CN111161237A - Fruit and vegetable surface quality detection method, storage medium and sorting device thereof - Google Patents
Fruit and vegetable surface quality detection method, storage medium and sorting device thereof Download PDFInfo
- Publication number
- CN111161237A CN111161237A CN201911376017.6A CN201911376017A CN111161237A CN 111161237 A CN111161237 A CN 111161237A CN 201911376017 A CN201911376017 A CN 201911376017A CN 111161237 A CN111161237 A CN 111161237A
- Authority
- CN
- China
- Prior art keywords
- fruit
- vegetable
- image
- image data
- information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 45
- 235000012055 fruits and vegetables Nutrition 0.000 title claims abstract description 37
- 230000007547 defect Effects 0.000 claims abstract description 74
- 238000013528 artificial neural network Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims description 49
- 238000012545 processing Methods 0.000 claims description 26
- 235000013399 edible fruits Nutrition 0.000 claims description 14
- 238000005457 optimization Methods 0.000 claims description 14
- 238000007689 inspection Methods 0.000 claims description 11
- 235000013311 vegetables Nutrition 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 2
- 230000000873 masking effect Effects 0.000 claims 1
- 238000013461 design Methods 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C5/00—Sorting according to a characteristic or feature of the articles or material being sorted, e.g. by control effected by devices which detect or measure such characteristic or feature; Sorting by manually actuated devices, e.g. switches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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
- G06V10/56—Extraction of image or video features relating to colour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B07—SEPARATING SOLIDS FROM SOLIDS; SORTING
- B07C—POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING
- B07C2501/00—Sorting according to a characteristic or feature of the articles or material to be sorted
- B07C2501/009—Sorting of fruit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30188—Vegetation; Agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Sorting Of Articles (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a fruit and vegetable surface quality detection method, a storage medium and a sorting device thereof, which comprise the following steps: s1, acquiring image data of the surface of the fruit and vegetable; s2, detecting the surface defect information in the image data, judging the obvious degree of the surface defect information, and classifying each piece of surface defect information according to the obvious degree; s3, selecting and carrying out the step S4 or the step S5 according to the classification condition; s4, analyzing the surface defect information based on the feature matching identification model to obtain first defect type information; s5, optimizing the image data, and then obtaining second defect type information according to the surface defect information based on the neural network identification model; s6, integrating the first defect type information and/or the second defect type information to output a detection result; reasonable classification is carried out in this design, guarantees the accuracy of whole result, improves holistic detection rate.
Description
Technical Field
The invention relates to the field of fruit and vegetable sorting, in particular to a fruit and vegetable surface quality inspection method, a storage medium and a sorting device thereof.
Background
The defect of the surface of the fruit seriously affects the quality of the fruit, and the problem of accurately and quickly sorting the fruit quality is always faced by enterprises. The traditional manual detection has the defects of high cost, easy fatigue of detection personnel, easy flaw and missed detection and the like.
The traditional machine detection has long running time and low accuracy, and is generally divided into two approaches: the method comprises the steps of identifying an image by feature matching based on the traditional image processing technology, detecting flaws by utilizing image binarization processing and morphological processing, but the steps of identifying the image by feature matching have poor compatibility and expandability, and the flaws on the surface of fruits and vegetables have various colors, variable shapes and complex textures, so that the image cannot be processed well to obtain an accurate result only by the traditional image processing by feature matching; the other method is a deep learning detection method based on a neural network, the extracted features have higher generalization performance than the artificially set features, the method can be well suitable for detection of the surfaces of fruits and vegetables, and the method is wide in applicability, but the parameter quantity and the calculation quantity in the neural network are huge, so that the training is very slow, the storage is very inconvenient, the complexity is high, the development period is long, the requirement on hardware is high, the cost is high, and meanwhile, in part of image data with unobvious flaws, the judgment can be influenced by too many interference factors existing in the image data.
Disclosure of Invention
The invention aims to solve at least one of the technical problems in the prior art, and provides a fruit and vegetable surface quality inspection method, a storage medium and a sorting device thereof.
The technical scheme adopted by the invention is as follows:
a fruit and vegetable surface quality inspection method comprises the following steps: s1, acquiring image data of the surface of the fruit and vegetable; s2, detecting the surface defect information in the image data, judging the obvious degree of the surface defect information, and classifying each piece of surface defect information according to the obvious degree; s3, selecting and carrying out the step S4 or the step S5 according to the classification condition; s4, analyzing the surface defect information based on the feature matching identification model to obtain first defect type information; s5, optimizing the image data, and then obtaining second defect type information according to the surface defect information based on the neural network identification model; and S6, integrating the first defect type information and/or the second defect type information to output a detection result.
In step S5, the image data optimization process includes an image resizing process and/or an image gradation conversion process and/or an image denoising process and/or an image enhancement process.
The image data optimization processing comprises image enhancement processing, and the image data is subjected to image enhancement processing by an unsharp mask method.
The image data optimization processing comprises image denoising processing, and the image denoising processing is carried out through a median filtering method.
In step S4, feature information of the surface defect information is extracted, where the feature information includes color features and/or shape features and/or texture features, and the extracted feature information and preset feature points representing defect categories are subjected to feature matching identification to obtain first defect type information.
The feature information includes color features, H, S, V numerical values of the image are obtained through a spatial three-channel splitting algorithm, distances between the color histogram features are obtained through a calculation histogram intersection algorithm, and the color features are extracted from H, S, V numerical values of the image and the distances between the color histogram features in step S4.
The feature information comprises shape features, and the shape features are extracted through a contour template detection algorithm.
The characteristic information comprises texture characteristics, and the texture characteristics are extracted by a Gibbs random field model method.
The fruit and vegetable surface quality detection method provided by the embodiment of the invention at least has the following beneficial effects:
the fruit and vegetable surface quality inspection method comprises the steps of obtaining image data of the surface of a fruit and vegetable, judging the obvious degree (size, color depth, outline and the like) from surface defect information presented on the image data, distinguishing the surface defect information through the obvious degree, and carrying out identification analysis on the surface defect information with the larger obvious degree based on a feature matching identification model to obtain first defect type information, wherein the identification step efficiency of the feature matching identification model is high, and the detection speed is high; the image data is optimized aiming at the surface defect information with small obvious degree, the surface defect information with small obvious degree is deeply and obviously displayed, the identification analysis is carried out based on the neural network identification model, the second defect type information is obtained, the identification step based on the neural network identification model is high in precision and high in self-adaption degree, the design is reasonably classified, the characteristic matching identification model can be used for quickly detecting with large obvious degree, the detection result can also reach high precision, after the surface defect information with large obvious degree is distinguished, the neural network identification model is used after the image optimization processing with small obvious degree, the accuracy of the whole result is ensured, all the surface defect information is not required to be identified by the neural network identification model, and the whole detection rate is improved through reasonable distribution.
The embodiment of the invention also discloses a storage medium which stores the fruit and vegetable surface quality inspection method disclosed by any one of the embodiments and can be read and operated by a computer.
The storage medium according to the embodiment of the invention has at least the following beneficial effects:
according to the invention, the storage medium and the computer acquire the image data of the surfaces of the fruits and vegetables for reasonable classification, the image data with a large obvious degree can be rapidly detected by using the feature matching identification model, the detection result can also reach higher precision, after the surface defect information with a large obvious degree is distinguished, the image optimization processing with a small obvious degree is carried out, and then the neural network identification model is used, so that the accuracy of the whole result is ensured, all the surface defect information is not required to be identified by adopting the neural network identification model, and the whole detection rate is reasonably distributed and improved.
The embodiment of the invention also discloses a sorting device which comprises a camera module, a sorting module and a main control module which is electrically connected with the camera module and the sorting module respectively, wherein the camera module is used for acquiring the image data of the surface of the fruit and vegetable to be detected, the main control module is used for obtaining the detection result according to the fruit and vegetable surface quality detection method disclosed by any one embodiment, and the sorting module is controlled to sort the fruit and vegetable according to the detection result.
The sorting device according to the embodiment of the invention has at least the following beneficial effects:
the sorting device can acquire the images of the fruits and the vegetables, obtain the detection result through quick and accurate analysis, generate the control signal according to the detection result, control the sorting module to sort the fruits and the vegetables, do not need manual sorting, reduce the cost and greatly improve the sorting speed and the accuracy.
Drawings
The following further describes embodiments of the present invention with reference to the drawings.
FIG. 1 is a flow chart of an embodiment of the fruit and vegetable surface quality inspection method of the present invention.
Fig. 2 is a schematic structural diagram of the sorting device of the invention.
Detailed Description
Reference will now be made in detail to the present preferred embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to like elements throughout.
In the description of the present invention, it should be understood that the orientation or positional relationship referred to in the description of the orientation, such as the upper, lower, front, rear, left, right, etc., is based on the orientation or positional relationship shown in the drawings, and is only for convenience of description and simplification of description, and does not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present invention.
In the description of the present invention, the meaning of a plurality of means is one or more, the meaning of a plurality of means is two or more, and larger, smaller, larger, etc. are understood as excluding the number, and larger, smaller, inner, etc. are understood as including the number. If the first and second are described for the purpose of distinguishing technical features, they are not to be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated or implicitly indicating the precedence of the technical features indicated.
In the description of the present invention, unless otherwise explicitly limited, terms such as arrangement, installation, connection and the like should be understood in a broad sense, and those skilled in the art can reasonably determine the specific meanings of the above terms in the present invention in combination with the specific contents of the technical solutions.
As shown in figure 1, the method for detecting the surface quality of the fruits and vegetables comprises the following steps: s1, acquiring image data of the surface of the fruit and vegetable; s2, detecting the surface defect information in the image data, judging the obvious degree of the surface defect information, and classifying each piece of surface defect information according to the obvious degree; s3, selecting and carrying out the step S4 or the step S5 according to the classification condition; s4, analyzing the surface defect information based on the feature matching identification model to obtain first defect type information; s5, optimizing the image data, and then obtaining second defect type information according to the surface defect information based on the neural network identification model; and S6, integrating the first defect type information and/or the second defect type information to output a detection result.
In step S2, the image data is preliminarily scanned to obtain surface defect information, and the determination of the apparent degree may be to determine the size, color depth, outline, etc. of the surface defect, to photograph the image data of the surface of the fruit or vegetable, where there may be a plurality of surface defect information, to preprocess the image data, to extract the color, outline, occupied area, etc. parameters, and to compare them with the preset contrast value, to obtain the defect degree.
After the surface defect information is distinguished through the obvious degree, the surface defect information with the larger obvious degree is identified and analyzed based on the feature matching identification model to obtain first defect type information, and the identification step of the feature matching identification model is high in efficiency and high in detection speed; the image data is optimized aiming at the surface defect information with small obvious degree, the surface defect information with small obvious degree is deeply and obviously displayed, the identification analysis is carried out based on the neural network identification model, the second defect type information is obtained, the identification step based on the neural network identification model is high in precision and high in self-adaption degree, the design is reasonably classified, the characteristic matching identification model can be used for quickly detecting with large obvious degree, the detection result can also reach high precision, after the surface defect information with large obvious degree is distinguished, the neural network identification model is used after the image optimization processing with small obvious degree, the accuracy of the whole result is ensured, all the surface defect information is not required to be identified by the neural network identification model, and the whole detection rate is improved through reasonable distribution.
In certain embodiments, the neural network recognition model may employ the neural network of YOLO v3 for target flaw detection.
The YOLO v3 neural network has high detection accuracy and high speed, the accuracy can be improved by setting the learning rate, inputting the size of a picture and the like, the number of network layers and the number of iterations can be trimmed according to specific requirements, the accuracy is further improved, and a corresponding weight file is obtained through training to obtain a trained neural network model.
In step S5, the image data optimization process includes an image resizing process, an image gray-scale conversion process, an image denoising process, and an image enhancement process.
In some embodiments, the image data optimization process may include an image resizing process, an image grayscale transformation process, an image denoising process, and an image enhancement process, so as to enhance the contrast of the image and improve the accuracy of image segmentation and the accuracy of image recognition. .
The image data optimization processing comprises image enhancement processing, the image data is subjected to image enhancement processing through an unsharp mask method, high-frequency components of the image can be highlighted through the unsharp mask method, low-frequency components of the image are reduced, and therefore the image becomes clearer.
The image data optimization processing comprises image denoising processing, the image denoising processing is carried out through a median filtering method, and the sorted median pixels replace original pixels through a filter, so that the influence of impulse noise is effectively inhibited.
In step S4, feature information of the surface defect information is extracted, where the feature information includes color features and/or shape features and/or texture features, and the extracted feature information and preset feature points representing defect categories are subjected to feature matching identification to obtain first defect type information.
The feature information includes color features, H, S, V numerical values of the image are obtained through a spatial three-channel splitting algorithm, distances between the color histogram features are obtained through a calculation histogram intersection algorithm, and the color features are extracted from H, S, V numerical values of the image and the distances between the color histogram features in step S4.
The feature information includes shape features, which are extracted by a contour template detection algorithm.
The characteristic information comprises texture characteristics, and the texture characteristics are extracted by a Gibbs random field model method.
And finally analyzing and identifying the defect type of the surface defect information by calculating the size, direction and scale information of the characteristic points.
The embodiment of the invention also discloses a storage medium which stores the fruit and vegetable surface quality inspection method disclosed by any one of the embodiments and can be read and operated by a computer.
According to the invention, the storage medium and the computer acquire the image data of the surfaces of the fruits and vegetables for reasonable classification, the image data with a large obvious degree can be rapidly detected by using the feature matching identification model, the detection result can also reach higher precision, after the surface defect information with a large obvious degree is distinguished, the image optimization processing with a small obvious degree is carried out, and then the neural network identification model is used, so that the accuracy of the whole result is ensured, all the surface defect information is not required to be identified by adopting the neural network identification model, and the whole detection rate is reasonably distributed and improved.
The embodiment of the invention also discloses a sorting device, as shown in fig. 2, the sorting device comprises a camera module 1, a sorting module 2 and a main control module 3 which is respectively electrically connected with the camera module 1 and the sorting module 2, the camera module 1 obtains image data of the surface of the fruit and vegetable to be detected, the main control module 3 obtains a detection result according to the fruit and vegetable surface quality detection method disclosed by any one embodiment, and the sorting module 2 is controlled to sort the fruit and vegetable according to the detection result.
Wherein, camera module 1 can be a plurality of camera, obtains the image data on vegetables and fruits surface through the shooting angle of difference, and the image data homoenergetic of a plurality of shooting angles can regard as the basis of letter sorting, and host system 3 can include CPU, MCU or PLC's main control chip and the peripheral circuit of chip.
And sorting module 2 can include the multiaxis manipulator, can extract vegetables and fruits to receive the control signal's that the testing result reachs control, classify vegetables and fruits to different regions.
The sorting device can acquire the images of the fruits and the vegetables, obtain the detection result through quick and accurate analysis, generate the control signal according to the detection result, control the sorting module to sort the fruits and the vegetables, do not need manual sorting, reduce the cost and greatly improve the sorting speed and the accuracy.
It is readily understood by those skilled in the art that the above-described preferred modes can be freely combined and superimposed without conflict.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge of those skilled in the art without departing from the gist of the present invention.
Claims (10)
1. The method for detecting the surface quality of the fruits and vegetables is characterized by comprising the following steps:
s1, acquiring image data of the surface of the fruit and vegetable;
s2, detecting the surface defect information in the image data, judging the obvious degree of the surface defect information, and classifying each piece of surface defect information according to the obvious degree;
s3, selecting and carrying out the step S4 or the step S5 according to the classification condition;
s4, analyzing the surface defect information based on the feature matching identification model to obtain first defect type information;
s5, optimizing the image data, and then obtaining second defect type information according to the surface defect information based on the neural network identification model;
and S6, integrating the first defect type information and/or the second defect type information to output a detection result.
2. The fruit and vegetable surface quality inspection method according to claim 1, wherein in step S5, the image data optimization process includes an image size adjustment process and/or an image gray scale transformation process and/or an image denoising process and/or an image enhancement process.
3. The fruit and vegetable surface quality inspection method according to claim 2, wherein the image data optimization processing comprises image enhancement processing, and the image data is subjected to image enhancement processing by an unsharp masking method.
4. The fruit and vegetable surface quality inspection method according to claim 2, wherein the image data optimization processing comprises image denoising processing, and the image denoising processing is performed by a median filtering method.
5. The fruit and vegetable surface quality inspection method according to claim 1, wherein in step S4, feature information of the surface defect information is extracted, the feature information includes color features and/or shape features and/or texture features, and the extracted feature information and preset feature points representing defect categories are subjected to feature matching identification to obtain first defect type information.
6. The fruit and vegetable surface quality detection method according to claim 5, characterized in that: the feature information includes color features, H, S, V numerical values of the image are obtained through a spatial three-channel splitting algorithm, distances between the color histogram features are obtained through a calculation histogram intersection algorithm, and the color features are extracted from H, S, V numerical values of the image and the distances between the color histogram features in step S4.
7. The fruit and vegetable surface quality detection method according to claim 5, characterized in that: the feature information comprises shape features, and the shape features are extracted through a contour template detection algorithm.
8. The fruit and vegetable surface quality detection method according to claim 5, characterized in that: the characteristic information comprises texture characteristics, and the texture characteristics are extracted by a Gibbs random field model method.
9. A storage medium storing a method for inspecting the surface quality of fruits and vegetables according to any one of claims 1 to 8, and capable of being read and operated by a computer.
10. A sorting device, comprising a camera module, a sorting module and a main control module electrically connected to the camera module and the sorting module respectively, wherein the camera module obtains image data of the surface of a fruit or vegetable to be inspected, the main control module obtains a detection result according to the method for inspecting the surface quality of the fruit or vegetable according to any one of claims 1 to 8, and controls the sorting module to sort the fruit or vegetable according to the detection result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911376017.6A CN111161237A (en) | 2019-12-27 | 2019-12-27 | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911376017.6A CN111161237A (en) | 2019-12-27 | 2019-12-27 | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111161237A true CN111161237A (en) | 2020-05-15 |
Family
ID=70558462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911376017.6A Pending CN111161237A (en) | 2019-12-27 | 2019-12-27 | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111161237A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753794A (en) * | 2020-06-30 | 2020-10-09 | 创新奇智(成都)科技有限公司 | Fruit quality classification method and device, electronic equipment and readable storage medium |
| CN112668445A (en) * | 2020-12-24 | 2021-04-16 | 南京泓图人工智能技术研究院有限公司 | Vegetable type detection and identification method based on yolov5 |
| CN112926438A (en) * | 2021-02-22 | 2021-06-08 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
| CN113781456A (en) * | 2021-09-16 | 2021-12-10 | 欧冶云商股份有限公司 | Steel surface defect detection method and equipment based on artificial intelligence image recognition |
| CN114354628A (en) * | 2022-01-05 | 2022-04-15 | 威海若维信息科技有限公司 | Root agricultural product defect detection method based on machine vision |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9212449D0 (en) * | 1991-06-11 | 1992-07-22 | Sumitomo Heavy Industries | Determination device for use in sorting objects,especially fruits |
| CN102722720A (en) * | 2012-05-25 | 2012-10-10 | 苏州大学 | Video background extraction method based on hue-saturation-value (HSV) space on-line clustering |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
| CN105067531A (en) * | 2014-12-31 | 2015-11-18 | 广西师范学院 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
| CN106951912A (en) * | 2017-02-15 | 2017-07-14 | 海尔优家智能科技（北京）有限公司 | A kind of method for building up of fruits and vegetables cosmetic variation identification model and recognition methods |
| CN107239514A (en) * | 2017-05-19 | 2017-10-10 | 邓昌顺 | A kind of plants identification method and system based on convolutional neural networks |
| CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
| CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
| CN110434090A (en) * | 2019-08-23 | 2019-11-12 | 中山德著智能科技有限公司 | A kind of carrot surface flaw detecting method |
-
2019
- 2019-12-27 CN CN201911376017.6A patent/CN111161237A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB9212449D0 (en) * | 1991-06-11 | 1992-07-22 | Sumitomo Heavy Industries | Determination device for use in sorting objects,especially fruits |
| CN102722720A (en) * | 2012-05-25 | 2012-10-10 | 苏州大学 | Video background extraction method based on hue-saturation-value (HSV) space on-line clustering |
| CN105067531A (en) * | 2014-12-31 | 2015-11-18 | 广西师范学院 | Mango quality nondestructive detection method and mango quality nondestructive detection apparatus |
| CN104992449A (en) * | 2015-08-06 | 2015-10-21 | 西安冉科信息技术有限公司 | Information identification and surface defect on-line detection method based on machine visual sense |
| CN106951912A (en) * | 2017-02-15 | 2017-07-14 | 海尔优家智能科技（北京）有限公司 | A kind of method for building up of fruits and vegetables cosmetic variation identification model and recognition methods |
| CN107239514A (en) * | 2017-05-19 | 2017-10-10 | 邓昌顺 | A kind of plants identification method and system based on convolutional neural networks |
| CN108734710A (en) * | 2018-06-14 | 2018-11-02 | 厦门理工学院 | A kind of intelligence fruits and vegetables selection method |
| CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
| CN110434090A (en) * | 2019-08-23 | 2019-11-12 | 中山德著智能科技有限公司 | A kind of carrot surface flaw detecting method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111753794A (en) * | 2020-06-30 | 2020-10-09 | 创新奇智(成都)科技有限公司 | Fruit quality classification method and device, electronic equipment and readable storage medium |
| CN111753794B (en) * | 2020-06-30 | 2024-02-27 | 创新奇智(成都)科技有限公司 | Fruit quality classification method, device, electronic equipment and readable storage medium |
| CN112668445A (en) * | 2020-12-24 | 2021-04-16 | 南京泓图人工智能技术研究院有限公司 | Vegetable type detection and identification method based on yolov5 |
| CN112926438A (en) * | 2021-02-22 | 2021-06-08 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
| CN112926438B (en) * | 2021-02-22 | 2024-04-05 | 深圳中科飞测科技股份有限公司 | Detection method and device, detection equipment and storage medium |
| CN113781456A (en) * | 2021-09-16 | 2021-12-10 | 欧冶云商股份有限公司 | Steel surface defect detection method and equipment based on artificial intelligence image recognition |
| CN114354628A (en) * | 2022-01-05 | 2022-04-15 | 威海若维信息科技有限公司 | Root agricultural product defect detection method based on machine vision |
| CN114354628B (en) * | 2022-01-05 | 2023-10-27 | 威海若维信息科技有限公司 | Rhizome agricultural product defect detection method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111161237A (en) | Fruit and vegetable surface quality detection method, storage medium and sorting device thereof | |
| CN108520274B (en) | High-reflectivity surface defect detection method based on image processing and neural network classification | |
| CN108765412B (en) | Strip steel surface defect classification method | |
| CN111862064B (en) | Silver wire surface flaw identification method based on deep learning | |
| CN109978822B (en) | Banana maturity judging modeling method and judging method based on machine vision | |
| Liming et al. | Automated strawberry grading system based on image processing | |
| CN109509187B (en) | Efficient inspection algorithm for small defects in large-resolution cloth images | |
| CN111325713A (en) | Wood defect detection method, system and storage medium based on neural network | |
| CN107230203B (en) | Casting defect identification method based on human eye visual attention mechanism | |
| CN107607554A (en) | A kind of Defect Detection and sorting technique of the zinc-plated stamping parts based on full convolutional neural networks | |
| CN115082683A (en) | Injection molding defect detection method based on image processing | |
| CN103593670A (en) | Copper sheet and strip surface defect detection method based on-line sequential extreme learning machine | |
| CN110210448B (en) | Intelligent face skin aging degree identification and evaluation method | |
| CN113505865B (en) | Sheet surface defect image recognition processing method based on convolutional neural network | |
| CN116188475B (en) | Intelligent control method, system and medium for automatic optical detection of appearance defects | |
| CN111582359B (en) | Image identification method and device, electronic equipment and medium | |
| CN112862744B (en) | Intelligent detection method for internal defects of capacitor based on ultrasonic image | |
| Wah et al. | Analysis on feature extraction and classification of rice kernels for Myanmar rice using image processing techniques | |
| CN111160451A (en) | Flexible material detection method and storage medium thereof | |
| CN113177924A (en) | Industrial production line product flaw detection method | |
| CN113256624A (en) | Continuous casting round billet defect detection method and device, electronic equipment and readable storage medium | |
| CN113435460A (en) | Method for identifying brilliant particle limestone image | |
| CN108073940A (en) | A kind of method of 3D object instance object detections in unstructured moving grids | |
| CN114972230A (en) | Method and system for detecting defects of circuit board on production line | |
| CN116559111A (en) | Sorghum variety identification method based on hyperspectral imaging technology |
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 | ||
| AD01 | Patent right deemed abandoned | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20231110 |