Handheld type multi-core real-time online network system for recognition of diseases and pests
A network system, hand-held technology, applied in the field of pattern recognition
Inactive Publication Date: 2013-05-08
JIANGSU ACADEMY OF AGRICULTURAL SCIENCES +1
View PDF0 Cites 1 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Theoretically, by using these features extracted from the images of diseases and insects, it is possible to identify the types of diseases and insects, but under the premise that there are a large number of species of diseases and insects, the image processing technology of diseases and insects is facing a huge challenge
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0037] The system is designed using Visual C++ as a tool.
[0038] 1. Image acquisition
[0039]The captureDlg() class realizes the function of obtaining the pictures of diseases and insects in real time from the camera, and the function of OpenBMPFile(const CStringFilePath) realizes the function of opening the existing pictures of diseases and insects. CopyScreenToBitmap(LPRECT lpRect, const char*filename) in the captureDlg class saves the picture captured by the camera into a BMP picture named filename. OpenBMPFile(const CString FilePath) opens the picture whose path name is FilePath, and can judge whether the picture is damaged or whether it meets the format requirements. The BMPDraw(CDC*pDC, int x1, int y1, int x2, int y2) function displays the picture in the corresponding control.
[0040] 2. Pest image preprocessing
[0041] The CDIB class is responsible for preprocessing the image. The ColorToBlackWhite() function converts the image from a color image to a grayscale...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
For a long time, classification and recognition of diseases and pests are limited to a few researchers for the diseases and the pests, manual inspection is relied on, and observation is conducted by naked eyes, so results which are obtained are not stable in a recognition rate and are very large in a misjudgment rate. Popularity degree of the understanding of the diseases and the pests by people is limited to a great extent, and massive losses are brought for agricultural production and economic activities. Therefore, a digital image technology is applied to the field of the classification and the recognition of the diseases and the pests, automatic recognition for the diseases and the pests is achieved, and non-ignorable functions are provided for promoting human to understand nature and reducing the damage which is caused by the diseases and the pests in the agricultural production. For the purpose, a handheld type multi-core real-time online network system for the recognition of the diseases and the pests is designed. The invention belongs to a module recognition technology. The handheld type multi-core real-time online network system is achieved by Visual C++, a basic principle and a method of module recognition are adopted, and the recognition is conducted according to extracted features after preprocessing is conducted on images of the diseases and the pests.
Description
technical field [0001] The invention belongs to pattern recognition technology. Background technique [0002] For a long time, the classification and identification of pests have been limited to a small number of pest researchers and plant protection scientific and technological workers, relying on manual inspection, naked eye observation, subjective intuition and group experience. The results obtained in this way are often the subjective emotions of the discerners. As a result, the recognition rate is unstable, especially in the case of long time and heavy workload, the misjudgment rate increases significantly. This also limits the popularization of people's knowledge of diseases and insect pests to a large extent, and often brings huge losses to agricultural production and economic activities. Therefore, the application of digital image technology in the field of pest classification and identification to realize the automatic identification of pests will promote human und...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More IPC IPC(8): G06K9/62
Inventor 葛道阔杨余旺曹宏鑫莫然汪文娟刘岩殷俊
Owner JIANGSU ACADEMY OF AGRICULTURAL SCIENCES