CN110929787B - Apple objective grading system based on image - Google Patents
Apple objective grading system based on image Download PDFInfo
- Publication number
- CN110929787B CN110929787B CN201911158969.0A CN201911158969A CN110929787B CN 110929787 B CN110929787 B CN 110929787B CN 201911158969 A CN201911158969 A CN 201911158969A CN 110929787 B CN110929787 B CN 110929787B
- Authority
- CN
- China
- Prior art keywords
- image
- apple
- fruit
- feature
- single fruit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 235000013399 edible fruits Nutrition 0.000 claims abstract description 62
- 201000010099 disease Diseases 0.000 claims abstract description 23
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 claims abstract description 23
- 238000000034 method Methods 0.000 claims abstract description 20
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 230000007547 defect Effects 0.000 claims description 14
- 239000011159 matrix material Substances 0.000 claims description 13
- 239000013598 vector Substances 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 6
- 238000012847 principal component analysis method Methods 0.000 claims description 5
- 239000003086 colorant Substances 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 3
- 238000013145 classification model Methods 0.000 claims description 2
- 241000220225 Malus Species 0.000 abstract description 46
- 235000021016 apples Nutrition 0.000 abstract description 20
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 6
- 238000012549 training Methods 0.000 description 4
- 241000238631 Hexapoda Species 0.000 description 3
- 230000006378 damage Effects 0.000 description 3
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 235000014443 Pyrus communis Nutrition 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000011869 dried fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 208000014674 injury Diseases 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Probability & Statistics with Applications (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an image-based apple objective grading method, which comprises the following steps: disease feature extraction is carried out on a single fruit image shot by a camera so as to judge whether the single fruit belongs to an inedible category or not; and carrying out classification feature extraction on the single fruits of the edible categories, and grading the single fruits according to multi-feature indexes generated by the feature extraction results. The invention replaces manpower with computer vision, replaces a lot of labor force and avoids subjectivity and fatigue of manpower; the inedible apples are eliminated before grading work, and a more complete system is realized; the detection classification is carried out by adopting a plurality of characteristic indexes, and compared with the traditional single characteristic, the quality and the efficiency are improved.
Description
Technical Field
The invention relates to the technical field of image recognition and classification, in particular to an image-based apple objective grading system.
Background
With the development of the high and new technology, the combination of the high and new technology and the agricultural field is deeper and deeper, and plays an important promotion role in the development of agriculture. Machine vision technology was proposed as a representative of advanced technology in the 60 s of the 20 th century, and related research is also started in China by the 80 s. In recent years, the machine vision technology also has abundant results in the field of fine agriculture, but China is a large country of world fruit trees, has long cultivation history and abundant resources, has more than 50 fruits and dried fruits, and is one of the countries with earliest provenance and most varieties of world fruit trees.
Apples are fruits with the largest yield in China, the export amount is large, but the export price is low, and the apple quality is correctly classified as the technology for detecting and classifying apples after picking in China is behind and the competitive power in the international market is lacking, so that the apple quality is an important link in the commercialization treatment of apples. Traditional fruit classification relies on manual operation and judgement, and classification speed is low, the precision is low, has great subjectivity, and degree of automation is low, and the human cost also begins to rise, can not satisfy international requirements. Therefore, how to quickly, objectively and accurately classify apples becomes an important research point in the current fruit classification field.
Disclosure of Invention
According to the technical problems of low fruit grading efficiency, poor precision and serious missing detection phenomenon, the image-based apple objective grading system is provided, the defect types of unqualified apples can be detected before grading and eliminated, and then the apples are automatically graded according to the 'fresh apple quality grade requirement' issued by China and combining with various external characteristics of apples.
The invention adopts the following technical means:
an image-based apple objective grading method is characterized by comprising the following steps: disease feature extraction is carried out on a single fruit image shot by a camera so as to judge whether the single fruit belongs to an inedible category or not; and carrying out classification feature extraction on the single fruits of the edible categories, and grading the single fruits according to multi-feature indexes generated by the feature extraction results.
Further, before determining whether the single fruit belongs to the inedible category, further comprises: and calibrating the shooting position of the camera by using a standard reference object, wherein the calibrated shooting position is set to be the shooting distance with the smallest influence on the actual size of the single fruit.
Further, the classifying feature extraction of the single fruits of the edible category comprises extracting size features, fruit shape features, color features and defect features of the single fruits.
Further, the extracting the disease features of the single fruit image shot by the camera includes: and reading an input single-fruit image, converting the single-fruit image into an LAB color space from an RGB color space, classifying color features by using Kmeans clusters, marking each pixel in the image as a result of Kmeans, generating an image segmented according to colors, and obtaining a color space range containing diseases.
Further, the determining whether the single fruit belongs to the inedible category includes: carrying out disease region identification on the color space range containing the disease obtained after segmentation by utilizing a gray level co-occurrence matrix and a Gabor filter, and carrying out dimension reduction on the obtained characteristic parameters by adopting a principal component analysis method; the diseases are distinguished through the characteristic parameters of different diseases, and the characteristic parameters are input into an SVM classifier to generate a classification model.
Further, calculating the diameter of the longitudinal section of the single fruit by using a minimum circumcircle method to serve as an extracted size characteristic; calculating the ratio of the cross-sectional area of a sample of a single fruit to the minimum circumcircle area by using a minimum circumcircle method to obtain an extracted fruit shape characteristic; using the color degree of the red component extracted in the HSV space as the extracted color feature; the area of the defect region obtained by the morphological operation of the image processing is used as the extracted defect feature.
Further, the single fruit image shot by the camera comprises a single fruit image shot by the camera directly and single fruit angle images shot by the camera and reflected by the plane mirror.
Compared with the prior art, the invention has the following advantages:
the invention replaces manpower with computer vision, replaces a lot of labor force and avoids subjectivity and fatigue of manpower; according to the invention, inedible apples are eliminated before grading work, so that a complete system is realized; the invention adopts multiple characteristic indexes to carry out detection classification, and improves the quality and the efficiency compared with the traditional single characteristic; the invention simulates the operation on the actual production line, acquires the whole surface of the apple, and improves the accuracy; the invention classifies according to the standard of fresh apple quality grade requirement, and has more scientificity and basis.
Based on the reasons, the invention can be widely popularized in the field of fruit classification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings may be obtained according to the drawings without inventive effort to a person skilled in the art.
FIG. 1 is a flow chart of the grading method of the present invention.
FIG. 2 is a schematic diagram of a grading device according to an embodiment of the present invention.
Detailed Description
In order that those skilled in the art will better understand the present invention, a technical solution in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in which it is apparent that the described embodiments are only some embodiments of the present invention, not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, shall fall within the scope of the present invention.
As shown in fig. 1, the invention provides an image-based apple objective grading method, which comprises the following steps: disease feature extraction is carried out on a single fruit image shot by a camera so as to judge whether the single fruit belongs to an inedible category or not; and carrying out classification feature extraction on the single fruits of the edible categories, and grading the single fruits according to multi-feature indexes generated by the feature extraction results.
Further, before determining whether the single fruit belongs to the inedible category, further comprises: and calibrating the shooting position of the camera by using a standard reference object, wherein the calibrated shooting position is set to be the shooting distance with the smallest influence on the actual size of the single fruit. Specifically, as one implementation mode of calibration, a USB camera is used to take a photograph of a single coin, and image processing is performed on the photograph: firstly, gray scale processing is carried out, then, after binarization processing, the pixel number occupied by the diameter of the coin is calculated, the actual diameter of the unitary coin is 25mm, and then the ratio of the actual diameter to the pixel number occupied by the diameter can be obtained:
wherein M is the actual diameter length of the coin; n is the number of pixels occupied by the diameter of the coin. Through multiple tests, the measurement of the diameter of the same apple under different heights is calculated, and the effect of the height on the actual size of an object is minimal when the height of the camera is 32 cm.
According to the 'apple and pear standards', once the surface of the apple has rot and insect damage, the apple is not included in the grading standard, so that a large number of rotten apple and insect damage apple data sets are manufactured, and the data sets are segmented by using a Kmeans algorithm, so that a disease area part is extracted. The method specifically comprises the following steps:
a) Reading an input single-effect image, converting the image into an LAB color space from RGB, classifying colors in an 'a' space and an 'b' space by using Kmeans clusters, marking each pixel in the image as a result of Kmeans, generating an image of dividing the image according to the colors, and selecting a color space range containing diseases.
The Kmeans algorithm uses the euclidean distance formula:
the distance between every two pairs of data objects can be calculated through a formula, and clustering is carried out according to the distance to the specified category number K. Taking k data randomly as class centers, and carrying out a class center iteration process:
wherein, center k Is a heart-like body; c (C) k Is the k-th class.
There are generally two conditions for the iteration to terminate: 1) Reaching the appointed iteration times; 2) The heart-like does not change any more.
b) And (3) carrying out disease region identification on the segmented disease region by utilizing a gray level co-occurrence matrix and a Gabor filter, and carrying out dimension reduction on the obtained characteristic parameters by adopting a principal component analysis method to remove redundant information. The diseases are distinguished through the characteristic parameters of different diseases, the characteristic parameters are input into an SVM classifier, and a training model is generated through multiple tests.
The texture features are analyzed by using a gray level co-occurrence matrix and a Gabor filter, wherein the gray level co-occurrence matrix reflects comprehensive information of image textures in the directions, adjacent intervals, variation amplitudes and speeds; the gray level co-occurrence matrix is obtained by counting the states that two pixel points of an image, which keep a certain fixed distance in a certain direction, respectively have a certain gray level.
The elements in the gray level co-occurrence matrix are represented by probability values, namely, the values of the elements are divided by the sum of the elements to obtain normalized values with the elements smaller than 1Namely:
wherein i and j respectively represent the gray scale of two pixels; delta is the spatial positional relationship between two pixels; s is the sum of elements in the gray level co-occurrence matrix.
The surface image texture characteristic value table is three measures, namely energy, entropy and contrast, obtained by an apple surface gray level image based on a gray level co-occurrence matrix:
wherein ASM, ENT, CON is the energy, entropy and contrast of the surface texture features, respectively; l represents the gray level of the image.
In order to acquire complete surface information, the invention additionally considers the direction parameter theta reflecting the spatial position relation and the distance parameter d reflecting the spatial position relation, calculates the gray level co-occurrence matrix under the conditions that theta=0 °, 45 °, 90 ° and 135 °, and d=1, and obtains the mean value and the variance of the obtained characteristic index as the characteristic vector.
At this time, the function of the two-dimensional Gabor transform is expressed as:
parameters affecting the Gabor filter include the center frequency f, the direction angle θ, and the bandwidth of the filter determined by σ. The Gabor filter in the invention adopts 40 Gabor filters composed of 5 center frequencies and 8 directions to process the image, and the sampling interval is set to be pi/8. The Gabor filters with different directions and scales are used for filtering the two-dimensional signals, so that the characteristics of the two-dimensional signals in the frequency domain space can be comprehensively reflected.
The principal component analysis method described above uses a new set of low-dimensional eigenvectors to represent the original samples as accurately as possible, i.e., uses m-dimensional eigenvectors q= [ Q1, Q2,..qm ] T to replace the original n-dimensional eigenvectors p= [ P1, P2,..pn ] T (m < n).
The main component analysis method is adopted to remove the correlation among samples and realize the compression of data, and the dimension reduction method is adopted in the invention to reduce the dimension of the Gabor feature vector of the image from 40 dimension to 10 dimension.
The classification method specifically comprises the following steps: libsvm is used for classification into 3 categories, respectively rot, insect injury and others. The input vectors respectively correspond to the texture feature vectors of the surface images, and training accuracy and class labels are output; training repeatedly by using enough samples to obtain a mode with proper classification; and inputting the texture feature vector of the apple surface image to be detected into the texture feature vector to obtain a final classification result.
Further, the classifying feature extraction of the single fruits of the edible category comprises extracting size features, fruit shape features, color features and defect features of the single fruits. Specifically:
when an apple sample is actually detected, as a preferred implementation mode of the invention, two LED illuminating lamps are placed at two sides of a camera in a closed space by using the device shown in fig. 2; four plane mirrors are symmetrically and obliquely placed so as to reflect the whole surface of the apple; several pictures of apples can be obtained, the pictures are segmented by a physical method, the whole surfaces of the apples can be detected, the pictures are segmented by Kmeans and input into a training model, and whether the apples are rotten fruits, insect-damaged fruits or other apples is judged. If the output is diseased apples, the apples are eliminated.
Further, extracting size characteristics, fruit shape characteristics, color characteristics and defect characteristics of the apples without diseases, and classifying the obtained characteristic standard reference 'fresh apple quality grade requirement' into special grade fruits, first grade fruits, second grade fruits, external fruits and the like.
The extraction size features are that the diameter of the longitudinal section of the apple is calculated by using a minimum circumcircle method, and the fruit shape index is expressed as follows:
wherein S0 is the area of the cross section of the apple sample; s1 is the area of the smallest circumscribed circle.
The color features are that the color of the HSV space is less affected by illumination, so that the color related features are selected to be researched under the HSV space, the H and S spaces are selected to extract the red component, and the glossiness is expressed as follows:
wherein S is the number of pixels on the apple surface; s2 is the pixel count of the red component.
The defect feature utilizes morphological operation of image processing to extract defect area of picture, firstly graying, secondly binarizing, extracting edge, filling it to obtain an edge, finally obtaining difference of two edges, namely defect edge, after filling it to obtain defect pixel number. The area of the defect is expressed as:
S d =N*k
wherein N is the number of defective pixels; k is the ratio of the actual size to the pixel size.
The image-based apple objective grading method disclosed by the invention replaces manpower by computer vision, replaces a large amount of labor force and avoids subjectivity and fatigue of manpower; the inedible apples are eliminated before grading work, and a more complete system is realized; the detection classification is carried out by adopting a plurality of characteristic indexes, so that the quality and the efficiency are improved compared with the traditional single characteristic; the operation on the actual production line is simulated, the whole surface of the apples is obtained, and the accuracy is improved; the fresh apples are classified according to the standard of the quality grade requirement of fresh apples, and are scientific and basic.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit of the invention.
Claims (4)
1. An image-based apple objective grading method is characterized by comprising the following steps:
calibrating the shooting position of the camera by using a standard reference object, wherein the calibrated shooting position is set to be the shooting distance with the least influence on the actual size of the single fruit;
disease feature extraction is carried out on a single fruit image shot by a camera so as to judge whether the single fruit belongs to an inedible category, and the method comprises the following steps:
reading an input single fruit image, converting the single fruit image into an LAB color space from an RGB color space, classifying color features by using Kmeans clusters, marking each pixel in the image as a Kmeans result, generating an image segmented by colors to obtain a color space range containing diseases, carrying out disease area identification on the segmented color space range containing the diseases by using a gray level symbiotic matrix and a Gabor filter, carrying out dimensionality reduction on the obtained feature parameters by using a principal component analysis method to distinguish diseases by using the feature parameters of different diseases, inputting the feature parameters into an SVM classifier to generate a classification model, carrying out statistics on the condition that two pixel points of the image with a certain fixed distance in a certain direction respectively have a certain gray level, obtaining elements in the gray level symbiotic matrix by using probability values, obtaining the probability values by dividing each element value by the sum of each element,
obtaining a surface image texture characteristic value through an apple surface gray level image based on a gray level co-occurrence matrix, wherein the surface image texture characteristic value comprises three measures of energy, entropy and contrast,
taking the direction parameter theta representing the spatial position relation and the distance parameter d representing the spatial position relation into consideration, calculating gray level co-occurrence matrix under the conditions that theta=0 °, 45 °, 90 ° and 135 ° and d=1, obtaining the mean value and variance of the obtained characteristic indexes as characteristic vectors,
disease region identification was performed based on the following two-dimensional Gabor filter:
wherein f is the center frequency, θ is the direction angle, σ is the bandwidth of the filter, x is the pixel abscissa, and y is the pixel ordinate;
reducing the Gabor feature vector dimension of the image from 40 to 10 by adopting a principal component analysis method;
and carrying out classification feature extraction on the single fruits of the edible categories, and grading the single fruits according to multi-feature indexes generated by the feature extraction results.
2. The image-based apple objective grading method according to claim 1, wherein the classifying feature extraction of the single fruits of the edible category comprises extracting size features, fruit shape features, color features and defect features of the single fruits.
3. The image-based apple objective grading method according to claim 2, wherein,
calculating the diameter of the longitudinal section of the single fruit by using a minimum circumcircle method to serve as an extracted size characteristic;
calculating the ratio of the cross-sectional area of a sample of a single fruit to the minimum circumcircle area by using a minimum circumcircle method to obtain an extracted fruit shape characteristic;
using the color degree of the red component extracted in the HSV space as the extracted color feature;
the area of the defect region obtained by the morphological operation of the image processing is used as the extracted defect feature.
4. The image-based apple objective grading method according to claim 1, wherein the single fruit images shot by the camera include single fruit images shot directly by the camera and single fruit angle images shot by the camera and reflected by the plane mirror.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911158969.0A CN110929787B (en) | 2019-11-22 | 2019-11-22 | Apple objective grading system based on image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911158969.0A CN110929787B (en) | 2019-11-22 | 2019-11-22 | Apple objective grading system based on image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110929787A CN110929787A (en) | 2020-03-27 |
CN110929787B true CN110929787B (en) | 2024-02-06 |
Family
ID=69850836
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911158969.0A Active CN110929787B (en) | 2019-11-22 | 2019-11-22 | Apple objective grading system based on image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110929787B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112556606A (en) * | 2020-12-24 | 2021-03-26 | 宁夏农林科学院农业经济与信息技术研究所(宁夏农业科技图书馆) | Self-propelled wolfberry fruit actual measurement method and device based on binocular vision |
TWI830982B (en) * | 2021-01-23 | 2024-02-01 | 鴻海精密工業股份有限公司 | Image recognition method based on texture classification, electronic device, and storage medium |
CN113887389A (en) * | 2021-09-29 | 2022-01-04 | 湖南省博世康中医药有限公司 | Quality inspection and classification method for traditional Chinese medicine decoction pieces based on image recognition |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012039597A2 (en) * | 2010-09-23 | 2012-03-29 | Universiti Putra Malaysia | Fruit ripeness grading system |
CN110148122A (en) * | 2019-05-17 | 2019-08-20 | 南京东奇智能制造研究院有限公司 | Apple presentation quality stage division based on deep learning |
CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
-
2019
- 2019-11-22 CN CN201911158969.0A patent/CN110929787B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2012039597A2 (en) * | 2010-09-23 | 2012-03-29 | Universiti Putra Malaysia | Fruit ripeness grading system |
CN110148122A (en) * | 2019-05-17 | 2019-08-20 | 南京东奇智能制造研究院有限公司 | Apple presentation quality stage division based on deep learning |
CN110276386A (en) * | 2019-06-11 | 2019-09-24 | 济南大学 | A kind of apple grading method and system based on machine vision |
Non-Patent Citations (2)
Title |
---|
李聪 等."基于计算机视觉的苹果自动分级方法研究".《计算机仿真》.2012,第29卷(第29期),第293-296页. * |
杜传来 等.《果蔬贮藏保鲜实用技术》.合肥:安徽大学出版社,2014,第24-26页. * |
Also Published As
Publication number | Publication date |
---|---|
CN110929787A (en) | 2020-03-27 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bhargava et al. | Fruits and vegetables quality evaluation using computer vision: A review | |
Mazen et al. | Ripeness classification of bananas using an artificial neural network | |
Sahu et al. | Defect identification and maturity detection of mango fruits using image analysis | |
CN110929787B (en) | Apple objective grading system based on image | |
CN109002851B (en) | Fruit classification method based on image multi-feature fusion and application | |
Hong et al. | Comparative study on vision based rice seed varieties identification | |
Luo et al. | Classification of weed seeds based on visual images and deep learning | |
Rahamathunnisa et al. | Vegetable disease detection using k-means clustering and svm | |
AlShahrani et al. | Automated system for crops recognition and classification | |
Cai et al. | Nondestructive gender identification of silkworm cocoons using X-ray imaging with multivariate data analysis | |
CN108020556A (en) | A kind of online damage testing sorting technique of corn seed based on machine vision | |
CN113222959B (en) | Fresh jujube wormhole detection method based on hyperspectral image convolutional neural network | |
Ünal et al. | Classification of hazelnut kernels with deep learning | |
CN103528967A (en) | Hyperspectral image based overripe Lonicera edulis fruit identification method | |
Zhang et al. | Grasping point detection of randomly placed fruit cluster using adaptive morphology segmentation and principal component classification of multiple features | |
CN109975292A (en) | A kind of atlantic salmon and rainbow trout method for quick identification based on machine vision | |
Yro et al. | Cocoa beans fermentation degree assessment for quality control using machine vision and multiclass svm classifier | |
Wu et al. | Fast location and classification of small targets using region segmentation and a convolutional neural network | |
Janardhana et al. | Computer aided inspection system for food products using machine vision—a review | |
Ji et al. | Apple color automatic grading method based on machine vision | |
Shweta et al. | External feature based quality evaluation of Tomato using K-means clustering and support vector classification | |
Auleria et al. | A review on KN earest neighbour based classification for object recognition | |
CN116229182A (en) | Small particle coffee defect green bean detection method based on feature fusion | |
Varjão et al. | Citrus fruit quality classification using support vector machines | |
Sreekanth et al. | Fruit detection using improved K-means algorithm |
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 |