CN105069484A - On-line Chinese-date grading method and system - Google Patents
On-line Chinese-date grading method and system Download PDFInfo
- Publication number
- CN105069484A CN105069484A CN201510530575.9A CN201510530575A CN105069484A CN 105069484 A CN105069484 A CN 105069484A CN 201510530575 A CN201510530575 A CN 201510530575A CN 105069484 A CN105069484 A CN 105069484A
- Authority
- CN
- China
- Prior art keywords
- date
- image
- setting
- denoising
- module
- 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
Classifications
-
- 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
- G06V10/20—Image preprocessing
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an on-line Chinese-date grading method and system. The method comprises: collecting a Chinese-date image; carrying out pretreatment on the Chinese-date image; extracting a feature of the Chinese-date image; and according to the extracted feature, carrying out grading on the Chinese-date. With the method and system, Chinese dates can be graded accurately.
Description
Technical field
The present invention relates to technical field of computer vision, be specifically related to the online stage division of a kind of date and system.
Background technology
Date with its abundant nutritive value and taste by people are liked, become requisite a kind of characteristic fruit in people's life, at present, the date that market is sold is all divide according to grade, so this just needs to carry out classification to date, existing concentrate in be all adopt manually to complete classification, this classification labor intensive, and production efficiency is low, Grading accuracy rate is not high.
Summary of the invention
Technical matters to be solved by this invention is to provide the online stage division of a kind of date and system, can carry out classification more accurately to date.
The technical scheme that the present invention solves the problems of the technologies described above is as follows: the online stage division of a kind of date, comprises the following steps:
Step 1, gathers date image;
Step 2, carries out pre-service to described date image;
Step 3, extracts the feature of described date image;
Step 4, the feature according to extracting carries out classification to described date.
On the basis of technique scheme, the present invention can also do following improvement:
Carry out pre-service to described date image in described step 2 to comprise:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
Further, described step 3 comprises size, color and the surface folding information of extracting described date image.
Further, described step 4 is specially: detected by the size of Sobel Operator to date, then testing result compared with the first threshold of setting, if be greater than described setting threshold value, is then high-quality date; Otherwise be inferior date.
Further, first Iamge Segmentation is carried out to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, then it is inferior date; Otherwise be high-quality date.
The invention has the beneficial effects as follows: classification is carried out to date by the size of comprehensive date and surface folding information simultaneously, classification more accurately can be carried out to date.
A kind of date on-line analysis system, comprising:
Acquisition module, for gathering date image;
Pretreatment module, for carrying out pre-service to described date image;
Extraction module, for extracting the feature of described date image;
Diversity module, for carrying out classification according to the feature extracted to described date.
Further, described pretreatment module is carried out pre-service to described date image and is comprised:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
Further, described extraction module comprises size, color and the surface folding information of extracting described date image.
Further, described diversity module is detected by the size of Sobel Operator to date, then testing result is compared with the first threshold of setting, if be greater than described setting threshold value, is then high-quality date; Otherwise be inferior date.
Further, first described diversity module carries out Iamge Segmentation to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, then it is inferior date; Otherwise be high-quality date.
The invention has the beneficial effects as follows: classification is carried out to date by the size of comprehensive date and surface folding information simultaneously, classification more accurately can be carried out to date.
Accompanying drawing explanation
Fig. 1 is the schematic flow sheet of the online stage division of a kind of date of the present invention;
Fig. 2 is the structural representation of the online hierarchy system of a kind of date of the present invention.
Embodiment
Be described principle of the present invention and feature below in conjunction with accompanying drawing, example, only for explaining the present invention, is not intended to limit scope of the present invention.
As shown in Figure 1, the online stage division of a kind of date, comprises the following steps:
Step 1, gathers date image;
Step 2, carries out pre-service to described date image; Carry out pre-service to described date image in described step 2 to comprise:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
Step 3, extracts the feature of described date image; Described step 3 comprises size, color and the surface folding information of extracting described date image.
Step 4, the feature according to extracting carries out classification to described date.Described step 4 is specially: detected by the size of Sobel Operator to date, then testing result compared with the first threshold of setting, if be greater than described setting threshold value, is then high-quality date; Otherwise be inferior date.
Further, first Iamge Segmentation is carried out to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, then it is inferior date; Otherwise be high-quality date.
The invention has the beneficial effects as follows: classification is carried out to date by the size of comprehensive date and surface folding information simultaneously, classification more accurately can be carried out to date.
As shown in Figure 2, a kind of date on-line analysis system, comprising:
Acquisition module, for gathering date image;
Pretreatment module, for carrying out pre-service to described date image; Described pretreatment module is to described
Date image carries out pre-service and comprises:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
Extraction module, for extracting the feature of described date image; Described extraction module comprises size, color and the surface folding information of extracting described date image.
Diversity module, for carrying out classification according to the feature extracted to described date.Described diversity module is detected by the size of Sobel Operator to date, then testing result is compared with the first threshold of setting, if be greater than described setting threshold value, is then high-quality date; Otherwise be inferior date.
Further, first described diversity module carries out Iamge Segmentation to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, then it is inferior date; Otherwise be high-quality date.
The foregoing is only preferred embodiment of the present invention, not in order to limit the present invention, within the spirit and principles in the present invention all, any amendment done, equivalent replacement, improvement etc., all should be included within protection scope of the present invention.
Claims (10)
1. the online stage division of date, is characterized in that, comprise the following steps:
Step 1, gathers date image;
Step 2, carries out pre-service to described date image;
Step 3, extracts the feature of described date image;
Step 4, the feature according to extracting carries out classification to described date.
2. state the online stage division of a kind of date according to claim 1, it is characterized in that, in described step 2, pre-service is carried out to described date image and comprise:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
3. state the online stage division of a kind of date according to claim 1, it is characterized in that, described step 3 comprises size, color and the surface folding information of extracting described date image.
4. state the online stage division of a kind of date according to claim 1, it is characterized in that, described step 4 is specially: detected by the size of Sobel Operator to date, then testing result compared with the first threshold of setting, if be greater than described setting threshold value, then it is high-quality date; Otherwise be inferior date.
5. the online stage division of a kind of date according to claim 4, it is characterized in that, first Iamge Segmentation is carried out to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, be then inferior date; Otherwise be high-quality date.
6. a date on-line analysis system, is characterized in that, comprising:
Acquisition module, for gathering date image;
Pretreatment module, for carrying out pre-service to described date image;
Extraction module, for extracting the feature of described date image;
Diversity module, for carrying out classification according to the feature extracted to described date.
7. a kind of date on-line analysis system according to claim 6, it is characterized in that, described pretreatment module is carried out pre-service to described date image and is comprised:
Step 2.1, adopts anisotropic Gaussian kernel method carry out denoising to described date image or adopt median filter method to carry out denoising to described date image;
Step 2.2, carries out image enhancement processing to the date image after denoising;
Step 2.3, carrying out binary conversion treatment to described through strengthening the image after process, obtaining gray level image.
8. a kind of date on-line analysis system according to claim 6, it is characterized in that, described extraction module comprises size, color and the surface folding information of extracting described date image.
9. a kind of date on-line analysis system according to claim 6, it is characterized in that, described diversity module is detected by the size of Sobel Operator to date, then testing result is compared with the first threshold of setting, if be greater than described setting threshold value, then it is high-quality date; Otherwise be inferior date.
10. a kind of date on-line analysis system according to claim 9, it is characterized in that, first described diversity module carries out Iamge Segmentation to described date image, extract the part comprising date, then corrode for date part, obtain corroding rear image, the surface folding information of date image after statistics corrosion, and compare with the Second Threshold of setting, if be greater than described setting threshold value, be then inferior date; Otherwise be high-quality date.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510530575.9A CN105069484A (en) | 2015-08-26 | 2015-08-26 | On-line Chinese-date grading method and system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510530575.9A CN105069484A (en) | 2015-08-26 | 2015-08-26 | On-line Chinese-date grading method and system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN105069484A true CN105069484A (en) | 2015-11-18 |
Family
ID=54498845
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510530575.9A Pending CN105069484A (en) | 2015-08-26 | 2015-08-26 | On-line Chinese-date grading method and system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105069484A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111940339A (en) * | 2020-08-18 | 2020-11-17 | 合肥金果缘视觉科技有限公司 | Red date letter sorting system based on artificial intelligence |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020019704A1 (en) * | 2000-05-04 | 2002-02-14 | Tusher Virginia Goss | Significance analysis of microarrays |
CN104215639A (en) * | 2013-06-05 | 2014-12-17 | 江南大学 | Pear surface defect detection method based on machine vision |
-
2015
- 2015-08-26 CN CN201510530575.9A patent/CN105069484A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20020019704A1 (en) * | 2000-05-04 | 2002-02-14 | Tusher Virginia Goss | Significance analysis of microarrays |
CN104215639A (en) * | 2013-06-05 | 2014-12-17 | 江南大学 | Pear surface defect detection method based on machine vision |
Non-Patent Citations (2)
Title |
---|
姚娜等: "基于图像边缘检测的红枣大小分级", 《湖北农业科学》 * |
王丽丽: "基于计算机视觉的哈密大枣无损检测分级技术及分级装置研究", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111940339A (en) * | 2020-08-18 | 2020-11-17 | 合肥金果缘视觉科技有限公司 | Red date letter sorting system based on artificial intelligence |
CN111940339B (en) * | 2020-08-18 | 2022-02-01 | 合肥金果缘视觉科技有限公司 | Red date letter sorting system based on artificial intelligence |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107748888B (en) | A kind of image text row detection method and device | |
CN109284758B (en) | Invoice seal eliminating method and device and computer storage medium | |
CN110399875A (en) | A kind of form of general use information extracting method based on deep learning and pixel projection | |
CN106295588A (en) | The automatic identifying method of leukocyte in a kind of leucorrhea micro-image | |
CN104820986B (en) | A kind of cable online test method based on machine vision | |
CN103077400B (en) | The ground category information remote sensing automatic identifying method that Land Use Database is supported | |
CN103679678B (en) | A kind of semi-automatic splicing restored method of rectangle character features a scrap of paper | |
CN106503695B (en) | A kind of tobacco plant identification and method of counting based on Aerial Images | |
CN108520212A (en) | Method for traffic sign detection based on improved convolutional neural networks | |
CN108960011A (en) | The citrusfruit image-recognizing method of partial occlusion | |
CN102663435B (en) | Junk image filtering method based on semi-supervision | |
CN107145884A (en) | Gangue near-infrared image identification technology | |
CN104156700A (en) | Face image glass removal method based on mobile shape model and weighted interpolation method | |
CN103149214A (en) | Method for detecting flaw on surface of fruit | |
CN105005969A (en) | Note image correction detecting method and system | |
CN103752533A (en) | Method and device for sorting coal and gangue online through image method | |
CN103810522B (en) | Counting method and device for corn ear grains | |
CN105719275A (en) | Parallel combination image defect segmentation method | |
CN105718964A (en) | Transmission line vibration damper visual detection method | |
CN109086772A (en) | A kind of recognition methods and system distorting adhesion character picture validation code | |
CN109409227A (en) | A kind of finger vena plot quality appraisal procedure and its device based on multichannel CNN | |
CN103500323B (en) | Based on the template matching method of self-adaptation gray level image filtering | |
CN110889311A (en) | Financial electronic facsimile document identification system and method | |
CN105069484A (en) | On-line Chinese-date grading method and system | |
CN107578414B (en) | Method for processing pavement crack image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20151118 |
|
RJ01 | Rejection of invention patent application after publication |