CN103617430A - Portable campus plant species recognition system based on plant leaf image information - Google Patents
Portable campus plant species recognition system based on plant leaf image information Download PDFInfo
- Publication number
- CN103617430A CN103617430A CN201310433155.XA CN201310433155A CN103617430A CN 103617430 A CN103617430 A CN 103617430A CN 201310433155 A CN201310433155 A CN 201310433155A CN 103617430 A CN103617430 A CN 103617430A
- Authority
- CN
- China
- Prior art keywords
- image information
- campus
- plant
- leaf image
- system based
- 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
Images
Landscapes
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a portable campus plant species recognition system based on plant leaf image information. The system includes: an image acquisition unit, a processor unit, a memory, a display screen and a user interactive button. The image acquisition unit comprises a camera and a white background frame. The image acquisition unit is responsible for image acquisition of plant leaves; the processor unit is mainly responsible for processing and recognition of a plant leaf image; the memory is used to store campus plant leaf image information and plant-related information; the display screen is used to display a recognition result; and the user interactive button is mainly responsible for interaction between a user and the system. The processor first pre-processes the collected plant leaf image information, then a feature is extracted and vectorized, and the distance between a recognized plant leaf vector and a plant leaf vector in the memory is calculated to identify a plant. According to the invention, the campus plant can be conveniently identified based on the plant leaf image information, and the important practical value is realized.
Description
Technical field
The invention belongs to information control technology field, be specifically related to a kind of exploitation of the portable species of campus plants recognition system based on leaf image information.
Background technology
Plant plays an important role at the mankind's the aspects such as clothing, food, lodging and transportion--basic necessities of life, also significant to environmental protection.And floristic identification be one extremely important but have challenging work.If therefore can develop one can identify floristic portable system automatically, it will have very high practical value to the classification of plant and management.Tellurian floristics is various, and it is unrealistic developing a kind of system that can identify all plants.By image technique, identify floristics, best feature is the blade of plant.Practical floristics automatic recognition system is actually rare in the market.Floristic automatic recognition system is the developing direction of following plant classification and management, has broad application prospects.
Summary of the invention
In order to realize floristic identification fast automatically, developed this portable species of campus plants recognition system based on leaf image information.It belongs to embedded system, and volume is little to be easy to carry.It is only identified the floristics in certain area, and this has just improved accuracy rate and the recognition speed of this system greatly.By gathering the leaf image information of a region (as campus) implants, through simple image, process (comprising image gray processing, binaryzation, removal noise and feature extraction), set up the database of a leaf image information, then pass through image retrieval algorithm, the similarity of the image that computing system collects and database Leaf image, thus identify the kind that is identified plant leaf blade.
The present invention is as follows in order to address the above problem adopted technical scheme:
Whole system forms by being responsible for dsp chip and system processor ARM chip that the camera of image acquisition and white background frame, user interactions button, display screen, archival memory and responsible image process.It is characterized in that size and mobile phone are similar, belong to portable embedded system, be convenient for carrying.
Camera and white background frame are mainly responsible for herborization leaf image information.Because the size of white background frame is known, while gathering image, blade is sprawled and lain on white background frame, by DSP, to the processing of the digital picture obtaining, just can obtain easily the area of plant leaf blade and the girth of blade profile like this, blade area and profile girth are very important to floristic identification.
The vectorization of leaf image information: forming the vector that represents blade information after the information quantizations such as circularity of the profile girth of the length breadth ratio of the area of the area of leaf image, minimum boundary rectangle, minimum boundary rectangle, parallel veins or dictyodromous, leaf color, blade square and Area Ratio, blade, leaf image information is showed by vectorial form.
Data after vectorization can not directly be used, and also each component will be normalized, and make the value of each component all between 0 and 1.Each component also will be got different weights, such as vein is netted or parallel shape weight is got maximum, and color secondly, sizes etc., for each component distributes different weights.In table 1, provide quantized value and the method for normalizing of each leaf characteristic, and provided the corresponding weight of each eigenwert.
First the foundation of database will gather the leaf image information in survey region, secondly by DSP, the digital picture collecting is processed, obtain representing that the vector of each leaf image information is stored in database, and the details of this plant are stored for user with textual form.
System acquisition, after image, is processed digital image information vectorization through DSP image, then calculates the Euclidean distance of each image vector in this leaf image vector and database.System is arranged comparative result according to Euclidean distance order from small to large, and result is presented on the display screen of system, user can manually select the plant leaf blade that oneself will look for by user interactions button, then selects to be identified plant and obtains more relevant details that are identified plant.
Table 1
Accompanying drawing explanation
Fig. 1 is system works structural drawing of the present invention
Fig. 2 is system construction drawing of the present invention
Fig. 3 is working-flow figure
Embodiment
Below in conjunction with accompanying drawing, the present invention is further detailed.
Image acquisition: system is equipped with the camera of herborization leaf image information and supporting white background frame.While gathering image, blade will be placed on to middle part and the lay of white background frame smooth, while taking pictures, camera will be parallel to white background frame plane to reduce the measuring error of blade area and blade profile as far as possible.
Image is processed: image is processed a series of image processing algorithms such as extraction of the filtering, gray processing, binaryzation, rim detection and each characteristic parameter of image that comprise image.Wherein relating to a large amount of data operations is all processed by DSP.Finally the data message of leaf image with vector representation out.
The numerical values recited of each eigenwert after vectorization differs, and for the ease of calculating, will be normalized, and after each component is normalized, the value of each component drops in [0,1] interval.Because the leaf characteristic of each component statement is different, some features are important, and some features are not particular importances, so distribute different weights will to each component.
Image recognition.Calculate the Euclidean distance of the leaf image information vector of storing in leaf image information vector and database, and arrange and be presented on display screen by distance order from small to large.
The close plant leaf blade retrieving is presented on display screen, and then the plant that user can will look for by the manual selection oneself of user interactions button further checks and choose the details of plant take to determine the whether plant as oneself looking for of this plant.Reliability and the dirigibility of system works have been increased like this.
Claims (1)
1. the portable species of campus plants recognition system based on leaf image information, mainly comprise: image acquisition units, processor unit, storer, display and user interactions button, wherein image acquisition units comprises the white background frame of camera and herborization leaf image;
The described portable species of campus plants recognition system based on leaf image information, the system of being primarily characterized in that has special white background frame, white background frame is that a length of side is that 15cm square white is dull and stereotyped, while gathering image, blade is laid on white background frame, the picture noise obtaining is like this less, is convenient to the further processing of image and real area and the girth of computed image easily;
The described portable species of campus plants recognition system based on leaf image information, is characterized in that usining that DSP is as picture processing chip, with ARM chip, as total processor of whole system, controls and coordinate the work between whole system various piece;
The described portable species of campus plants recognition system based on leaf image information, is characterized in that user can be undertaken alternately, having guaranteed like this accuracy and the dirigibility of system identification by interactive button and system;
The described portable species of campus plants recognition system based on leaf image information, is characterized in that the vectorization of leaf image information, and selection, quantification and the normalization of each component in vector;
The described portable species of campus plants recognition system based on leaf image information, is characterized in that the normalization of vector after vectorization and the distribution of each component weight;
The described portable species of campus plants recognition system based on leaf image information, is characterized in that it only identifies the floristics in certain area (as campus).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310433155.XA CN103617430A (en) | 2013-09-14 | 2013-09-14 | Portable campus plant species recognition system based on plant leaf image information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310433155.XA CN103617430A (en) | 2013-09-14 | 2013-09-14 | Portable campus plant species recognition system based on plant leaf image information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103617430A true CN103617430A (en) | 2014-03-05 |
Family
ID=50168133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310433155.XA Pending CN103617430A (en) | 2013-09-14 | 2013-09-14 | Portable campus plant species recognition system based on plant leaf image information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103617430A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182763A (en) * | 2014-08-12 | 2014-12-03 | 中国计量学院 | Plant type identification system based on flower characteristics |
| CN104331713A (en) * | 2014-11-04 | 2015-02-04 | 无锡北斗星通信息科技有限公司 | Mobile terminal for detecting leaf varieties |
| CN105203456A (en) * | 2015-10-28 | 2015-12-30 | 小米科技有限责任公司 | Plant species identification method and apparatus thereof |
| CN106910313A (en) * | 2017-03-22 | 2017-06-30 | 广东小天才科技有限公司 | Reminding method and device |
| CN107615196A (en) * | 2015-05-26 | 2018-01-19 | 三菱电机株式会社 | Numerical control device and display control method |
| CN108090126A (en) * | 2017-11-14 | 2018-05-29 | 维沃移动通信有限公司 | Image processing method, device and mobile terminal, image-recognizing method and server |
| CN108834287A (en) * | 2018-07-20 | 2018-11-16 | 芜湖碧水谣医疗设备科技有限公司 | A kind of plant growth lamp light control system |
| CN110487741A (en) * | 2019-08-22 | 2019-11-22 | Oppo（重庆）智能科技有限公司 | It irrigates information and determines method, apparatus and terminal device |
| CN114023380A (en) * | 2021-11-17 | 2022-02-08 | 中国农业科学院农业质量标准与检测技术研究所 | Toxic organism identification method and device and server |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398898A (en) * | 2008-10-20 | 2009-04-01 | 中国科学院合肥物质科学研究院 | Plant leaf identification method based on manifold learning |
| CN101916382A (en) * | 2010-07-30 | 2010-12-15 | 广州中医药大学 | Method for recognizing image of plant leaf |
-
2013
- 2013-09-14 CN CN201310433155.XA patent/CN103617430A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101398898A (en) * | 2008-10-20 | 2009-04-01 | 中国科学院合肥物质科学研究院 | Plant leaf identification method based on manifold learning |
| CN101916382A (en) * | 2010-07-30 | 2010-12-15 | 广州中医药大学 | Method for recognizing image of plant leaf |
Non-Patent Citations (4)
| Title |
|---|
| JI-XIANG DU 等: "Leaf shape based plant species recognition", 《APPLIED MATHEMATICS AND COMPUTATION》 * |
| 张宁 等: "基于图像分析的植物叶片识别技术综述", 《计算机应用研究》 * |
| 肖雪洋: "植物叶片图像识别特征的研究和在线识别系统实现", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 陈芳 等: "嵌入式植物自动识别系统的设计与实现", 《浙江农林大学学报》 * |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104182763A (en) * | 2014-08-12 | 2014-12-03 | 中国计量学院 | Plant type identification system based on flower characteristics |
| CN104182763B (en) * | 2014-08-12 | 2017-11-07 | 中国计量学院 | A kind of floristics identifying system based on flower feature |
| CN104331713A (en) * | 2014-11-04 | 2015-02-04 | 无锡北斗星通信息科技有限公司 | Mobile terminal for detecting leaf varieties |
| CN104331713B (en) * | 2014-11-04 | 2017-07-07 | 许金普 | Mobile terminal for detecting leaf kind |
| CN107615196A (en) * | 2015-05-26 | 2018-01-19 | 三菱电机株式会社 | Numerical control device and display control method |
| CN105203456A (en) * | 2015-10-28 | 2015-12-30 | 小米科技有限责任公司 | Plant species identification method and apparatus thereof |
| CN106910313A (en) * | 2017-03-22 | 2017-06-30 | 广东小天才科技有限公司 | Reminding method and device |
| CN108090126A (en) * | 2017-11-14 | 2018-05-29 | 维沃移动通信有限公司 | Image processing method, device and mobile terminal, image-recognizing method and server |
| CN108090126B (en) * | 2017-11-14 | 2021-09-24 | 维沃移动通信有限公司 | Image processing method and device, mobile terminal, image identification method and server |
| CN108834287A (en) * | 2018-07-20 | 2018-11-16 | 芜湖碧水谣医疗设备科技有限公司 | A kind of plant growth lamp light control system |
| CN110487741A (en) * | 2019-08-22 | 2019-11-22 | Oppo（重庆）智能科技有限公司 | It irrigates information and determines method, apparatus and terminal device |
| CN114023380A (en) * | 2021-11-17 | 2022-02-08 | 中国农业科学院农业质量标准与检测技术研究所 | Toxic organism identification method and device and server |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103617430A (en) | Portable campus plant species recognition system based on plant leaf image information | |
| CN110263659B (en) | Finger vein recognition method and system based on triplet loss and lightweight network | |
| WO2022213612A1 (en) | Non-contact three-dimensional human body size measurement method | |
| CN103903213B (en) | A kind of image pickup method and electronic equipment | |
| CN110473141A (en) | Image processing method, device, storage medium and electronic equipment | |
| CN109978918A (en) | A kind of trajectory track method, apparatus and storage medium | |
| CN108090458A (en) | Tumble detection method for human body and device | |
| CN108629791A (en) | Pedestrian tracting method and device and across camera pedestrian tracting method and device | |
| CN103093208A (en) | Method and system for fruit and vegetable recognition | |
| CN110363091A (en) | Face identification method, device, equipment and storage medium in the case of side face | |
| CN104021419B (en) | A kind of method and apparatus for counting paper number | |
| CN111476280A (en) | Plant leaf identification method and system | |
| CN105404853A (en) | Content-based plant leaf online recognition system | |
| CN104331686B (en) | A kind of soil surface improving straw mulching rate human assistance identifying system | |
| CN109815823B (en) | Data processing method and related product | |
| CN113723157B (en) | Crop disease identification method and device, electronic equipment and storage medium | |
| CN101916279A (en) | Plant species inquiring system and method based on image analysis technology | |
| CN109446946A (en) | A kind of multi-cam real-time detection method based on multithreading | |
| CN103428537A (en) | Video processing method and video processing device | |
| CN114140665A (en) | Dense small target detection method based on improved YOLOv5 | |
| CN109063776A (en) | Image identifies network training method, device and image recognition methods and device again again | |
| CN103530411A (en) | Plant three-dimensional model database establishing method | |
| CN109753873A (en) | Image processing method and relevant apparatus | |
| Hazra et al. | Shape oriented feature selection for tomato plant identification | |
| Gupta et al. | Tree species detection using full waveform lidar data in a complex forest |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20140305 |