CN109856345A - A kind of fruit quality recognition methods and system - Google Patents
A kind of fruit quality recognition methods and system Download PDFInfo
- Publication number
- CN109856345A CN109856345A CN201910183460.5A CN201910183460A CN109856345A CN 109856345 A CN109856345 A CN 109856345A CN 201910183460 A CN201910183460 A CN 201910183460A CN 109856345 A CN109856345 A CN 109856345A
- Authority
- CN
- China
- Prior art keywords
- fruit
- quality
- history
- parameter
- tested
- 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.)
- Withdrawn
Links
Landscapes
- Investigating Or Analyzing Materials By The Use Of Ultrasonic Waves (AREA)
Abstract
The invention discloses a kind of fruit quality recognition methods and systems.The fruit quality recognition methods includes: to obtain the history fruit parameter and history fruit quality of various fruits；The history fruit parameter includes fruit type, fruit volume, smell, hardness, color and beats echo；The history fruit quality includes high-quality quality, mean quality and low quality；It is input with the history fruit parameter, is output with the history fruit quality, establishes fruit quality identification model；Obtain the tested fruit parameter of tested fruit；The tested fruit parameter is input to the fruit quality identification model, determines the first fruit quality of the tested fruit.Fruit quality accuracy of identification can be improved using fruit quality recognition methods provided by the present invention and system.
Description
Technical field
The present invention relates to fruit qualities to identify field, more particularly to a kind of fruit quality recognition methods and system.
Background technique
With the raising of human life quality, the requirement for quality of food is also higher and higher, and fruit is as a variety of dimensions
The source of nutrition of raw element, fruit quality is more paid attention to, when fruit is assembled at case, it is generally the case that can according to fruit size with
And fruit mature condition carries out classification assembly, fruit head is big and a height of quality fruit of maturity, fruit head it is big but at
The low fruit of ripe degree or the fruit that fruit head is small but maturity is high are the fruit of medium quality, and fruit head is small and maturity is low
Fruit be ropy fruit；The different fruit price of fruit quality is determined according to the difference of fruit quality.
Currently, carrying out classification assembly to fruit according to fruit quality, but this manual sort assembles using manual type
Mode is time-consuming and laborious, and since the subjective consciousness of people is strong and human eye can not directly determine the mature condition of fruit, Wu Fajing
Really identification fruit quality, nicety of grading are low.
Summary of the invention
The object of the present invention is to provide a kind of fruit quality recognition methods and systems, can not accurately be known with solving fruit quality
Other problem.
To achieve the above object, the present invention provides following schemes:
A kind of fruit quality recognition methods, comprising:
Obtain the history fruit parameter and history fruit quality of various fruits；The history fruit parameter includes fruits
Type, fruit volume, smell, hardness, color and beat echo；The history fruit quality includes high-quality quality, mean quality
And low quality；
It is input with the history fruit parameter, is output with the history fruit quality, establishes fruit quality identification mould
Type；
Obtain the tested fruit parameter of tested fruit；
The tested fruit parameter is input to the fruit quality identification model, determines the first water of the tested fruit
Fruit quality.
Optionally, it is described with the history fruit parameter be input, with the history fruit quality be output, establish fruit
Quality Identification model, specifically includes:
It is input with the history fruit parameter, is output with the history fruit quality, is built using convolutional neural networks
Vertical fruit quality identification model.
Optionally, described that the tested fruit parameter is input to the fruit quality identification model, it determines described tested
Before first fruit quality of fruit, further includes:
Judge fruit type in the tested fruit parameter whether with the fruit type phase in the history fruit parameter
Together, the first judging result is obtained；
If fruit type and the history fruit that first judging result is expressed as in the tested fruit parameter are joined
Fruit type in number is identical, and the first fruit quality of the tested fruit is determined according to the fruit quality identification model；
If first judging result be expressed as the fruit type in the tested fruit parameter not with the history fruit
Fruit type in parameter is identical, obtains the sugar content of the tested fruit；
The maturity of the tested fruit is determined according to the sugar content of the tested fruit；
Judge that the maturity whether in maturity threshold range, obtains the second judging result；
If second judging result is expressed as the maturity in maturity threshold range, according to described tested
Fruit volume in fruit parameter determines the second fruit quality.
Optionally, it after the fruit volume according in the tested fruit parameter determines the second fruit quality, also wraps
It includes:
Fruit type not identical with the fruit type in the history fruit parameter is added to the history fruit parameter,
Obtain updated history fruit parameter；
Second fruit quality is added to the history fruit quality, obtains updated history fruit quality；
Using the updated history fruit parameter as input, using the updated history fruit quality as defeated
Out, fruit quality identification model is re-established.
A kind of fruit quality identifying system, comprising:
History fruit parameter and history fruit quality obtain module, for obtain the history fruit parameter of various fruits with
And history fruit quality；The history fruit parameter includes fruit type, fruit volume, smell, hardness, color and beats back
Sound；The history fruit quality includes high-quality quality, mean quality and low quality；
Fruit quality identification model establishes module, for being input with the history fruit parameter, with the history fruit
Quality is output, establishes fruit quality identification model；
Tested fruit parameter acquisition module, for obtaining the tested fruit parameter of tested fruit；
First the first determining module of fruit quality is identified for the tested fruit parameter to be input to the fruit quality
Model determines the first fruit quality of the tested fruit.
Optionally, the fruit quality identification model is established module and is specifically included:
Fruit quality identification model establishes unit, for being input with the history fruit parameter, with the history fruit
Quality is output, establishes fruit quality identification model using convolutional neural networks.
Optionally, further includes:
First judgment module, for judge the fruit type in the tested fruit parameter whether with the history fruit join
Fruit type in number is identical, obtains the first judging result；
First the second determining module of fruit quality, if being expressed as the tested fruit parameter for first judging result
Interior fruit type is identical as the fruit type in the history fruit parameter, determines institute according to the fruit quality identification model
State the first fruit quality of tested fruit；
Sugar content obtains module, if being expressed as the fruits in the tested fruit parameter for first judging result
Type is not identical as the fruit type in the history fruit parameter, obtains the sugar content of the tested fruit；
Maturity determining module, for determining the mature journey of the tested fruit according to the sugar content of the tested fruit
Degree；
Second judgment module, for judging that the maturity whether in maturity threshold range, obtains second and sentences
Disconnected result；
Second fruit quality determining module, if being expressed as the maturity in mature journey for second judging result
It spends in threshold range, the second fruit quality is determined according to the fruit volume in the tested fruit parameter.
Optionally, further includes:
History fruit parameter updating module, for being added not and in the history fruit parameter to the history fruit parameter
The identical fruit type of fruit type, obtain updated history fruit parameter；
History fruit quality update module is obtained for adding second fruit quality to the history fruit quality
Updated history fruit quality；
Fruit quality identification model rebuilds module, is used for using the updated history fruit parameter as input, with institute
Updated history fruit quality is stated as output, re-establishes fruit quality identification model.
The specific embodiment provided according to the present invention, the invention discloses following technical effects: the present invention provides one kind
Fruit quality recognition methods and system establish fruit quality identification model according to history fruit parameter and history fruit quality,
The fruit quality of tested fruit is determined according to the fruit quality identification model, to realize automatic identification fruit quality, improves water
The recognition efficiency of fruit quality.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is fruit quality recognition methods flow chart provided by the present invention；
Fig. 2 is fruit quality identifying system structure chart provided by the present invention.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The object of the present invention is to provide a kind of fruit quality recognition methods and systems, can be improved fruit quality identification essence
Degree.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, with reference to the accompanying drawing and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is fruit quality recognition methods flow chart provided by the present invention, as shown in Figure 1, a kind of fruit quality identifies
Method, comprising:
Step 101: obtaining the history fruit parameter and history fruit quality of various fruits；The history fruit parameter packet
It includes fruit type, fruit volume, smell, hardness, color and beats echo etc.；The history fruit quality includes high-quality matter
Amount, mean quality and low quality.
Most Common Fruits can be by color to determine whether maturation, and inclined yellow is with regard to marks mature, and cyan
It means that without maturation, such as banana, apple and pear, can judge by such method；Certainly, apple is come
Say there are some special types, may be mature be also cyan, such apple can only be sentenced by showing gloss and fold
It is disconnected.
Some fruit can not judge maturity from color, but can be judged by hardness, such as avocado,
Fruit as mango；It does not see that changes substantially from color, can be judged by the method for pressing test, if hard
Firmly, by not going down, it is exactly not have maturation also, if soft flexible, means that maturation.
It is most of it is melon can be judged by tapping sound, certain muskmelon and pumpkin are vegetables or fruit on earth,
It is real not important, if watermelon is during percussion, if there is dull sound, mean that ripe；Certainly, melon fruit
Pressing method can be used to detect maturity, such as "Hami" melon, if mature, shell can soften, and press flexible.
Citrus fruit generally will not be mature too early, color is also had no idea the maturity for illustrating them.Such as lemon
Lemon, if mature, color change is not very greatly, therefore, to judge citrus fruit usual way is whether pericarp is compact, such as
Fruit is too tight, illustrates maturation not yet, if too loose, illustrates to have put for a long time.
The present invention carries out establishing fruit quality by the history fruit parameter and history fruit quality for obtaining various fruits
Identification model, high degree improve the accuracy of identification of fruit quality identification model, to more have with convincingness.
Step 102: being input with the history fruit parameter, be output with the history fruit quality, establish fruit matter
Measure identification model.
The step 102 specifically includes: being input with the history fruit parameter, is defeated with the history fruit quality
Out, fruit quality identification model is established using convolutional neural networks.
Step 103: obtaining the tested fruit parameter of tested fruit.
Step 104: the tested fruit parameter being input to the fruit quality identification model, determines the tested fruit
The first fruit quality.
Before the step 104, further includes: judge fruit type in the tested fruit parameter whether with the history
Fruit type in fruit parameter is identical, if so, determining the first of the tested fruit according to the fruit quality identification model
Fruit quality；If it is not, obtaining the sugar content of the tested fruit；The tested water is determined according to the sugar content of the tested fruit
The maturity of fruit；The maturity is judged whether in maturity threshold range, if so, joining according to the tested fruit
Fruit volume in number determines the second fruit quality.
The fruit volume according in the tested fruit parameter determines after the second fruit quality, further includes: to institute
It states history fruit parameter and adds fruit type not identical with the fruit type in the history fruit parameter, obtain updated
History fruit parameter；Second fruit quality is added to the history fruit quality, obtains updated history fruit quality；
It is built again using the updated history fruit parameter as input using the updated history fruit quality as output
Vertical fruit quality identification model.
Fig. 2 is fruit quality identifying system structure chart provided by the present invention, as shown in Fig. 2, a kind of fruit quality identifies
System, comprising:
History fruit parameter and history fruit quality obtain module 201, and the history fruit for obtaining various fruits is joined
Several and history fruit quality；The history fruit parameter includes fruit type, fruit volume, smell, hardness, color and strikes
Return sound；The history fruit quality includes high-quality quality, mean quality and low quality.
Fruit quality identification model establishes module 202, for being input with the history fruit parameter, with the history water
Fruit quality is output, establishes fruit quality identification model.
The fruit quality identification model is established module 202 and specifically included: fruit quality identification model establishes unit, is used for
It is input with the history fruit parameter, is output with the history fruit quality, establishes fruit matter using convolutional neural networks
Measure identification model.
Tested fruit parameter acquisition module 203, for obtaining the tested fruit parameter of tested fruit.
First the first determining module of fruit quality 204, for the tested fruit parameter to be input to the fruit quality
Identification model determines the first fruit quality of the tested fruit.
The invention also includes first judgment module, for judge fruit type in the tested fruit parameter whether with
Fruit type in the history fruit parameter is identical, obtains the first judging result；First the second determining module of fruit quality is used
If in the fruit type and the history fruit parameter that first judging result is expressed as in the tested fruit parameter
Fruit type is identical, and the first fruit quality of the tested fruit is determined according to the fruit quality identification model；Sugar content obtains
Modulus block, if for first judging result be expressed as the fruit type in the tested fruit parameter not with the history water
Fruit type in fruit parameter is identical, obtains the sugar content of the tested fruit；Maturity determining module, for according to
The sugar content of tested fruit determines the maturity of the tested fruit；Second judgment module, for judging the maturity
Whether in maturity threshold range, the second judging result is obtained；Second fruit quality determining module, if being used for described second
Judging result is expressed as the maturity in maturity threshold range, according to the fruit body in the tested fruit parameter
Product determines the second fruit quality.
The invention also includes history fruit parameter updating module, for history fruit parameter addition not with it is described
The identical fruit type of fruit type in history fruit parameter, obtains updated history fruit parameter；History fruit quality
Update module obtains updated history fruit quality for adding second fruit quality to the history fruit quality；
Fruit quality identification model rebuilds module, is used for using the updated history fruit parameter as input, after the update
History fruit quality as output, re-establish fruit quality identification model.
Fruit quality identification can greatly be simplified using fruit quality recognition methods provided by the present invention and system
Process automatically identifies fruit quality, avoids the influence of human factor, improves fruit quality accuracy of identification.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of fruit quality recognition methods characterized by comprising
Obtain the history fruit parameter and history fruit quality of various fruits；The history fruit parameter include fruit type,
Fruit volume, smell, hardness, color and beat echo；The history fruit quality include high-quality quality, mean quality and
Low quality；
It is input with the history fruit parameter, is output with the history fruit quality, establishes fruit quality identification model；
Obtain the tested fruit parameter of tested fruit；
The tested fruit parameter is input to the fruit quality identification model, determines the first fruit matter of the tested fruit
Amount.
2. fruit quality recognition methods according to claim 1, which is characterized in that described to be with the history fruit parameter
Input is output with the history fruit quality, establishes fruit quality identification model, specifically include:
It is input with the history fruit parameter, is output with the history fruit quality, establishes water using convolutional neural networks
Fruit quality Identification model.
3. fruit quality recognition methods according to claim 1, which is characterized in that described that the tested fruit parameter is defeated
Before entering the first fruit quality for determining the tested fruit to the fruit quality identification model, further includes:
Judge whether the fruit type in the tested fruit parameter is identical as the fruit type in the history fruit parameter, obtains
To the first judging result；
If first judging result is expressed as in the fruit type in the tested fruit parameter and the history fruit parameter
Fruit type it is identical, the first fruit quality of the tested fruit is determined according to the fruit quality identification model；
If first judging result be expressed as the fruit type in the tested fruit parameter not with the history fruit parameter
In fruit type it is identical, obtain the sugar content of the tested fruit；
The maturity of the tested fruit is determined according to the sugar content of the tested fruit；
Judge that the maturity whether in maturity threshold range, obtains the second judging result；
If second judging result is expressed as the maturity in maturity threshold range, according to the tested fruit
Fruit volume in parameter determines the second fruit quality.
4. fruit quality recognition methods according to claim 3, which is characterized in that described according to the tested fruit parameter
Interior fruit volume determines after the second fruit quality, further includes:
Fruit type not identical with the fruit type in the history fruit parameter is added to the history fruit parameter, is obtained
Updated history fruit parameter；
Second fruit quality is added to the history fruit quality, obtains updated history fruit quality；
Using the updated history fruit parameter as input, using the updated history fruit quality as output, weight
Newly establish fruit quality identification model.
5. a kind of fruit quality identifying system characterized by comprising
History fruit parameter and history fruit quality obtain module, for obtaining the history fruit parameter of various fruits and going through
History fruit quality；The history fruit parameter includes fruit type, fruit volume, smell, hardness, color and beats echo；
The history fruit quality includes high-quality quality, mean quality and low quality；
Fruit quality identification model establishes module, for being input with the history fruit parameter, with the history fruit quality
For output, fruit quality identification model is established；
Tested fruit parameter acquisition module, for obtaining the tested fruit parameter of tested fruit；
First the first determining module of fruit quality identifies mould for the tested fruit parameter to be input to the fruit quality
Type determines the first fruit quality of the tested fruit.
6. fruit quality identifying system according to claim 5, which is characterized in that the fruit quality identification model is established
Module specifically includes:
Fruit quality identification model establishes unit, for being input with the history fruit parameter, with the history fruit quality
For output, fruit quality identification model is established using convolutional neural networks.
7. fruit quality identifying system according to claim 5, which is characterized in that further include:
First judgment module, for judge the fruit type in the tested fruit parameter whether in the history fruit parameter
Fruit type it is identical, obtain the first judging result；
First the second determining module of fruit quality, if being expressed as in the tested fruit parameter for first judging result
Fruit type is identical as the fruit type in the history fruit parameter, determines the quilt according to the fruit quality identification model
Survey the first fruit quality of fruit；
Sugar content obtains module, if being expressed as the fruit type in the tested fruit parameter not for first judging result
It is identical as the fruit type in the history fruit parameter, obtain the sugar content of the tested fruit；
Maturity determining module, for determining the maturity of the tested fruit according to the sugar content of the tested fruit；
Second judgment module, for judging that the maturity whether in maturity threshold range, obtains the second judgement knot
Fruit；
Second fruit quality determining module, if being expressed as the maturity in maturity threshold for second judging result
It is worth in range, the second fruit quality is determined according to the fruit volume in the tested fruit parameter.
8. fruit quality identifying system according to claim 7, which is characterized in that further include:
History fruit parameter updating module, for the history fruit parameter addition not with the water in the history fruit parameter
The identical fruit type of fruit type, obtains updated history fruit parameter；
History fruit quality update module is updated for adding second fruit quality to the history fruit quality
History fruit quality afterwards；
Fruit quality identification model rebuild module, for will the updated history fruit parameter as input, with it is described more
History fruit quality after new re-establishes fruit quality identification model as output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910183460.5A CN109856345A (en) | 2019-03-12 | 2019-03-12 | A kind of fruit quality recognition methods and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910183460.5A CN109856345A (en) | 2019-03-12 | 2019-03-12 | A kind of fruit quality recognition methods and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109856345A true CN109856345A (en) | 2019-06-07 |
Family
ID=66900436
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910183460.5A Withdrawn CN109856345A (en) | 2019-03-12 | 2019-03-12 | A kind of fruit quality recognition methods and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109856345A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111640451A (en) * | 2020-05-07 | 2020-09-08 | Oppo广东移动通信有限公司 | Maturity evaluation method and device, and storage medium |
| CN113496157A (en) * | 2020-03-20 | 2021-10-12 | 庄宿龙 | Type identification system using big data server |
-
2019
- 2019-03-12 CN CN201910183460.5A patent/CN109856345A/en not_active Withdrawn
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113496157A (en) * | 2020-03-20 | 2021-10-12 | 庄宿龙 | Type identification system using big data server |
| CN111640451A (en) * | 2020-05-07 | 2020-09-08 | Oppo广东移动通信有限公司 | Maturity evaluation method and device, and storage medium |
| CN111640451B (en) * | 2020-05-07 | 2023-01-31 | Oppo广东移动通信有限公司 | Maturity evaluation method and device, and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110867196B (en) | Machine equipment state monitoring system based on deep learning and voice recognition | |
| Jayasena et al. | ° Brix/acid ratio as a predictor of consumer acceptability of Crimson Seedless table grapes | |
| CN109856345A (en) | A kind of fruit quality recognition methods and system | |
| Caselli | Technology Differences over Space and Time | |
| CN103405217B (en) | System and method for multi-dimensional measurement of dysarthria based on real-time articulation modeling technology | |
| EP3667664A1 (en) | Noise data artificial intelligence apparatus and pre-conditioning method for identifying source of problematic noise | |
| CN104582584B (en) | Ultrasound observation apparatus and the method for operating of ultrasound observation apparatus | |
| Jin et al. | Learn low wavenumber information in FWI via deep inception based convolutional networks | |
| CN110120038A (en) | A kind of pavement crack defect inspection method generating network based on confrontation | |
| CN114566282B (en) | Treatment decision system based on echocardiogram detection report | |
| CN109447976A (en) | A kind of medical image cutting method and system based on artificial intelligence | |
| CN111383210B (en) | Fundus image classification model training method and device | |
| WO2005101244A3 (en) | Method for estimating examinee attribute parameters in a cognitive diagnosis model | |
| CN105225658A (en) | The determination method and apparatus of rhythm pause information | |
| Oliver et al. | A comparison of Temporal Dominance of Sensation (TDS) and Quantitative Descriptive Analysis (QDA™) to identify flavors in strawberries | |
| Karlsson et al. | How well does diadochokinetic task performance predict articulatory imprecision? Differentiating individuals with Parkinson’s disease from control subjects | |
| Stocks et al. | Cognitive decision strategies adopted by trained judges in reminder difference tests when tasting yoghurt, mayonnaise, and ice tea | |
| CN107607419B (en) | Method for identifying quality of donkey-hide gelatin jujube | |
| Oliver et al. | Identifying key flavors in strawberries driving liking via internal and external preference mapping | |
| CN109686446A (en) | A kind of hemodialysis program analysis method and system based on track planning of dual robots study | |
| CN109934816A (en) | A kind of method of complementation model, equipment and computer readable storage medium | |
| CN109829050A (en) | A kind of language exercise method, apparatus and system | |
| CN113284621A (en) | Hierarchical management system and method for cardiovascular disease risk assessment | |
| Tiemer | The success of the Nordic Countries as a blueprint for small open economies | |
| Charters et al. | The intrinsic dimensions of wine quality: An exploratory investigation |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190607 |