Liberobacter asiaticum detection method based on visible light images
A citrus huanglongbing and detection method technology, which is applied in image analysis, image data processing, instruments, etc., can solve the problems of long cycle, high detection cost, and difficult popularization and application in grassroots production
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0042] Present embodiment uses SLR camera to carry out the image acquisition of citrus leaf, and the image that gathers is color image, is connected with computer by data line, and image input computer (or sends to remote computer through network, carries out remote diagnosis). By analyzing the texture feature and color feature of the leaf image, extracting the relevant feature data, judging the diseased condition of the leaf plant (on Matlab software), and giving the final recognition result.
[0043] Using the Matlab software platform and the collected citrus leaf image information, the visible light image processing algorithm for the detection of citrus Huanglongbing disease is realized. First, the texture feature and color feature theory involved in this embodiment are specifically explained as follows.
[0044] Texture features: Since the texture is formed by the repeated occurrence of grayscale distribution in the spatial position, there will be a certain grayscale relati...
Embodiment 2
[0057] Present embodiment except following feature other structures are with embodiment 1:
[0058] Because the color features of HLB leaves are difficult to distinguish, sometimes the color features under HSV cannot achieve a good resolution effect. In this embodiment, the color moment of HSI space is also added when judging whether the leaves are healthy or yellow. The steps are: using the HSI color space of the color image, calculating the first-order moment, the second-order moment and the third-order moment in the color space, and using the above three values as HSI detection feature values. Finally, the grayscale detection feature value, HSV detection feature value, and HSI detection feature value are all input into the BP neural network for training and learning, and the optimal BP neural network model is obtained. Realize the identification of whether the leaves are yellow and healthy.
Embodiment 3
[0060] Present embodiment except following feature other structures are with embodiment 1:
[0061] In actual operation, although leaf yellowing is unhealthy, it may not be caused by infection of Huanglongbing. At the same time, the types of Huanglongbing are divided into three types: uniform yellowing, mosaic, and mottled. If it can be further classified , which is more practical for agricultural testing. Therefore, the present embodiment is further supplemented on the basis of embodiment 2, such as figure 1 As shown, the identification steps are as follows.
[0062] 1. Training stage
[0063] (1) Select images with uniform yellowing of the known species of Huanglongbing, mosaic images of known species of Huanglongbing, mottled images of known species of Huanglongbing, and yellowing images of non-Huanglongbing, and extract the value of each image Grayscale detection eigenvalues, HSV detection eigenvalues, HSI detection eigenvalues.
[0064] (2) Select the images with unif...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com