out Lab color space conversion respectively, to obtain the body surface subimage after the flake subimage after conversion and conversion, the sub-device of described feature extraction is connected with the sub-device of described color space conversion, calculate each color component mean value of the flake subimage after conversion to obtain flake L component mean value on the spot, flake a component mean value and on the spot flake b component mean value on the spot, calculate each color component mean value of the body surface subimage after conversion to obtain body surface L component mean value on the spot, body surface a component mean value and on the spot body surface b component mean value on the spot, to flake L component mean value on the spot, flake a component mean value on the spot, flake b component mean value on the spot, body surface L component mean value on the spot, on the spot body surface a component mean value and on the spot body surface b component mean value form on the spot fish body characteristics vector, described master control equipment is connected respectively with described freshness identification equipment and described memory device, the described body characteristics of the fish on the spot vector benchmark fish body characteristics vector corresponding respectively with the fish body freshness of each grade in the described fish body freshness table of comparisons is mated one by one, the grade of the grade of the fish body freshness of the benchmark fish body characteristics vector correspondence that the match is successful as the fish body freshness of detected fish body is exported, wherein, the sub-device of described medium filtering, the sub-device of described gray processing process, described eyes image splits sub-device, described surface images splits sub-device, the sub-device of described color space conversion and the sub-device of described feature extraction adopt fpga chip to realize respectively, and the type selecting of the fpga chip adopted is all the Artix-7 series of Xilinx company.
More specifically, in described fish body freshness recognition system, also comprise: described master control equipment is according to the dump energy of power-supply unit, determine to send enabling signal, power save signal or shutdown signal to described picture pick-up device, and send enabling signal, power save signal or shutdown signal, to control the mode of operation of described picture pick-up device and described freshness identification equipment respectively to described freshness identification equipment.
More specifically, in described fish body freshness recognition system, also comprise: described display device is LCDs.
More specifically, in described fish body freshness recognition system, also comprise: described picture pick-up device and described freshness identification equipment are integrated on one piece of surface-mounted integrated circuit.
More specifically, in described fish body freshness recognition system, also comprise: described picture pick-up device is positioned at the top center position of the circular housing of described detection casing.
Accompanying drawing explanation
Below with reference to accompanying drawing, embodiment of the present invention are described, wherein:
Fig. 1 is the block diagram of the fish body freshness recognition system illustrated according to an embodiment of the present invention.
Fig. 2 is the block diagram of the freshness identification equipment of the fish body freshness recognition system illustrated according to an embodiment of the present invention.
Embodiment
Below with reference to accompanying drawings the embodiment of fish body freshness recognition system of the present invention is described in detail.
Food security (food safety), refers to that food is nontoxic, harmless, meets the nutritional requirement that should have, and does not cause any acute, subacute or chronic hazard to health.According to the definition of doubly promise food security, food security is " in food, poisonous and harmful substances is to the public health problem of Health Impact ".Food security is also that special a discussion guarantees food hygiene and edible safety in the processes such as food processing, storage, sale, reduces disease risk, takes precautions against interdisciplinary fields of food poisoning, so food security is very important.
In order to ensure food security, the activity such as plantation, cultivation, processing, packaging, storage, transport, sale, consumption of food all will meet certain standard and requirement, does not exist and may damage or threaten the poisonous and harmful substance of health die to cause consumer's disease or jeopardize the hidden danger of consumer and offspring thereof.Food security both comprised production safety as can be seen here, also comprised operation safety; Both comprise result safety, also comprise process safety; Both comprise real safety, also comprise future secure.
Food safety detection means of the prior art are mainly concentrated and are to judge whether food exists various noxious material, whether damages human body, and judge whether the various nutritional labelings in food reach preset standard, whether meet the demand of human intake.And lack a kind of efficient, harmless food freshness detecting pattern, such as, the freshness of fish products is detected.In fact, the detection of food freshness is related to whether can better experience for the diet of people bring and enjoy.
For this reason, the invention provides a kind of fish body freshness recognition system, by the acquisition and processing to fish volumetric image data, make use of flake and the fish body body surface feature more responsive than the reaction of other parts to freshness, achieve the Non-Destructive Testing of freshness, and while guarantee data precision and validity, improve the speed of detection.
Fig. 1 is the block diagram of the fish body freshness recognition system illustrated according to an embodiment of the present invention, described recognition system comprises picture pick-up device 1, freshness identification equipment 2 and master control equipment 3, described master control equipment 3 is connected respectively with described picture pick-up device 1 and described freshness identification equipment 2, and described picture pick-up device 1 is connected with described freshness identification equipment 2.
Wherein, described picture pick-up device 1 is for taking to obtain fish volume image to detected fish body, described freshness identification equipment 2 is for carrying out image procossing to described fish volume image, and described master control equipment 3 is for determining the freshness of detected fish body based on the processing result image of described freshness identification equipment 2.
Then, continue to be further detailed the concrete structure of fish body freshness recognition system of the present invention.
Described recognition system also comprises: detect casing, comprise wedge shape platform, circular housing and gear train, described wedge shape platform is for placing detected fish body, described gear train is for being sent to described wedge shape platform by detected fish body from detection case external body, and described circular housing is for holding described wedge shape platform.
Described recognition system also comprises: servicing lighting, be arranged in described detection casing, the top of described wedge shape platform, for providing floor light for the shooting of described picture pick-up device 1, brightness and the brightness of described servicing lighting surrounding environment of described floor light light are inversely proportional to.
Described recognition system also comprises: power-supply unit, under the control of described master control equipment 3, for each consuming parts of described recognition system provides electric power supply.
Described recognition system also comprises: memory device, for prestoring flake gray scale upper limit threshold and flake gray scale lower threshold, the numerical value of described flake gray scale upper limit threshold and flake gray scale lower threshold is all between 0-255, for by the flake in image and background separation, described memory device has also prestored the fish body freshness table of comparisons, the described fish body freshness table of comparisons with fish body freshness for index, save the benchmark fish body characteristics vector that the fish body freshness of each grade is corresponding respectively, described benchmark fish body characteristics vector is by benchmark flake L component mean value, benchmark flake a component mean value, benchmark flake b component mean value, benchmark body surface L component mean value, benchmark body surface a component mean value and benchmark body surface b component mean value composition, the benchmark flake L component mean value that the fish body freshness of each grade is corresponding, benchmark flake a component mean value, benchmark flake b component mean value is by each color component mean value benchmark fish eye images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion, the benchmark body surface L component mean value that the fish body freshness of each grade is corresponding, benchmark body surface a component mean value and benchmark body surface b component mean value are by each color component mean value benchmark fish body surface images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion.
Described recognition system also comprises: display device, is connected with described master control equipment 3, for showing the grade of the fish body freshness of detected fish body.
Described picture pick-up device 1 comprises front cover glass, camera lens, filter and image-forming electron unit, and for taking to obtain fish volume image to detected fish body, the resolution of described fish volume image is 1920 × 1080, and described image-forming electron unit is CMOS vision sensor.
As shown in Figure 2, described freshness identification equipment 2 is connected respectively with described memory device and described picture pick-up device 1, comprises the sub-device of medium filtering 21, the sub-device of gray processing process 22, eyes image splits sub-device 23, surface images splits sub-device 24, the sub-device of color space conversion 25 and the sub-device 26 of feature extraction.
The sub-device of described medium filtering 21 is connected with described picture pick-up device 1, for carrying out the medium filtering process of 5 × 5 filter windows to described fish volume image, to obtain filtering fish volume image.
The sub-device of described gray processing process 22 is connected with the sub-device 21 of described medium filtering, carries out gray processing process to filtering fish volume image, to obtain gray scale fish volume image.
Described eyes image is split sub-device 23 and is connected respectively with described picture pick-up device 1, the sub-device of described gray processing process 22 and described memory device, the pixel of gray-scale value between flake gray scale upper limit threshold and flake gray scale lower threshold in gray scale fish volume image is identified as detected flake pixel, all detected flake pixels are formed a detected flake grayscale sub-image, and in described fish volume image, is partitioned into corresponding flake subimage based on the relative position of described detected flake grayscale sub-image in described gray scale fish volume image.
Described surface images is split sub-device 24 and is connected with the sub-device 21 of described medium filtering, according to the size of fish body boundary rectangle in filtering fish volume image, in filtering fish volume image, fish body is drawn according to preset ratio and get one piece of rectangular area to obtain body surface subimage, described preset ratio is the ratio of drawing rectangular area and the fish body boundary rectangle got.
The sub-device of described color space conversion 25 and described eyes image are split sub-device 23 and described surface images and are split sub-device 24 and be connected respectively, flake subimage and body surface subimage are carried out Lab color space conversion respectively, to obtain the body surface subimage after the flake subimage after conversion and conversion.
The sub-device of described feature extraction 26 is connected with the sub-device 25 of described color space conversion, calculate each color component mean value of the flake subimage after conversion to obtain flake L component mean value on the spot, flake a component mean value and on the spot flake b component mean value on the spot, calculate each color component mean value of the body surface subimage after conversion to obtain body surface L component mean value on the spot, body surface a component mean value and on the spot body surface b component mean value on the spot, to flake L component mean value on the spot, flake a component mean value on the spot, flake b component mean value on the spot, body surface L component mean value on the spot, on the spot body surface a component mean value and on the spot body surface b component mean value form on the spot fish body characteristics vector.
Described master control equipment 3 is connected respectively with described freshness identification equipment 2 and described memory device, the described body characteristics of the fish on the spot vector benchmark fish body characteristics vector corresponding respectively with the fish body freshness of each grade in the described fish body freshness table of comparisons is mated one by one, the grade of the grade of the fish body freshness of the benchmark fish body characteristics vector correspondence that the match is successful as the fish body freshness of detected fish body is exported.
Wherein, the sub-device of described medium filtering 21, the sub-device of described gray processing process 22, described eyes image split sub-device 23, described surface images splits sub-device 24, the sub-device of described color space conversion 25 and the sub-device 26 of described feature extraction adopt fpga chip to realize respectively, and the type selecting of the fpga chip adopted is all the Artix-7 series of Xilinx company.
Wherein, in described fish body freshness recognition system, alternatively, described master control equipment 3 is according to the dump energy of power-supply unit, determine to send enabling signal to described picture pick-up device 1, power save signal or shutdown signal, and send enabling signal to described freshness identification equipment 2, power save signal or shutdown signal, to control the mode of operation of described picture pick-up device 1 and described freshness identification equipment 2 respectively, described display device is chosen as LCDs, can described picture pick-up device 1 and described freshness identification equipment 2 be integrated on one piece of surface-mounted integrated circuit, and alternatively, described picture pick-up device 1 is positioned at the top center position of the circular housing of described detection casing.
In addition, FPGA (Field-Programmable Gate Array), i.e. field programmable gate array, he is the product further developed on the basis of the programming devices such as PAL, GAL, CPLD, occur as a kind of semi-custom circuit in special IC (ASIC) field, he solves the deficiency of custom circuit, also overcomes the shortcoming that original programming device gate circuit number is limited.
As far back as 1980 mid-nineties 90s, FPGA takes root in PLD equipment.CPLD and FPGA includes the Programmadle logic unit of some relatively large amount.The density of CPLD logic gate is between several thousand to several ten thousand logical blocks, and FPGA normally arrives millions of several ten thousand.The key distinction of CPLD and FPGA is their system architecture.CPLD is a somewhat restrictive structure.This structure is arranged by the logical groups of one or more editable result sum and forms with the register of the locking of some relatively small amounts.Such result lacks editor's dirigibility, but but have the time delay and logical block that can estimate to the advantage of linkage unit height ratio.And FPGA has a lot of linkage units, although allow him edit more flexibly like this, structure is complicated many.The difference of CPLD and FPGA another one is that most FPGA contains high-level built-in module (such as totalizer and multiplier) and built-in memory body.Therefore relevant important difference be much new FPGA support completely or part system in reconfigure.Allow their design along with system upgrade or dynamically reconfigure and change.Some FPGA can allow a part for equipment update and other parts continue normal operation.
FPGA have employed logical cell array LCA (Logic Cell Array) such concept, and inside comprises configurable logic blocks CLB (Configurable Logic Block), input/output module IOB (Input Output Block) and interconnector (Interconnect) three parts.Field programmable gate array (FPGA) is programming device, and as compared to conventional logic circuit and gate array (as PAL, GAL and CPLD device), FPGA has different structures.FPGA utilizes small-sized look-up table (16 × 1RAM) to realize combinational logic, each look-up table is connected to the input end of a d type flip flop, trigger drives other logical circuits again or drives I/O, thus constitute the basic logic unit module that not only can realize combination logic function but also can realize sequential logic function, these intermodules utilize metal connecting line to be connected to each other or are connected to I/O module.
Adopt fish body freshness recognition system of the present invention, the technical matters of harmless efficient detection fish body freshness is lacked for prior art, develop a set of non-damage drive system based on image procossing, flake and fish body body surface is utilized to be fish body two technical characterstics to the most responsive region of freshness with it, detect the position of flake and fish body body surface accurately and fast, utilizing the brightness of Lab color space to disturb few technical characterstic, extracting the multiple characteristics for detecting fish body freshness.Fish body freshness recognition system of the present invention owing to employing multiple parts of customization, detection efficiency and precision higher.
Be understandable that, although the present invention with preferred embodiment disclose as above, but above-described embodiment and be not used to limit the present invention.For any those of ordinary skill in the art, do not departing under technical solution of the present invention ambit, the technology contents of above-mentioned announcement all can be utilized to make many possible variations and modification to technical solution of the present invention, or be revised as the Equivalent embodiments of equivalent variations.Therefore, every content not departing from technical solution of the present invention, according to technical spirit of the present invention to any simple modification made for any of the above embodiments, equivalent variations and modification, all still belongs in the scope of technical solution of the present invention protection.
Claims (6)
1. a fish body freshness recognition system, comprise picture pick-up device, freshness identification equipment and master control equipment, described picture pick-up device is used for taking to obtain fish volume image to detected fish body, described freshness identification equipment is connected with described picture pick-up device, for carrying out image procossing to described fish volume image, described master control equipment is connected with described freshness identification equipment, and the processing result image based on described freshness identification equipment determines the freshness of detected fish body.
2. fish body freshness recognition system as claimed in claim 1, it is characterized in that, described recognition system also comprises:
Detect casing, comprise wedge shape platform, circular housing and gear train, described wedge shape platform is for placing detected fish body, and described gear train is for being sent to described wedge shape platform by detected fish body from detection case external body, and described circular housing is for holding described wedge shape platform;
Servicing lighting, is arranged in described detection casing, the top of described wedge shape platform, and for providing floor light for the shooting of described picture pick-up device, brightness and the brightness of described servicing lighting surrounding environment of described floor light light are inversely proportional to;
Power-supply unit, under the control of described master control equipment, for each consuming parts of described recognition system provides electric power supply;
Memory device, for prestoring flake gray scale upper limit threshold and flake gray scale lower threshold, the numerical value of described flake gray scale upper limit threshold and flake gray scale lower threshold is all between 0-255, for by the flake in image and background separation, described memory device has also prestored the fish body freshness table of comparisons, the described fish body freshness table of comparisons with fish body freshness for index, save the benchmark fish body characteristics vector that the fish body freshness of each grade is corresponding respectively, described benchmark fish body characteristics vector is by benchmark flake L component mean value, benchmark flake a component mean value, benchmark flake b component mean value, benchmark body surface L component mean value, benchmark body surface a component mean value and benchmark body surface b component mean value composition, the benchmark flake L component mean value that the fish body freshness of each grade is corresponding, benchmark flake a component mean value, benchmark flake b component mean value is by each color component mean value benchmark fish eye images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion, the benchmark body surface L component mean value that the fish body freshness of each grade is corresponding, benchmark body surface a component mean value and benchmark body surface b component mean value are by each color component mean value benchmark fish body surface images of the fish body freshness with each grade being carried out to the acquisition of Lab color space conversion,
Display device, is connected with described master control equipment, for showing the grade of the fish body freshness of detected fish body;
Described picture pick-up device comprises front cover glass, camera lens, filter and image-forming electron unit, and for taking to obtain fish volume image to detected fish body, the resolution of described fish volume image is 1920 × 1080, and described image-forming electron unit is CMOS vision sensor;
Described freshness identification equipment is connected respectively with described memory device and described picture pick-up device, comprises the sub-device of medium filtering, the sub-device of gray processing process, eyes image splits sub-device, surface images splits sub-device, the sub-device of color space conversion and the sub-device of feature extraction, the sub-device of described medium filtering is connected with described picture pick-up device, for carrying out the medium filtering process of 5 × 5 filter windows to described fish volume image, to obtain filtering fish volume image, the sub-device of described gray processing process is connected with the sub-device of described medium filtering, carries out gray processing process to filtering fish volume image, to obtain gray scale fish volume image, described eyes image is split sub-device and is connected respectively with described picture pick-up device, the sub-device of described gray processing process and described memory device, the pixel of gray-scale value between flake gray scale upper limit threshold and flake gray scale lower threshold in gray scale fish volume image is identified as detected flake pixel, all detected flake pixels are formed a detected flake grayscale sub-image, and in described fish volume image, is partitioned into corresponding flake subimage based on the relative position of described detected flake grayscale sub-image in described gray scale fish volume image, described surface images is split sub-device and is connected with the sub-device of described medium filtering, according to the size of fish body boundary rectangle in filtering fish volume image, in filtering fish volume image, fish body is drawn according to preset ratio and get one piece of rectangular area to obtain body surface subimage, described preset ratio is the ratio of drawing rectangular area and the fish body boundary rectangle got, the sub-device of described color space conversion and described eyes image are split sub-device and described surface images and are split sub-device and be connected respectively, flake subimage and body surface subimage are carried out Lab color space conversion respectively, to obtain the body surface subimage after the flake subimage after conversion and conversion, the sub-device of described feature extraction is connected with the sub-device of described color space conversion, calculate each color component mean value of the flake subimage after conversion to obtain flake L component mean value on the spot, flake a component mean value and on the spot flake b component mean value on the spot, calculate each color component mean value of the body surface subimage after conversion to obtain body surface L component mean value on the spot, body surface a component mean value and on the spot body surface b component mean value on the spot, to flake L component mean value on the spot, flake a component mean value on the spot, flake b component mean value on the spot, body surface L component mean value on the spot, on the spot body surface a component mean value and on the spot body surface b component mean value form on the spot fish body characteristics vector,
Described master control equipment is connected respectively with described freshness identification equipment and described memory device, the described body characteristics of the fish on the spot vector benchmark fish body characteristics vector corresponding respectively with the fish body freshness of each grade in the described fish body freshness table of comparisons is mated one by one, the grade of the grade of the fish body freshness of the benchmark fish body characteristics vector correspondence that the match is successful as the fish body freshness of detected fish body is exported;
Wherein, the sub-device of described medium filtering, the sub-device of described gray processing process, described eyes image splits sub-device, described surface images splits sub-device, the sub-device of described color space conversion and the sub-device of described feature extraction adopt fpga chip to realize respectively, and the type selecting of the fpga chip adopted is all the Artix-7 series of Xilinx company.
3. fish body freshness recognition system as claimed in claim 2, is characterized in that:
Described master control equipment is according to the dump energy of power-supply unit, determine to send enabling signal, power save signal or shutdown signal to described picture pick-up device, and send enabling signal, power save signal or shutdown signal, to control the mode of operation of described picture pick-up device and described freshness identification equipment respectively to described freshness identification equipment.
4. fish body freshness recognition system as claimed in claim 2, is characterized in that:
Described display device is LCDs.
5. fish body freshness recognition system as claimed in claim 2, is characterized in that:
Described picture pick-up device and described freshness identification equipment are integrated on one piece of surface-mounted integrated circuit.
6. fish body freshness recognition system as claimed in claim 2, is characterized in that:
Described picture pick-up device is positioned at the top center position of the circular housing of described detection casing.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710532875.XA CN107392117B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
| CN201510103973.2A CN104636737B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510103973.2A CN104636737B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
Related Child Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710532875.XA Division CN107392117B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104636737A true CN104636737A (en) | 2015-05-20 |
| CN104636737B CN104636737B (en) | 2017-10-20 |
Family
ID=53215467
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710532875.XA Active CN107392117B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
| CN201510103973.2A Expired - Fee Related CN104636737B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710532875.XA Active CN107392117B (en) | 2015-03-10 | 2015-03-10 | Fish body freshness identifying system |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN107392117B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133184A (en) * | 2017-12-20 | 2018-06-08 | 中国水产科学研究院渔业机械仪器研究所 | It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method |
| CN111724350A (en) * | 2020-05-29 | 2020-09-29 | 北京农业信息技术研究中心 | Nondestructive testing method and device for freshness of fish body |
| CN112586548A (en) * | 2020-11-06 | 2021-04-02 | 泰州锐比特智能科技有限公司 | Blade parameter selection system utilizing cloud storage |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110940125A (en) * | 2019-10-30 | 2020-03-31 | 珠海格力电器股份有限公司 | Method, device and medium for determining optimal refrigeration scheme of food in refrigerator and refrigerator |
| CN115512429B (en) * | 2022-11-21 | 2023-03-10 | 山东理工大学 | Cultured fish product freshness distinguishing method based on eye image recognition |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100194291A1 (en) * | 2007-09-26 | 2010-08-05 | Toshiba Lighting & Technology Corporation | Illumination apparatus |
| CN102507459A (en) * | 2011-11-23 | 2012-06-20 | 中国农业大学 | Method and system for quick lossless evaluation on freshness of fresh beef |
| CN103076288A (en) * | 2012-12-26 | 2013-05-01 | 中国科学院海洋研究所 | Automatic fish flesh grading device and method based on computer vision |
| CN204423395U (en) * | 2015-03-10 | 2015-06-24 | 无锡桑尼安科技有限公司 | Fish body freshness recognition system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102110294B (en) * | 2011-02-21 | 2012-11-14 | 中国农业大学 | Method and system for processing image of diseased fish body |
| CN102147402A (en) * | 2011-03-08 | 2011-08-10 | 江苏大学 | Machine vision technology based method for rapidly detecting egg freshness |
| CN202133619U (en) * | 2011-06-13 | 2012-02-01 | 浙江海洋学院 | Fish-eye image acquisition frame for detecting freshness of fish |
| CN104049068B (en) * | 2014-06-06 | 2015-11-18 | 中国肉类食品综合研究中心 | The non-destructive determination device of fresh poultry meat freshness and assay method |
-
2015
- 2015-03-10 CN CN201710532875.XA patent/CN107392117B/en active Active
- 2015-03-10 CN CN201510103973.2A patent/CN104636737B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100194291A1 (en) * | 2007-09-26 | 2010-08-05 | Toshiba Lighting & Technology Corporation | Illumination apparatus |
| CN102507459A (en) * | 2011-11-23 | 2012-06-20 | 中国农业大学 | Method and system for quick lossless evaluation on freshness of fresh beef |
| CN103076288A (en) * | 2012-12-26 | 2013-05-01 | 中国科学院海洋研究所 | Automatic fish flesh grading device and method based on computer vision |
| CN204423395U (en) * | 2015-03-10 | 2015-06-24 | 无锡桑尼安科技有限公司 | Fish body freshness recognition system |
Non-Patent Citations (2)
| Title |
|---|
| PEIYUAN GUO ET AL.: ""Detection and Identifying of Meat Fresh Degree Based on Adipose Tissue"", 《2009 3RD INTERNATIONAL CONFERENCE ON BIOINFORMATICS AND BIOMEDICAL ENGINEERING》 * |
| 黄星奕 等: ""计算机视觉技术在鱼新鲜度检测中的应用研究"", 《计算机工程与设计》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108133184A (en) * | 2017-12-20 | 2018-06-08 | 中国水产科学研究院渔业机械仪器研究所 | It is a kind of based on the fish of fractal theory and BP algorithm identification and vaccine injection method |
| CN108133184B (en) * | 2017-12-20 | 2020-04-28 | 中国水产科学研究院渔业机械仪器研究所 | Fish identification and vaccine injection method based on fractal theory and BP algorithm |
| CN111724350A (en) * | 2020-05-29 | 2020-09-29 | 北京农业信息技术研究中心 | Nondestructive testing method and device for freshness of fish body |
| CN112586548A (en) * | 2020-11-06 | 2021-04-02 | 泰州锐比特智能科技有限公司 | Blade parameter selection system utilizing cloud storage |
| CN112586548B (en) * | 2020-11-06 | 2021-12-10 | 合肥市贵谦信息科技有限公司 | Blade parameter selection system utilizing cloud storage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107392117A (en) | 2017-11-24 |
| CN107392117B (en) | 2019-10-08 |
| CN104636737B (en) | 2017-10-20 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104636737A (en) | Fish body fresh degree recognition system | |
| US11615672B2 (en) | Inspection system and inspection device | |
| CN104764744B (en) | Visual inspection device and method for inspecting freshness of poultry eggs | |
| KR20210127199A (en) | Neural network-based physical state evaluation of electronic devices, and related systems and methods | |
| US6434257B1 (en) | Size recognition system with method for determining price of a commodity | |
| CN204423395U (en) | Fish body freshness recognition system | |
| US20220165074A1 (en) | Separation of objects in images from three-dimensional cameras | |
| US10410337B2 (en) | System and method for identifying the presence or absence of transparent pills in blister packer machines using high resolution 3D stereo reconstruction based on color linear cameras | |
| Siswantoro et al. | Volume measurement of food product with irregular shape using computer vision and Monte Carlo method: a framework | |
| CN114365024A (en) | Mobile phone imaging system and analysis method based on machine learning | |
| Thong et al. | Mango classification system uses image processing technology and artificial intelligence | |
| CN111753837A (en) | Learning completion model generation method and device, and commodity discrimination method and device | |
| CN111144238A (en) | Article detection method and system based on Faster R-CNN | |
| CN108021914B (en) | Method for extracting character area of printed matter based on convolutional neural network | |
| US11243172B2 (en) | Portable scanning device for ascertaining attributes of sample materials | |
| Sarkar et al. | Counting of cigarettes in cigarette packets using LabVIEW | |
| CN112364702A (en) | Article verification method and device | |
| CN109671227B (en) | Intelligent container consumption behavior identification method and device, storage medium and electronic equipment | |
| CN104655026A (en) | Cut tobacco width recognition platform | |
| CN204473278U (en) | Based on the commodity excessive packaging detecting device of 3-D scanning | |
| Thong et al. | Mango sorting mechanical system uses machine vision and artificial intelligence | |
| JP2002131239A (en) | Apparatus and method for inspection of foreign body | |
| CN105241890A (en) | Capsule real-time inspection method with double detection | |
| Lualhati et al. | Development and Testing of Green Coffee Bean Quality Sorter using Image Processing and Artificial Neural Network | |
| JP6961319B2 (en) | Evaluation method and evaluation device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170630 Address after: Shushan District of Hefei City, Anhui Province, Jiangmen 230031 garden business office floor B-1014 room 10 Applicant after: HEFEI WISDOM LONGTUTENG INTELLECTUAL PROPERTY CO., LTD. Address before: 214000 Jiangsu city of Wuxi Province East Pavilion Street Xishan District Yingbin Road No. 1 Applicant before: Wuxi Sani pacifies Science and Technology Ltd. |
|
| CB03 | Change of inventor or designer information |
Inventor after: Wang Wenqi Inventor after: Xu Shenbo Inventor after: Yang Ning Inventor after: Xu Hairuo Inventor after: Ren Yichao Inventor after: Wang Xin Inventor before: The inventor has waived the right to be mentioned |
|
| CB03 | Change of inventor or designer information | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170912 Address after: 266000 Qingdao Road, Chengyang District, Shandong, No. 700 the Great Wall Applicant after: Qingdao Agricultural University Applicant after: Qingdao Hairuo wisdom Technology Co. Ltd. Address before: Shushan District of Hefei City, Anhui Province, Jiangmen 230031 garden business office floor B-1014 room 10 Applicant before: HEFEI WISDOM LONGTUTENG INTELLECTUAL PROPERTY CO., LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20171020 Termination date: 20190310 |