CN113390834B - Crisp plum maturity detection method based on visual recognition - Google Patents

Crisp plum maturity detection method based on visual recognition Download PDF

Info

Publication number
CN113390834B
CN113390834B CN202110698288.4A CN202110698288A CN113390834B CN 113390834 B CN113390834 B CN 113390834B CN 202110698288 A CN202110698288 A CN 202110698288A CN 113390834 B CN113390834 B CN 113390834B
Authority
CN
China
Prior art keywords
crisp
detection
plums
color
maturity
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
Application number
CN202110698288.4A
Other languages
Chinese (zh)
Other versions
CN113390834A (en
Inventor
李宇
孙钟雷
康莉
刘圳
王劲招
王飞
聂源瑶
吴姗珊
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Yangtze Normal University
Original Assignee
Yangtze Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Yangtze Normal University filed Critical Yangtze Normal University
Priority to CN202110698288.4A priority Critical patent/CN113390834B/en
Priority to CN202310574112.7A priority patent/CN116380814A/en
Publication of CN113390834A publication Critical patent/CN113390834A/en
Application granted granted Critical
Publication of CN113390834B publication Critical patent/CN113390834B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • A—HUMAN NECESSITIES
    • A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
    • A23B—PRESERVING, e.g. BY CANNING, MEAT, FISH, EGGS, FRUIT, VEGETABLES, EDIBLE SEEDS; CHEMICAL RIPENING OF FRUIT OR VEGETABLES; THE PRESERVED, RIPENED, OR CANNED PRODUCTS
    • A23B7/00—Preservation or chemical ripening of fruit or vegetables
    • A—HUMAN NECESSITIES
    • A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
    • A23B—PRESERVING, e.g. BY CANNING, MEAT, FISH, EGGS, FRUIT, VEGETABLES, EDIBLE SEEDS; CHEMICAL RIPENING OF FRUIT OR VEGETABLES; THE PRESERVED, RIPENED, OR CANNED PRODUCTS
    • A23B7/00—Preservation or chemical ripening of fruit or vegetables
    • A23B7/14—Preserving or ripening with chemicals not covered by groups A23B7/08 or A23B7/10
    • A23B7/144—Preserving or ripening with chemicals not covered by groups A23B7/08 or A23B7/10 in the form of gases, e.g. fumigation; Compositions or apparatus therefor
    • A23B7/148—Preserving or ripening with chemicals not covered by groups A23B7/08 or A23B7/10 in the form of gases, e.g. fumigation; Compositions or apparatus therefor in a controlled atmosphere, e.g. partial vacuum, comprising only CO2, N2, O2 or H2O
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N1/00—Sampling; Preparing specimens for investigation
    • G01N1/02—Devices for withdrawing samples
    • G01N1/22—Devices for withdrawing samples in the gaseous state
    • G01N1/24—Suction devices
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/01—Arrangements or apparatus for facilitating the optical investigation
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
    • G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
    • G01N21/27—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands using photo-electric detection ; circuits for computing concentration
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
    • A—HUMAN NECESSITIES
    • A23—FOODS OR FOODSTUFFS; TREATMENT THEREOF, NOT COVERED BY OTHER CLASSES
    • A23V—INDEXING SCHEME RELATING TO FOODS, FOODSTUFFS OR NON-ALCOHOLIC BEVERAGES AND LACTIC OR PROPIONIC ACID BACTERIA USED IN FOODSTUFFS OR FOOD PREPARATION
    • A23V2002/00—Food compositions, function of food ingredients or processes for food or foodstuffs

Landscapes

  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Food Science & Technology (AREA)
  • Chemical Kinetics & Catalysis (AREA)
  • Polymers & Plastics (AREA)
  • Zoology (AREA)
  • Wood Science & Technology (AREA)
  • General Chemical & Material Sciences (AREA)
  • Spectroscopy & Molecular Physics (AREA)
  • Molecular Biology (AREA)
  • Biomedical Technology (AREA)
  • Medicinal Chemistry (AREA)
  • Mathematical Physics (AREA)
  • Theoretical Computer Science (AREA)
  • Investigating Or Analysing Materials By Optical Means (AREA)
  • Storage Of Fruits Or Vegetables (AREA)
  • Storage Of Harvested Produce (AREA)

Abstract

The invention discloses a method for detecting the maturity of crisp plums based on visual identification, which comprises a step of detecting the surface color of the crisp plums, namely, adopting a light source to irradiate the crisp Li Biaomian, taking a photo to obtain the surface image information of the crisp plums, adopting a computer to process the surface image information, extracting the surface color characteristic parameter and the surface color qualified preset parameter value of the crisp plums for comparison and judgment, and is characterized by also comprising a step of detecting the pulp color of the crisp plums, namely, adopting the light source to transmit the crisp plums, taking the photo to obtain the pulp transmission image information of the crisp plums, and adopting the computer to extract the pulp color characteristic parameter and the pulp color qualified preset parameter value for comparison and judgment; and judging the crisp Li Chengshou when the surface color characteristic parameter is larger than the surface color qualified preset parameter value and the pulp color characteristic parameter is larger than the pulp color qualified preset parameter value. The invention is designed specifically for crisp Li Tedian and has the advantage of being capable of judging whether the crisp Li Tedian is mature or not more accurately and reliably.

Description

Crisp plum maturity detection method based on visual recognition
Technical Field
The invention relates to a fruit detection technology, in particular to a crisp plum maturity detection method based on visual identification.
Background
Crisp plums are the general name of off-core plums (deboned plums), which are cyan and bitter and sour when immature, and yellow and sweet when fully mature. The fruit juice has the characteristics of rich color and luster of the epicarp, crisp and sweet pulp, high quality and strong adaptability, is mainly distributed in southwest areas of China, comprises Jiangan plums, wushan Li Yiji Bashan plums and the like, belongs to the category, and increases the planting area and the yield year by year.
In the picking process of the crisp plums, fruit farmers are easy to misjudge when picking the fruits and cause mispicking due to inconsistent maturity of the fruits, the quality of fresh fruits is affected, and the fruits are not easy to store; in the process of storage and transportation, overripening often occurs, so that bad fruits are caused, the sales of crisp plums are seriously influenced, and great economic loss is caused. The current detection method of the fruit maturity comprises artificial sensory detection, physicochemical analysis and instrument detection, but has certain defects, and similar quality is difficult to distinguish. In the detection and analysis of sugar content and acidity in the crisp plums, a titration method is generally adopted, various chemical reagents are required to be prepared, the operation is complicated, the detection efficiency is low, and the on-site nondestructive detection cannot be realized. The size and color detection of the crisp plums usually adopts a manual visual inspection method, has low detection speed, consumes manpower and material resources, cannot achieve objective and accurate effects, and is difficult to realize standardization and quantification. The aroma and taste of the crisp plums are usually detected by adopting a method of artificial nose smell and taste, and three factors of external environmental conditions, sensory evaluation personnel and prepared samples can influence sensory detection results singly or cooperatively. Ethylene is an important marker in the maturity detection, for which highly selective and sensitive detection at low concentrations is critical for regulating fruit ripening, however current detection of ethylene is still immature. The current ethylene content detection method mainly adopts a gas chromatography method, and has the problems of complicated operation, high instrument price and the like. Furthermore, the crispness Li Chengshou degree is not integral or representative only from a single index.
CN202110112114.5 discloses a plum sorting machine, which comprises a charging area and a plurality of sorting areas which are sequentially arranged, wherein the charging area is connected with the sorting areas through a conveyor belt, a visual recognition system is arranged above the sorting areas, and a collecting area is correspondingly arranged below the sorting areas; the device flexibly applies the visual recognition technology to the plum sorting process, utilizes equipment linkage and calculation analysis processing, and automatically and accurately sorts and collects plums according to appearance color, thereby sorting plums with different maturity. The scheme of the invention is based on photographing directly above plums, and sorting is carried out according to the recognition and color formation of the photographs; the method is only a conventional judgment method for identifying and sorting based on the colors of the outer surfaces of plums, and the judgment accuracy is low.
Therefore, how to develop a method capable of realizing the maturity detection more accurately according to the characteristics of the crisp plums, and the method is a problem to be considered to be solved by the person skilled in the art.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to solve the technical problems that: how to provide a crisp plum maturity detection method based on visual recognition, which is designed aiming at crisp Li Tedian and can judge whether the crisp plum is mature or not more accurately.
In order to solve the technical problems, the invention adopts the following technical scheme:
the method for detecting the maturity of the prune based on visual identification comprises a prune surface color detection step, namely, irradiating the prune with a light source, shooting a photo to obtain surface image information of the prune, processing the surface image information by a computer, and extracting a surface color characteristic parameter and a surface color qualified preset parameter value for comparison and judgment, and is characterized by further comprising a prune pulp color detection step, namely, transmitting the prune with the light source, shooting the photo to obtain pulp transmission image information of the prune, and extracting a pulp color characteristic parameter and a pulp color qualified preset parameter value for comparison and judgment by the computer; and judging the crisp Li Chengshou when the surface color characteristic parameter is larger than the surface color qualified preset parameter value and the pulp color characteristic parameter is larger than the pulp color qualified preset parameter value.
This is because the surface colour starts to yellow after the prune has ripened, the more yellow the colour is, the higher the ripeness. However, the color change of the surface of the prune is mainly related to the irradiation amplitude of the sun, and sometimes the irradiation of the sun is too strong, which may cause the peel and yellowing of the inner pulp when the inner pulp is not fully mature. At the same time, sometimes crisp plums not exposed to the sun, even after the flesh has fully ripened, may have relatively insignificant surface color changes. However, after the crisp plums are ripe, the pulp of the crisp plums is certainly converted into crystal clear pulp, and the pulp transmittance of the crisp plums is sharply improved. Therefore, in the method, a light source transmission mode is adopted, so that the light source transmits the crispy plum pulp, then the transmission image information of the crispy plum pulp is shot for detection and judgment, the crispy plums with different maturity degrees are completely different in transmission brightness, and whether the crispy plums are mature or not can be accurately judged. Then, two modes based on visual recognition are adopted simultaneously, and the judgment and the detection are combined, so that the accuracy and the reliability of the detection can be greatly improved.
Further, in the step of detecting the color of the surface of the crisp plums, in a detection chamber sealed by the crisp Li Zhiyu, an illuminating lamp at the position above the crisp plums is used as a light source for illumination, and a camera is arranged above the crisp plums for shooting and detection.
Therefore, the unified stability of the detection light source can be better ensured, the interference of sunlight and external light is avoided, and the reliability of the detection result is ensured. In the implementation, the illuminating lamp is arranged right above or obliquely above, and the camera is arranged right above or obliquely above.
Further, in the step of detecting the color of the crisp plum flesh, a light hole in a partition plate horizontally arranged in a detection chamber which is sealed by the crisp Li Zhiyu is irradiated by a light source lamp for transmission detection arranged below the light hole, and a camera is arranged obliquely above the crisp plum for shooting and detection.
Therefore, the stability of the detection light source can be better ensured, and the interference of the external light source is avoided. Meanwhile, the arrangement of the partition plate ensures the transmission effect, and the camera is positioned at the upper part obliquely, so that the bright part of the crisp plums after being transmitted extends upwards from the edge position of the light holes at the lower part, the higher the maturity of the crisp plums is, the larger and brighter the bright area of the lower end extending upwards is, and the range of the bright area of the crisp Li Xia part can be better detected by adopting the camera at the upper part obliquely, so that the detection precision is improved. Meanwhile, the classification detection of the maturity of the crisp plums can be realized based on the range of the crisp Li Faliang area.
Further, in the step of detecting the color of the surface of the crisp plums, after the camera shoots, image information is transmitted to a computer, R value, G value and B value of the crisp plums in the image are extracted by adopting an RGB color extraction technology, the R value, the G value and the B value are respectively compared with preset qualified parameter values, and when the R value, the G value and the B value are all larger than the corresponding preset qualified parameter values, the detection of the color of the surface is judged to be qualified.
This is because the color of the crisp plum surface is detected and more judged by the color of the surface. According to actual detection, analysis and comparison, the surface color of the more mature crisp plums is more yellow, the three-element color of image extraction R, G, B is increased along with the increase of the maturity of the crisp plums, wherein the increase of the R value is most obvious, the increase degree of the G value is secondary, and the increase of the B value is more secondary. Therefore, in the method, RGB color extraction technology is adopted in the step of detecting the surface color of the prune, three primary colors are extracted for judgment respectively, and the maturity of the prune can be judged more accurately through comparing the three primary colors with a threshold value. In implementation, the technology of performing RGB color extraction according to pictures is mature prior art, and will not be described in detail herein. The qualified preset parameter value for judgment can be obtained by manually selecting mature crisp Li Shiyan in advance. Of course, in implementation, other methods of image feature extraction may be used to perform detection and determination, for example, an image feature extraction processing technique featuring three elements, i.e., h, s, and w, but the specific determination method needs to be verified separately and is not described in detail herein.
Further, in the step of detecting the color of the crisp plum pulp, after the camera shoots, image information is transmitted to a computer, a watershed algorithm is adopted to carry out image segmentation processing, an iteration method is adopted to binarize the image, gray processing is realized, a black-white dichroism image is obtained, the proportion of a white part is calculated, and then the proportion is compared with a preset qualified parameter value, and the condition that the color of the crisp plum pulp is detected to be qualified is judged when the proportion is larger than the preset qualified parameter value.
In this way, the color detection step of the prune flesh is to detect the prune flesh according to the difference of brightness after the prune flesh is transmitted by light. Therefore, the proportion of the white area is detected after the image is binarized and black-and-white processed, and the proportion of the luminous area is obtained. And is used as a standard for judging whether the pulp is ripe or not, and is more accurate and reliable. The specific steps of the watershed algorithm, the iteration method and the like belong to the mature prior art, and are not described in detail herein.
In the sample application, different image processing algorithms are respectively adopted for the crisp plum surface color detection step and the crisp plum pulp color detection step, so that the crisp plum surface color detection step and the crisp plum pulp color detection step are respectively more targeted, and the judgment of the steps can be better carried out. Meanwhile, different image processing algorithms are adopted for comprehensive judgment, so that the possibility of misjudgment caused by single algorithm is also reduced. The reliability of detection is better improved. Meanwhile, in the scheme, the related scheme of the detection step of the color of the crisp plum pulp is completely proposed by the applicant for the first time, and particularly, the method of detecting the brightness of the crisp plum pulp by adopting light transmission is adopted to judge that the crisp Li Shifou is mature, so that the scheme is a very original detection scheme, and the scheme is completely feasible to independently implement, has higher judgment reliability when independently implemented, and is relatively simpler and easier to implement.
Further, the method is realized by adopting the following crisp plum maturity detection equipment based on visual identification, the crisp plum maturity detection equipment based on visual identification comprises a shell, a detection cavity is arranged in the shell, a door capable of opening the detection cavity is arranged on the shell, an objective table is arranged in the detection cavity, the method further comprises a visual identification detection system, the visual identification detection system comprises an illuminating lamp arranged above the objective table, the illuminating lamp is used as a light source, the visual identification detection system further comprises a camera arranged above the objective table in an inclined manner, and the camera is connected with a computer through a communication module; wherein, the objective table upper surface level is provided with a baffle, has the light trap that supplies fragile Li Gezhi on the baffle, and the light trap below is right to being provided with the transmission and detects and use the light source lamp.
Thus, software modules for realizing the steps of detecting the surface color of the prune and detecting the pulp color of the prune can be preset in the computer; the software module of the crisp plum surface color detection step comprises an RGB color extraction judgment module, wherein the RGB color extraction judgment module is used for extracting an R value, a G value and a B value of the crisp plums in the image, comparing the R value, the G value and the B value with preset qualified parameter values respectively, and judging that the surface color detection is qualified when the R value, the G value and the B value are all larger than the corresponding preset qualified parameter values; the software module of the crisp plum flesh color detection step comprises an image segmentation processing module and a gray level processing judging module, wherein the image segmentation processing module adopts a watershed algorithm to carry out image segmentation processing, and the shiny part and the rest part are segmented; and the gray processing judging module adopts an iteration method to realize image binarization and gray processing, obtains a black-white bicolor picture, calculates the proportion of a white part, compares the proportion with a preset qualified parameter value, and judges that the color detection of the crisp plum pulp is qualified when the proportion is larger than the preset qualified parameter value. Then, the illuminating lamp is used as a light source, the illuminating lamp is independently turned on, and the camera is used for shooting images, so that the brittle plum surface color detection step is realized. And then turning off the illuminating lamp, independently turning on the light source lamp for transmission detection, and shooting an image by means of the camera to realize the step of detecting the flesh color of the crisp plums. Therefore, the device can realize the brittle Li Chengshou degree judgment operation based on the image detection and recognition technology of two different mechanisms, and can judge the maturity of the brittle plums very conveniently, accurately and reliably. When in use, the size of the light transmission hole is about 2-3cm in diameter, which is based on that the crisp Li Neng can be placed on the light transmission hole and light can be conveniently transmitted through the crisp plums for emitting.
Further, a closed light source setting chamber is provided below the partition plate, and a light source lamp for transmission detection is installed in the light source setting chamber. Thus, the light of the light source for transmission detection can be ensured to only pass out from the light hole.
Further, a plurality of light holes are arranged on the partition board in an array mode. Thus, the detection of a batch of crisp plums can be realized at one time, and when the detection requirement of the crisp Li Manzu with the specified proportion (for example, 90%) in the batch of crisp plums is met, the batch of crisp Li Chengshou can be judged. Therefore, the brittle Li Chengshou degree judgment of batches can be realized more conveniently and rapidly. The method has practical significance for guiding production application.
Further, a light source lamp for transmission detection is arranged at the middle position below each light hole, the light source lamps for transmission detection are arranged in parallel, a detection switch is further arranged in series in each circuit branch of the light source lamp for transmission detection, and the detection switch is used for switching on the circuit branch after detecting that articles are placed on the light holes.
Therefore, after the fragile plums are placed on each light hole, the detection switch controls the light source lamp for transmission detection corresponding to the lower part to be turned on, and the detection of the fragile plums on the light holes is realized. Therefore, the light source lamp for transmission detection below the light holes without the fragile plums cannot be turned on to generate interference, so that the detection accuracy can be better ensured. In the specific implementation, the detection switch can be a piezoelectric switch or a contact switch or a proximity switch which are arranged on the light hole.
Further, a cone-shaped reflecting lampshade is arranged outside each transmission detection light source lamp, and the large-diameter end of the reflecting lampshade is upwards connected with the corresponding light hole.
Therefore, the light rays of the light source lamps for transmission detection are further guaranteed to act on the light holes above the light source lamps, the illumination effect is improved, mutual interference is avoided, and the detection reliability is improved better.
Further, the light source lamp for transmission detection is a led bulb. Thus, the cost is low and the setting is facilitated.
Further, the odor identifying and detecting system comprises a sensor array module, wherein the sensor array module is positioned in the detecting cavity or is communicated with the detecting cavity, one or more of an ethylene sensor, an aldehyde gas sensor, an alcohol gas sensor, an ester gas sensor and a phenol gas sensor are arranged on the sensor array module, and each sensor on the sensor array module is connected with a computer.
This is because the mature crisp Li Hui volatilizes characteristic gases such as ethylene, aldehydes, alcohols, esters, phenols, etc.; therefore, the corresponding gas sensor is arranged in the odor identification detection system, the content of each component in the gas volatilized in the detection chamber of the prune is detected, compared and judged, and if the corresponding gas content exceeds the preset threshold value, the corresponding gas content is judged to be mature, and the preset threshold value can be measured through a pre-test. The accurate judgment of the maturity of the crisp plums can be better assisted. The sensor array module integrates various gas sensors, so that the classification identification of the crisp Li Duoji can be better facilitated, and the classification storage or transportation is facilitated. For example, higher detection of esters and phenols indicates better maturity, while higher detection of aldehydes and alcohols indicates that the crisp Li You may be too ripe to be suitable for storage or transportation and need to be consumed as soon as possible.
Further, the smell recognition and detection system further comprises an airflow cover arranged above the objective table, the airflow cover is cone-shaped, the upper end of the airflow cover is connected to a gas detection chamber through an air extraction pipeline, an air pump and a one-way valve leading to the gas detection chamber are arranged on the air extraction pipeline, and the sensor array module is arranged in the gas detection chamber.
Therefore, the gas emitted by the brittle Li Hui on the object stage is pumped into the gas detection chamber in a gas pumping mode, enrichment of collected gas is achieved, the content proportion of volatile component gas is improved, the detection time is greatly shortened, and the detection sensitivity and accuracy are improved.
Further, the detection chamber is also internally provided with a heating device, the detection chamber is also internally communicated with an oxygen supply device, and the oxygen supply device is communicated with the detection chamber through an oxygen supply pipeline.
Thus, the temperature of the detection chamber can be increased by supplying oxygen and heating the detection chamber (the detection chamber can be heated to about 35-50 ℃ in general), the ripening environment of the crisp plums is simulated, and the ripening effect of the crisp plums is enlarged (the ripening effect of the crisp plums is enlarged mainly in a mode of increasing the oxygen concentration). The detected crisp Li Ke volatilizes characteristic gases more quickly, and the time required for odor identification and detection is greatly shortened.
Based on the crisp plum maturity detection equipment added with the heating device and the oxygen supply device, the invention essentially discloses a crisp Li Cuishou method; placing the picked plums in batches in a closed ripening space (namely, a detection room of a plums maturity detection device); then the environmental temperature of the ripening space is increased by the heating device, the oxygen content of the ripening space is increased by the oxygen supply device so as to simulate the ripening environment of the crisp plums and enlarge the ripening effect (the ripening effect is usually enlarged mainly by increasing the oxygen concentration content), the ripening process of the crisp Li Huxi is accelerated, and the natural simulated ripening of the crisp plums is realized. Compared with the ripening method relying on various ripening agents in the prior art, the ripening method is natural, scientific, rapid and efficient, no artificial reagent residue exists, natural green safety of fruit foods is ensured, and the development requirements of green foods and organic foods advocated at present are met. Meanwhile, in the ripening method, the ripening degree of the crisp plums can be detected in real time based on the equipment in the process of the crisp Li Cuishou, so that the reliability and the stability of the ripening process are ensured, and the situation that the crisp plums are difficult to transport, sell and even eat due to catalytic overripening is avoided.
Further, the bottom of the shell is also provided with a water storage cavity, water is stored in the water storage cavity, the heating device is arranged in the water storage cavity or adjacent to the water storage cavity, and the upper end of the water storage cavity is communicated with the detection cavity.
Therefore, the water in the water storage cavity can be evaporated by depending on the temperature of the heating device, so that the water is evaporated into the detection cavity, and the humidity of the detection cavity is improved. Because the crisp plums can be better ripened in a high-heat, humid and oxygen-enriched environment, the environment condition required by the ripening of the crisp plums can be better simulated, and the ripening effect is improved. In the use processes of detecting the crisp Li Chengshou degrees, ripening the crisp plums and the like, the required time can be shortened better, and the equipment use efficiency is improved. The heating means is preferably an electrical heating means to facilitate control.
Further, the bottom of the water storage cavity is obliquely arranged, and a water discharge switch valve is arranged at the lower side of the water storage cavity.
Therefore, when the device is not needed to be used in ripening, water in the water storage cavity is conveniently discharged through the water discharge switch valve, and damage to parts caused by overlarge humidity in the device is prevented.
Further, a temperature sensor, an oxygen concentration sensor and a humidity sensor are further arranged in the detection cavity, the temperature sensor, the oxygen concentration sensor and the humidity sensor are respectively connected with a computer, and the computer is respectively connected with a heating device, an oxygen supply device and a switch control valve arranged at the upper end of the water storage cavity and the communication position of the detection cavity to realize control.
Therefore, the temperature, humidity and oxygen-containing concentration data in the detection cavity can be detected and monitored in real time, the temperature, humidity and oxygen-containing concentration data are controlled to be in a proper ripening degree, and the stability and reliability of the ripening process are ensured.
Further, a turbulent fan is arranged above the objective table.
The bypass fan can well ensure that the temperature, the humidity and the oxygen content concentration of each part in the detected air are in an equilibrium state, so that the crispness Li Neng used for detection or ripening in batches in the bypass fan can more uniformly realize ripening.
Further, the lower part of the object stage is provided with a storage space, a storage frame is placed in the storage space in a drawable manner, and holes are densely distributed on the storage frame.
Therefore, when the device is used for the crispy plum in batches Li Cuishou, the storage frame can be used for accommodating the crispy plums, so that the quantity of the crispy plums subjected to the batch ripening treatment is increased.
Further, the outer side of the shell is also provided with an insulating layer.
Therefore, the heat preservation and heat insulation can be realized, and the internal ripening environment can be kept.
Further, a prune deboning detection device is arranged in the detection cavity and used for detecting the prune deboning degree.
Because the crisp Li Youming deboned plums have the characteristics that the pulp and the fruit pits of the crisp plums are separated to form a hollow shape after the crisp plums are ripe, the more ripe crisp plums have obvious deboned effect relative to the crisp plums, and meanwhile, consumers are willing to purchase the crisp plums with obvious deboned effect, so that the crisp plums have better taste after eating and the fruit pits are easier to separate and spit completely, and the crisp plums with obvious deboned plums are higher. Therefore, after the crisp Li Chengshou degrees are detected, the bone removal degree of the crisp plums can be detected, and the grading sorting of products can be better assisted.
Further, the fragile plum bone removal detection device comprises a mesh orifice plate which is horizontally arranged, a blast channel is arranged below the mesh orifice plate, a blower is arranged below the blast channel, and an upward blocking piece is arranged on the periphery of the mesh orifice plate.
In this way, the blower blows air through the air blowing duct to uniformly guide and apply strong air flow to the mesh plate, and when detecting, the blower will be fragile Li Fangzhi to the mesh plate. The fragile plum with high bone removal degree has larger internal space, smaller relative density and is easier to be blown upwards by the blower, so the air flow speed is adjusted, and the bone removal degree of the fragile plum can be judged according to whether the fragile Li Neng is blown away from the mesh orifice plate or not and even the height of the fragile plum blown away from the mesh orifice plate. And further realizes the grading sorting of the crisp plums. Meanwhile, the method has the characteristics of being very convenient and quick and not damaging the fragile plums. Wherein the blocking member prevents the prunes from being blown out of the mesh opening plate. As other modes, when the method is implemented, the detection of the bone-removing degree of the crisp plums can be realized in a reselection mode by adopting the water solution with the prepared density, but the method has the defects of poor reliability, inconvenient operation and inconvenience for later storage or eating after the crisp Li Zhan water.
Further, the blocking piece is a vertically arranged cloth with the height of 3-8 cm.
The blocking piece is formed by adopting the cloth with the height of 3-8cm, the cloth is flexible, is in a soft state when not blown, is convenient for placing the fragile plums, is blown to be in a vertical upward state in the detection process, and does not damage the fragile plums in the detection process.
Further, the mesh plate is divided into a long strip shape with the width of 4-7cm and the length of several times of the width by the surrounding cloth.
Like this, can hold in width direction and prevent next or two fragile plums just, can concentrate upward blowing fragile plums with the windstream in width direction and detect, still can avoid blocking piece self to exist to the interference of fragile Li Shouli to the maximum extent (if can put into three or more fragile plums in the width direction, the fragile plums of obvious intermediate position and the fragile Li Shou upward force effect of both sides position can be different, both sides can receive the surrounding cloth interference), can guarantee fragile Li Shouli equilibrium better, improve the reliability of detecting.
Further, meshes are densely distributed on the surrounding cloth and are increased from bottom to top.
Thus, the more upward and outward wind flows are lost, and the smaller the upward supporting force of the fragile plums is due to the wind flow. Therefore, the bone-removing degree of the crisp plums can be judged better in an auxiliary mode according to the blown-up height of the crisp plums, and the crisp Li Fenji can be realized more accurately in an auxiliary mode.
In conclusion, the invention is designed specifically for crisp Li Tedian, and has the advantage of being capable of judging whether the crisp Li Tedian is mature or not more accurately and reliably.
Drawings
Fig. 1 is a schematic structural diagram of a prune maturity detection apparatus according to an embodiment of the present invention.
Fig. 2 is a schematic view of the door and the panel of fig. 1 with the front side removed and showing the internal structure.
FIG. 3 is a schematic view of the upper surface baffle of the individual stage of FIG. 2.
Fig. 4 is an enlarged schematic view of fig. 2 at a single point a.
Fig. 5 is a schematic view of the individual enclosures of fig. 2.
Fig. 6 is a comparison chart of photographs obtained after the camera shooting, the image segmentation processing and the image binarization gray scale processing in the detection step of the flesh color of the crisp plums in three different maturity degrees.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings.
Best mode for carrying out the invention: the method for detecting the maturity of the prune based on visual identification comprises a prune surface color detection step, namely, irradiating the prune with a light source Li Biaomian, shooting a photo to obtain surface image information of the prune, processing the surface image information by a computer, extracting surface color characteristic parameters and surface color qualified preset parameter values of the prune, and comparing and judging the surface color characteristic parameters and the surface color qualified preset parameter values, wherein the method also comprises a prune pulp color detection step, namely, transmitting the prune with the light source, shooting the photo to obtain pulp transmission image information of the prune, and extracting pulp color characteristic parameters and the pulp color qualified preset parameter values of the prune by the computer for comparing and judging; and judging the crisp Li Chengshou when the surface color characteristic parameter is larger than the surface color qualified preset parameter value and the pulp color characteristic parameter is larger than the pulp color qualified preset parameter value.
This is because the surface colour starts to yellow after the prune has ripened, the more yellow the colour is, the higher the ripeness. However, the color change of the surface of the prune is mainly related to the irradiation amplitude of the sun, and sometimes the irradiation of the sun is too strong, which may cause the peel and yellowing of the inner pulp when the inner pulp is not fully mature. At the same time, sometimes crisp plums not exposed to the sun, even after the flesh has fully ripened, may have relatively insignificant surface color changes. However, after the crisp plums are ripe, the pulp of the crisp plums is certainly converted into crystal clear pulp, and the pulp transmittance of the crisp plums is sharply improved. Therefore, in the method, a light source transmission mode is adopted, so that the light source transmits the crispy plum pulp, then the transmission image information of the crispy plum pulp is shot for detection and judgment, the crispy plums with different maturity degrees are completely different in transmission brightness, and whether the crispy plums are mature or not can be accurately judged. Then, two modes based on visual recognition are adopted simultaneously, and the judgment and the detection are combined, so that the accuracy and the reliability of the detection can be greatly improved.
In the step of detecting the color of the surface of the crisp plums, in a detection chamber sealed by the crisp Li Zhiyu, an illuminating lamp at the position above the crisp plums is used as a light source for illumination, and a camera is arranged above the crisp plums for shooting and detection.
Therefore, the unified stability of the detection light source can be better ensured, the interference of sunlight and external light is avoided, and the reliability of the detection result is ensured. In the implementation, the illuminating lamp is arranged right above or obliquely above, and the camera is arranged right above or obliquely above.
When the color and luster of the fragile plums are detected, the transparent holes in the partition plate horizontally arranged in the detection cavity which is sealed by the fragile Li Zhiyu are irradiated by the light source lamp for transmission detection, and the camera is arranged obliquely above the fragile plums for shooting and detection.
Therefore, the stability of the detection light source can be better ensured, and the interference of the external light source is avoided. Meanwhile, the arrangement of the partition plate ensures the transmission effect, and the camera is positioned at the upper part obliquely, so that the bright part of the crisp plums after being transmitted extends upwards from the edge position of the light holes at the lower part, the higher the maturity of the crisp plums is, the larger and brighter the bright area of the lower end extending upwards is, and the range of the bright area of the crisp Li Xia part can be better detected by adopting the camera at the upper part obliquely, so that the detection precision is improved. Meanwhile, the classification detection of the maturity of the crisp plums can be realized based on the range of the crisp Li Faliang area.
And when the R value, the G value and the B value are all larger than the corresponding qualified preset parameter values, judging that the surface color detection is qualified.
This is because the color of the crisp plum surface is detected and more judged by the color of the surface. According to actual detection, analysis and comparison, the surface color of the more mature crisp plums is more yellow, the three-element color of image extraction R, G, B is increased along with the increase of the maturity of the crisp plums, wherein the increase of the R value is most obvious, the increase degree of the G value is secondary, and the increase of the B value is more secondary. Therefore, in the method, RGB color extraction technology is adopted in the step of detecting the surface color of the prune, three primary colors are extracted for judgment respectively, and the maturity of the prune can be judged more accurately through comparing the three primary colors with a threshold value. In implementation, the technology of performing RGB color extraction according to pictures is mature prior art, and will not be described in detail herein. The qualified preset parameter value for judgment can be obtained by manually selecting mature crisp Li Shiyan in advance. Of course, in implementation, other methods of image feature extraction may be used to perform detection and determination, for example, an image feature extraction processing technique featuring three elements, i.e., h, s, and w, but the specific determination method needs to be verified separately and is not described in detail herein.
When the color detection step of the crisp plum pulp is carried out, after the camera shoots, image information is transmitted to a computer, a watershed algorithm is adopted to carry out image segmentation processing, an iteration method is adopted to binarize the image, gray processing is realized, a black-white dichroism image is obtained, the proportion of a white part is calculated, and then the proportion is compared with a preset qualified parameter value, and the condition that the color detection of the crisp plum pulp is qualified is judged when the proportion is larger than the preset qualified parameter value.
In this way, the color detection step of the prune flesh is to detect the prune flesh according to the difference of brightness after the prune flesh is transmitted by light. Therefore, the proportion of the white area is detected after the image is binarized and black-and-white processed, and the proportion of the luminous area is obtained. And is used as a standard for judging whether the pulp is ripe or not, and is more accurate and reliable. The specific steps of the watershed algorithm, the iteration method and the like belong to the mature prior art, and are not described in detail herein. Referring to fig. 6, in the step of detecting the flesh color of the crisp plums, the contrast images of the three crisp plums with different maturity are obtained from left to right after the shooting by the camera, the image segmentation processing and the image binarization gray scale processing. Three kinds of crisp plums with different maturity are low-degree ripeness at the upper part, medium-degree ripeness at the middle part and high-degree ripeness at the lower part. The left side is the photo after the camera shoots, the middle is the photo after the image segmentation processing, and the right side is the photo after the image binarization gray processing. Wherein the left and middle photographs are originally brittle Li Yuanse, the color is canceled due to the declared text format requiring processing. As can be seen from fig. 6, the more mature crisp plums, the larger the proportion of white lightening areas is after binarization of the image, the more obvious the distinction is, so that the accuracy is high and the classification sorting can be well assisted as a judging standard for whether the pulp is mature or not.
In the sample application, different image processing algorithms are respectively adopted for the crisp plum surface color detection step and the crisp plum pulp color detection step, so that the crisp plum surface color detection step and the crisp plum pulp color detection step are respectively more targeted, and the judgment of the steps can be better carried out. Meanwhile, different image processing algorithms are adopted for comprehensive judgment, so that the possibility of misjudgment caused by single algorithm is also reduced. The reliability of detection is better improved. Meanwhile, in the scheme, the related scheme of the detection step of the color of the crisp plum pulp is completely proposed by the applicant for the first time, and particularly, the method of detecting the brightness of the crisp plum pulp by adopting light transmission is adopted to judge that the crisp Li Shifou is mature, so that the scheme is a very original detection scheme, and the scheme is completely feasible to independently implement, has higher judgment reliability when independently implemented, and is relatively simpler and easier to implement.
In the embodiment, the method is realized by adopting a crisp plum maturity detection device based on visual identification, and the crisp plum maturity detection device based on visual identification is shown in fig. 1-5, and comprises a shell 1, wherein a detection chamber 2 is arranged in the shell 1, a door 3 capable of opening the detection chamber is arranged on the shell 1, an objective table 4 is arranged in the detection chamber 2, the method further comprises a visual identification detection system, the visual identification detection system comprises an illuminating lamp 5 arranged above the objective table, the illuminating lamp 5 is used as a light source, the visual identification detection system further comprises a camera 6 arranged obliquely above the objective table, and the camera 6 is connected with a computer 7 through a communication module; wherein, the objective table upper surface level is provided with a baffle 8, has the light trap 9 that supplies fragile Li Gezhi on the baffle 8, and light source lamp 10 for transmission detection is arranged right below light trap 9.
Thus, software modules for realizing the steps of detecting the surface color of the prune and detecting the pulp color of the prune can be preset in the computer; the software module of the crisp plum surface color detection step comprises an RGB color extraction judgment module, wherein the RGB color extraction judgment module is used for extracting an R value, a G value and a B value of the crisp plums in the image, comparing the R value, the G value and the B value with preset qualified parameter values respectively, and judging that the surface color detection is qualified when the R value, the G value and the B value are all larger than the corresponding preset qualified parameter values; the software module of the crisp plum flesh color detection step comprises an image segmentation processing module and a gray level processing judging module, wherein the image segmentation processing module adopts a watershed algorithm to carry out image segmentation processing, and the shiny part and the rest part are segmented; and the gray processing judging module adopts an iteration method to realize image binarization and gray processing, obtains a black-white bicolor picture, calculates the proportion of a white part, compares the proportion with a preset qualified parameter value, and judges that the color detection of the crisp plum pulp is qualified when the proportion is larger than the preset qualified parameter value. Then, the illuminating lamp is used as a light source, the illuminating lamp is independently turned on, and the camera is used for shooting images, so that the brittle plum surface color detection step is realized. And then turning off the illuminating lamp, independently turning on the light source lamp for transmission detection, and shooting an image by means of the camera to realize the step of detecting the flesh color of the crisp plums. Therefore, the device can realize the brittle Li Chengshou degree judgment operation based on the image detection and recognition technology of two different mechanisms, and can judge the maturity of the brittle plums very conveniently, accurately and reliably. When in use, the size of the light transmission hole is about 2-3cm in diameter, which is based on that the crisp Li Neng can be placed on the light transmission hole and light can be conveniently transmitted through the crisp plums for emitting.
Wherein, a closed light source setting chamber is arranged below the partition board, and a light source lamp 10 for transmission detection is arranged in the light source setting chamber. Thus, the light of the light source for transmission detection can be ensured to only pass out from the light hole.
Wherein, a plurality of light holes 9 are arranged on the partition board in an array manner. Thus, the detection of a batch of crisp plums can be realized at one time, and when the detection requirement of the crisp Li Manzu with the specified proportion (for example, 90%) in the batch of crisp plums is met, the batch of crisp Li Chengshou can be judged. Therefore, the brittle Li Chengshou degree judgment of batches can be realized more conveniently and rapidly. The method has practical significance for guiding production application.
Wherein, a light source lamp 10 for transmission detection is installed in the middle position below each light hole 9, the light source lamps 10 for transmission detection are arranged in parallel, a detection switch 11 is also arranged in series in the circuit branch of each light source lamp for transmission detection, and the detection switch 11 is used for switching on the circuit branch after detecting that articles are placed on the light holes.
Therefore, after the fragile plums are placed on each light hole, the detection switch controls the light source lamp for transmission detection corresponding to the lower part to be turned on, and the detection of the fragile plums on the light holes is realized. Therefore, the light source lamp for transmission detection below the light holes without the fragile plums cannot be turned on to generate interference, so that the detection accuracy can be better ensured. In the specific implementation, the detection switch can be a piezoelectric switch or a contact switch or a proximity switch which are arranged on the light hole.
Wherein, each light source lamp 10 for transmission detection is provided with a cone-shaped reflecting lampshade 12 outside, and the large diameter end of the reflecting lampshade 12 is upwards connected with the corresponding light hole 9.
Therefore, the light rays of the light source lamps for transmission detection are further guaranteed to act on the light holes above the light source lamps, the illumination effect is improved, mutual interference is avoided, and the detection reliability is improved better.
The light source lamp 10 for transmission detection is a led bulb. Thus, the cost is low and the setting is facilitated.
The odor identifying and detecting system comprises a sensor array module 17, wherein the sensor array module 17 is positioned in the detecting cavity or is communicated with the detecting cavity, one or more of an ethylene sensor, an aldehyde gas sensor, an alcohol gas sensor, an ester gas sensor and a phenol gas sensor are arranged on the sensor array module, and each sensor on the sensor array module is connected with a computer.
This is because the mature crisp Li Hui volatilizes characteristic gases such as ethylene, aldehydes, alcohols, esters, phenols, etc.; therefore, the corresponding gas sensor is arranged in the odor identification detection system, the content of each component in the gas volatilized in the detection chamber of the prune is detected, compared and judged, and if the corresponding gas content exceeds the preset threshold value, the corresponding gas content is judged to be mature, and the preset threshold value can be measured through a pre-test. The accurate judgment of the maturity of the crisp plums can be better assisted. The sensor array module integrates various gas sensors, so that the classification identification of the crisp Li Duoji can be better facilitated, and the classification storage or transportation is facilitated. For example, higher detection of esters and phenols indicates better maturity, while higher detection of aldehydes and alcohols indicates that the crisp Li You may be too ripe to be suitable for storage or transportation and need to be consumed as soon as possible.
The smell identifying and detecting system further comprises an air flow cover 13 arranged above the object stage, the air flow cover is in a cone-shaped hopper shape, the upper end of the air flow cover 13 is connected to a gas detecting chamber 14 through an air exhaust pipeline, an air pump 15 and a one-way valve 16 leading to the gas detecting chamber are arranged on the air exhaust pipeline, and the sensor array module 17 is arranged in the gas detecting chamber.
Therefore, the gas emitted by the brittle Li Hui on the object stage is pumped into the gas detection chamber in a gas pumping mode, enrichment of collected gas is achieved, the content proportion of volatile component gas is improved, the detection time is greatly shortened, and the detection sensitivity and accuracy are improved.
Wherein, still be provided with heating device 18 in the detection cavity, still be provided with oxygen suppliment device 19 in the detection cavity 2 switch-on, oxygen suppliment device 19 communicates with detection cavity 2 through the oxygen supply pipeline.
Thus, the temperature of the detection chamber can be increased by supplying oxygen and heating the detection chamber (the detection chamber can be heated to about 35-50 ℃ in general), the ripening environment of the crisp plums is simulated, and the ripening effect of the crisp plums is enlarged (the ripening effect of the crisp plums is enlarged mainly in a mode of increasing the oxygen concentration). The detected crisp Li Ke volatilizes characteristic gases more quickly, and the time required for odor identification and detection is greatly shortened.
Based on the crisp plum maturity detection equipment added with the heating device and the oxygen supply device, the invention essentially discloses a crisp Li Cuishou method; placing the picked plums in batches in a closed ripening space (namely, a detection room of a plums maturity detection device); then the environmental temperature of the ripening space is increased by the heating device, the oxygen content of the ripening space is increased by the oxygen supply device so as to simulate the ripening environment of the crisp plums and enlarge the ripening effect (the ripening effect is usually enlarged mainly by increasing the oxygen concentration content), the ripening process of the crisp Li Huxi is accelerated, and the natural simulated ripening of the crisp plums is realized. Compared with the ripening method relying on various ripening agents in the prior art, the ripening method is natural, scientific, rapid and efficient, no artificial reagent residue exists, natural green safety of fruit foods is ensured, and the development requirements of green foods and organic foods advocated at present are met. Meanwhile, in the ripening method, the ripening degree of the crisp plums can be detected in real time based on the equipment in the process of the crisp Li Cuishou, so that the reliability and the stability of the ripening process are ensured, and the situation that the crisp plums are difficult to transport, sell and even eat due to catalytic overripening is avoided.
The bottom of the shell 1 is also provided with a water storage cavity 20, water is stored in the water storage cavity 20, the heating device 18 is arranged in or adjacent to the water storage cavity 20, and the upper end of the water storage cavity is communicated with the detection cavity.
Therefore, the water in the water storage cavity can be evaporated by depending on the temperature of the heating device, so that the water is evaporated into the detection cavity, and the humidity of the detection cavity is improved. Because the crisp plums can be better ripened in a high-heat, humid and oxygen-enriched environment, the environment condition required by the ripening of the crisp plums can be better simulated, and the ripening effect is improved. In the use processes of detecting the crisp Li Chengshou degrees, ripening the crisp plums and the like, the required time can be shortened better, and the equipment use efficiency is improved. The heating means is preferably an electrical heating means to facilitate control.
Wherein, the bottom of the water storage cavity 20 is obliquely arranged, and a water discharge switch valve is arranged at the lower side position.
Therefore, when the device is not needed to be used in ripening, water in the water storage cavity is conveniently discharged through the water discharge switch valve, and damage to parts caused by overlarge humidity in the device is prevented.
The detection chamber is also provided with a temperature sensor, an oxygen concentration sensor and a humidity sensor (not shown in the figure), the temperature sensor, the oxygen concentration sensor and the humidity sensor are respectively connected with a computer 7, and the computer is respectively connected with a heating device 18, an oxygen supply device 19 and a switch control valve arranged at the upper end of the water storage chamber and the communication position of the detection chamber to realize control.
Therefore, the temperature, humidity and oxygen-containing concentration data in the detection cavity can be detected and monitored in real time, the temperature, humidity and oxygen-containing concentration data are controlled to be in a proper ripening degree, and the stability and reliability of the ripening process are ensured.
Wherein, turbulent fan 21 is also arranged above objective table 4.
The bypass fan can well ensure that the temperature, the humidity and the oxygen content concentration of each part in the detected air are in an equilibrium state, so that the crispness Li Neng used for detection or ripening in batches in the bypass fan can more uniformly realize ripening.
Wherein, the lower part of the object stage 4 is provided with a storage space, a storage frame 22 is arranged in the storage space in a drawable manner, and holes are densely distributed on the storage frame.
Therefore, when the device is used for the crispy plum in batches Li Cuishou, the storage frame can be used for accommodating the crispy plums, so that the quantity of the crispy plums subjected to the batch ripening treatment is increased.
Wherein, the outside of the shell 1 is also provided with an insulating layer.
Therefore, the heat preservation and heat insulation can be realized, and the internal ripening environment can be kept.
The detection chamber 2 is also internally provided with a crisp plum bone-removal detection device for detecting the bone-removal degree of the crisp plums.
Because the crisp Li Youming deboned plums have the characteristics that the pulp and the fruit pits of the crisp plums are separated to form a hollow shape after the crisp plums are ripe, the more ripe crisp plums have obvious deboned effect relative to the crisp plums, and meanwhile, consumers are willing to purchase the crisp plums with obvious deboned effect, so that the crisp plums have better taste after eating and the fruit pits are easier to separate and spit completely, and the crisp plums with obvious deboned plums are higher. Therefore, after the crisp Li Chengshou degrees are detected, the bone removal degree of the crisp plums can be detected, and the grading sorting of products can be better assisted.
The crisp plum bone removal detection device comprises a mesh orifice plate 23 which is horizontally arranged, a blast duct 24 is arranged below the mesh orifice plate, a blower 25 is arranged below the blast duct, and an upward blocking piece 26 is arranged on the periphery of the mesh orifice plate.
In this way, the blower blows air through the air blowing duct to uniformly guide and apply strong air flow to the mesh plate, and when detecting, the blower will be fragile Li Fangzhi to the mesh plate. The fragile plum with high bone removal degree has larger internal space, smaller relative density and is easier to be blown upwards by the blower, so the air flow speed is adjusted, and the bone removal degree of the fragile plum can be judged according to whether the fragile Li Neng is blown away from the mesh orifice plate or not and even the height of the fragile plum blown away from the mesh orifice plate. And further realizes the grading sorting of the crisp plums. Meanwhile, the method has the characteristics of being very convenient and quick and not damaging the fragile plums. Wherein the blocking member prevents the prunes from being blown out of the mesh opening plate. As other modes, when the method is implemented, the detection of the bone-removing degree of the crisp plums can be realized in a reselection mode by adopting the water solution with the prepared density, but the method has the defects of poor reliability, inconvenient operation and inconvenience for later storage or eating after the crisp Li Zhan water.
Wherein the blocking piece 26 is a vertically arranged cloth with the height of 3-8 cm.
The blocking piece is formed by adopting the cloth with the height of 3-8cm, the cloth is flexible, is in a soft state when not blown, is convenient for placing the fragile plums, is blown to be in a vertical upward state in the detection process, and does not damage the fragile plums in the detection process.
Wherein, the mesh hole plate is divided into long strips with the width of 4-7cm and the length of several times of the width by the surrounding cloth.
Like this, can hold in width direction and prevent next or two fragile plums just, can concentrate upward blowing fragile plums with the windstream in width direction and detect, still can avoid blocking piece self to exist to the interference of fragile Li Shouli to the maximum extent (if can put into three or more fragile plums in the width direction, the fragile plums of obvious intermediate position and the fragile Li Shou upward force effect of both sides position can be different, both sides can receive the surrounding cloth interference), can guarantee fragile Li Shouli equilibrium better, improve the reliability of detecting.
Wherein, the meshes 27 are densely distributed on the surrounding cloth and are increased from bottom to top.
Thus, the more upward and outward wind flows are lost, and the smaller the upward supporting force of the fragile plums is due to the wind flow. Therefore, the bone-removing degree of the crisp plums can be judged better in an auxiliary mode according to the blown-up height of the crisp plums, and the crisp Li Fenji can be realized more accurately in an auxiliary mode.

Claims (8)

1. The method for detecting the maturity of the prune based on visual identification comprises a prune surface color detection step, namely, irradiating the prune with a light source, shooting a photo to obtain surface image information of the prune, processing the surface image information by a computer, and extracting a surface color characteristic parameter and a surface color qualified preset parameter value for comparison and judgment, and is characterized by further comprising a prune pulp color detection step, namely, transmitting the prune with the light source, shooting the photo to obtain pulp transmission image information of the prune, and extracting a pulp color characteristic parameter and a pulp color qualified preset parameter value for comparison and judgment by the computer; judging crispness Li Chengshou when the surface color characteristic parameter is larger than the surface color qualified preset parameter value and the pulp color characteristic parameter is larger than the pulp color qualified preset parameter value;
in the step of detecting the color of the crisp plum flesh, a light hole on a partition plate horizontally arranged in a detection chamber sealed by crisp Li Zhiyu is irradiated by a light source lamp for transmission detection arranged below the light hole, and a camera is arranged obliquely above the crisp plum for shooting detection; when the color of the crisp plum flesh is changed, the brighter the lighting area of which the lower end extends upwards is, the higher the maturity of the crisp plum is, so that the classification detection of the maturity of the crisp plum can be realized based on the range of the area of the crisp Li Faliang;
In the step of detecting the color of the crisp plum pulp, after the camera shoots, image information is transmitted to a computer, a watershed algorithm is adopted to carry out image segmentation processing, an iteration method is adopted to binarize the image, gray processing is realized, a black-white dichroism image is obtained, the proportion of a white part is calculated, and then the proportion is compared with a preset qualified parameter value, and the condition that the color of the crisp plum pulp is detected to be qualified is judged when the proportion is larger than the preset qualified parameter value.
2. The method for detecting the maturity of the crisp plums based on visual recognition according to claim 1, wherein in the step of detecting the surface color of the crisp plums, an illuminating lamp at the position above the crisp plums is used as a light source for illumination in a detection chamber sealed by a crisp Li Zhiyu, and a camera is arranged above the crisp plums for shooting and detection.
3. The method for detecting the maturity of the crisp plums based on visual recognition according to claim 1, wherein in the step of detecting the surface color of the crisp plums, after the camera shoots, image information is transmitted to a computer, R value, G value and B value of the crisp plums in the image are extracted by adopting RGB color extraction technology, the R value, the G value and the B value are respectively compared with preset qualified preset parameter values, and when the R value, the G value and the B value are all larger than the corresponding qualified preset parameter values, the detection of the surface color is judged to be qualified.
4. The method for detecting the maturity of the crisp plums based on visual identification according to claim 1 is characterized by comprising the following visual identification based crisp plums maturity detection equipment, wherein the visual identification based crisp plums maturity detection equipment comprises a shell, a detection chamber is arranged inside the shell, a door capable of opening the detection chamber is arranged on the shell, an objective table is arranged inside the detection chamber, the visual identification based crisp plums maturity detection equipment further comprises a visual identification detection system, the visual identification based crisp plums maturity detection system comprises an illuminating lamp arranged above the objective table, the illuminating lamp is used as a light source, the visual identification based crisp plums maturity detection system further comprises a camera arranged obliquely above the objective table, and the camera is connected with a computer through a communication module; wherein, the objective table upper surface level is provided with a baffle, has the light trap that supplies fragile Li Gezhi on the baffle, and the light trap below is right to being provided with the transmission and detects and use the light source lamp.
5. The visual recognition-based crisp plum maturity detection method as claimed in claim 4, wherein a closed light source setting chamber is provided below the partition plate, and a light source lamp for transmission detection is installed in the light source setting chamber.
6. The method for detecting the maturity of crisp plums based on visual recognition according to claim 4, wherein a light source lamp for transmission detection is installed at the center position below each light hole, the light source lamps for transmission detection are arranged in parallel, a detection switch is further arranged in series in each circuit branch of the light source lamps for transmission detection, and the detection switch is used for switching on the circuit branch after detecting that articles are placed on the light holes.
7. The visual recognition-based crisp plum maturity detection method according to claim 4, wherein a cone-shaped reflecting lampshade is arranged outside each transmission detection light source lamp, and the large diameter end of the reflecting lampshade is upwards connected with the corresponding light hole;
the light source lamp for transmission detection is a led bulb.
8. The method for detecting the maturity of the prune based on visual identification according to claim 4, wherein a prune deboning detection device is further arranged in the detection chamber for detecting the degree of the deboning of the prune;
the crisp plum bone removal detection device comprises a mesh orifice plate which is horizontally arranged, a blast channel is arranged below the mesh orifice plate, a blower is arranged below the blast channel, and an upward blocking piece is arranged on the periphery of the mesh orifice plate;
the blocking piece is a vertically arranged cloth with the height of 3-8 cm; the mesh hole plate is divided into long strips with the width of 4-7cm and the length of several times of the width by the surrounding cloth; meshes are densely distributed on the surrounding cloth and are increased from bottom to top.
CN202110698288.4A 2021-06-23 2021-06-23 Crisp plum maturity detection method based on visual recognition Active CN113390834B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202110698288.4A CN113390834B (en) 2021-06-23 2021-06-23 Crisp plum maturity detection method based on visual recognition
CN202310574112.7A CN116380814A (en) 2021-06-23 2021-06-23 Crisp plum maturity detection equipment based on visual identification

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110698288.4A CN113390834B (en) 2021-06-23 2021-06-23 Crisp plum maturity detection method based on visual recognition

Related Child Applications (1)

Application Number Title Priority Date Filing Date
CN202310574112.7A Division CN116380814A (en) 2021-06-23 2021-06-23 Crisp plum maturity detection equipment based on visual identification

Publications (2)

Publication Number Publication Date
CN113390834A CN113390834A (en) 2021-09-14
CN113390834B true CN113390834B (en) 2023-04-28

Family

ID=77623708

Family Applications (2)

Application Number Title Priority Date Filing Date
CN202310574112.7A Pending CN116380814A (en) 2021-06-23 2021-06-23 Crisp plum maturity detection equipment based on visual identification
CN202110698288.4A Active CN113390834B (en) 2021-06-23 2021-06-23 Crisp plum maturity detection method based on visual recognition

Family Applications Before (1)

Application Number Title Priority Date Filing Date
CN202310574112.7A Pending CN116380814A (en) 2021-06-23 2021-06-23 Crisp plum maturity detection equipment based on visual identification

Country Status (1)

Country Link
CN (2) CN116380814A (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114097425A (en) * 2021-12-02 2022-03-01 南通科技职业学院 Portable telescopic high-altitude fruit picking device and method thereof
CN116584472B (en) * 2023-07-13 2023-10-27 四川省农业机械科学研究院 Multistage control-based brittle Li Pen medicine method and system

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01127088A (en) * 1987-11-11 1989-05-19 Hiroshi Uda Method and apparatus for automatically grading and classifying vetgetables and fruits
JP2002139433A (en) * 2000-11-02 2002-05-17 Kansai Tlo Kk Method for discriminating internal quality of vegetable and fruit
JP2003021598A (en) * 2001-07-09 2003-01-24 Mitsui Mining & Smelting Co Ltd Vegetables and fruits evaluation apparatus
JP2003042942A (en) * 2001-08-03 2003-02-13 Ishii Ind Co Ltd Instrument for measuring specimen
JP2004097969A (en) * 2002-09-10 2004-04-02 Shinsen Giken:Kk Imaging apparatus for imaging down face of agricultural product and classifying apparatus for sorting rank of agricultural product
CN104056789A (en) * 2013-03-19 2014-09-24 青岛农业大学 Carrot defect image quantitative detection method and carrot sorting apparatus
CN105874322A (en) * 2013-11-01 2016-08-17 陶朗分选股份有限公司 Method and apparatus for detecting matter
CN110756455A (en) * 2018-07-25 2020-02-07 成都东山兰韵农业有限公司 Strawberry sorting device
CN111860125A (en) * 2020-06-04 2020-10-30 南通科技职业学院 Method for identifying fruit maturity based on machine vision

Family Cites Families (21)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1245630C (en) * 2004-01-08 2006-03-15 江苏大学 Agricultural and animal product nondestrctive detection method based on electronic visual sense and smell sense fusion technology and its device
CN2733343Y (en) * 2004-05-12 2005-10-12 严衍禄 Internal non-destructive integral analytical equipment for agricultural products such as fruit and vegetable
BE1018303A3 (en) * 2008-10-10 2010-08-03 Bestray METHOD FOR DIVIDING A STONE FRUIT IN A PRELIMINARY CLASS.
ES2403335B1 (en) * 2010-06-08 2014-09-10 Multiscan Technologies, S.L. MACHINE FOR INSPECTION AND CLASSIFICATION OF FRUITS AND METHOD TO INSPECT AND CLASSIFY FRUITS USED BY SUCH MACHINE.
CN102972512A (en) * 2012-11-28 2013-03-20 刘江辉 Household intelligent fruit and vegetable storage and fresh-keeping device
CN204486317U (en) * 2014-12-05 2015-07-22 江苏瑞雪海洋科技股份有限公司 One main laver automatic sorting device
CN106338517A (en) * 2016-09-23 2017-01-18 江苏大学 Intelligent judgment method for fruit freshness based on coordination of visual information and olfactory information
CN206325858U (en) * 2016-11-01 2017-07-14 湖北中烟工业有限责任公司 A kind of cigarette perfume pearl automatic splinter screening device for screening
CN106622958A (en) * 2017-01-23 2017-05-10 贵州大学 Abortive grain and plump grain separation machine and separation method thereof
CN107860722B (en) * 2017-10-30 2020-04-21 内蒙古农业大学 Method and system for online detection of internal quality of honeydew melons
CN108273764A (en) * 2017-12-28 2018-07-13 华东交通大学 A kind of intelligence fruit sorter
CN208987772U (en) * 2018-01-17 2019-06-18 宁波大学 A kind of safety device of porphyra haitanensis processing
CN108827962B (en) * 2018-04-28 2020-03-27 四川大学 Egg maturity detection method based on light transmission method
CN108872085B (en) * 2018-05-09 2023-04-25 南京林业大学 Navel orange heart rot nondestructive testing method based on blue wave band transmission image detection
CN109490418B (en) * 2018-12-24 2020-11-17 长江师范学院 Rapid detection method and device for pepper quality and application
CN210449861U (en) * 2019-05-22 2020-05-05 北京义利面包食品有限公司 Walnut separating and sorting device
CN211587513U (en) * 2019-12-13 2020-09-29 雷波县小平特色农产品开发有限公司 Winnowing type walnut kernel and shell separator
CN111282847A (en) * 2020-02-21 2020-06-16 莱芜职业技术学院 Foreign trade agricultural product detection device based on thing networking
CN111422407B (en) * 2020-03-31 2021-07-30 方家铺子（莆田）绿色食品有限公司 Longan packaging machine
CN111687069B (en) * 2020-06-01 2023-02-28 安徽农业大学 Intelligent pecan shell and kernel sorting machine based on convolutional neural network algorithm
CN112893190A (en) * 2021-01-27 2021-06-04 广东工业大学 Plum sorting machine

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPH01127088A (en) * 1987-11-11 1989-05-19 Hiroshi Uda Method and apparatus for automatically grading and classifying vetgetables and fruits
JP2002139433A (en) * 2000-11-02 2002-05-17 Kansai Tlo Kk Method for discriminating internal quality of vegetable and fruit
JP2003021598A (en) * 2001-07-09 2003-01-24 Mitsui Mining & Smelting Co Ltd Vegetables and fruits evaluation apparatus
JP2003042942A (en) * 2001-08-03 2003-02-13 Ishii Ind Co Ltd Instrument for measuring specimen
JP2004097969A (en) * 2002-09-10 2004-04-02 Shinsen Giken:Kk Imaging apparatus for imaging down face of agricultural product and classifying apparatus for sorting rank of agricultural product
CN104056789A (en) * 2013-03-19 2014-09-24 青岛农业大学 Carrot defect image quantitative detection method and carrot sorting apparatus
CN105874322A (en) * 2013-11-01 2016-08-17 陶朗分选股份有限公司 Method and apparatus for detecting matter
CN110756455A (en) * 2018-07-25 2020-02-07 成都东山兰韵农业有限公司 Strawberry sorting device
CN111860125A (en) * 2020-06-04 2020-10-30 南通科技职业学院 Method for identifying fruit maturity based on machine vision

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
Kang N.B. 等."Design and experiment of synchronization actuator system based on electromagnetism for fresh jujube classifier".《Transactions of the Chinese Society of Agricultural Engineering》.2017,第33卷(第7期),第254-260页. *

Also Published As

Publication number Publication date
CN113390834A (en) 2021-09-14
CN116380814A (en) 2023-07-04

Similar Documents

Publication Publication Date Title
CN113390834B (en) Crisp plum maturity detection method based on visual recognition
AU2007352792B2 (en) Lumber inspection method, device and program
Xu et al. Identification of freezer burn on frozen salmon surface using hyperspectral imaging and computer vision combined with machine learning algorithm
CN106052296A (en) Control method for intelligent fresh-keeping refrigerator capable of identifying kinds of fruits and vegetables
Shearer et al. Color and defect sorting of bell peppers using machine vision
Zhang et al. From hyperspectral imaging to multispectral imaging: Portability and stability of HIS-MIS algorithms for common defect detection
CN103076288B (en) A kind of flesh of fish self-grading device based on computer vision and method
Zulkifli et al. Application of laser-induced backscattering imaging for predicting and classifying ripening stages of “Berangan” bananas
CN106091536A (en) A kind of Intelligent fresh-keeping refrigerator of recognizable fruit and vegerable kind
CN104897581A (en) Method and device for identifying fresh meat, chilled meat, and frozen meat based on hyperspectrum
Huang et al. Evaluating quality of tomato during storage using fusion information of computer vision and electronic nose
CN111239142A (en) Paste appearance defect detection device and method
CN113390833A (en) Crisp plum maturity judging method based on multiple detection modes
Donis-González et al. Color vision system to assess English walnut (Juglans Regia) kernel pellicle color
KR101838729B1 (en) Eotoxicity evaluation analyzer device using microalgae image-analysis program and method thereof
CN108801926A (en) A kind of device and method detected automatically for egg Dan Shuanhuang
Fu et al. Color based classification for berries of Japanese Blue Honeysuckle
Wang et al. Research on the evaluation method of eggshell dark spots based on machine vision
Yao et al. Study on detection method of external defects of potato image in visible light environment
Aniyan et al. An android app scanner for detecting the freshness and age of poultry eggs using image processing
Huang et al. Early detection of bruises on apples using near-infrared hyperspectral image
CN106052297A (en) Control system capable of recognizing types of fruits and vegetables in intelligent food fresh keeping refrigerator
CN112784769B (en) Double-yolk egg online identification system and method based on raspberry pie and machine vision
Sun et al. A digital image method for measuring and analyzing color characteristics of various color scores of beef
CN113433076A (en) Hyperspectral imaging technology-based method for identifying aflatoxin in corn seeds

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant