Plant leaf image stoma identification method and device
A technology of plant leaves and stomata, applied in character and pattern recognition, biological neural network models, instruments, etc., can solve problems that affect scientific research progress and efficiency, time-consuming and labor-intensive, and increase errors
Inactive Publication Date: 2017-12-15
CAPITAL NORMAL UNIVERSITY
View PDF4 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0002] At present, in the experiments on stomatal research in botany, researchers manually count the number of stomata after taking images, but there are tens of thousands of pictures taken, and it is time-consuming and laborious to count the number of stomata, and the long-term statistics will greatly increase the probability of errors , affecting the progress and efficiency of scientific research
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
[0048] The preferred embodiments of the present invention will be described below in conjunction with the accompanying drawings. It should be understood that the preferred embodiments described here are only used to illustrate and explain the present invention, and are not intended to limit the present invention.
[0049] Figure 1A It is a flow chart of a method for identifying stomata of plant leaf photos taken under an inverted microscope according to an exemplary embodiment. The air hole identification method is applied in a server. As shown in Figure 1, the method includes steps S101-S106:
[0050] In step S101, the leaf photo taken under the inverted microscope is used as the input original image;
[0051] In step S102, the convolutional neural network model is used to process the leaf photo with a VGG16 convolutional neural network to obtain the first feature matrix containing the stomata characteristics of the leaf; the parameters of the convolutional neural network m...
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
The present invention provides a stoma identification method and device of plant leaf images shot by an inverted microscope. The method comprises: taking blade images shot by an inverted microscope as input original images; employing a VGG16 convolutional neural network model to perform convolution processing of the blade images to obtain a first feature matrix comprising blade stoma features; taking each feature point as a center point to perform mapping to the original images to take the points on the original images after mapping as center points to obtain areas with different sizes; performing first preset rank convolution processing of each feature point and adjacent feature points on the first feature matrix, and determining whether the areas mapping back to the original images are interesting target areas and the range of the target areas or not; mapping the target areas on the original images back to the first feature matrix, and obtaining a corresponding second feature matrix; and determining whether the second feature matrix is a stoma area and the range of the stoma area or not according to the preset full-connection neural network. The researchers' operation can be reduced, and the scientific research speed and efficiency can be improved.
Description
technical field [0001] The invention relates to the field of biotechnology, in particular to a method and device for identifying stomata in photos of plant leaves. Background technique [0002] At present, in the experiments on stomatal research in botany, researchers manually count the number of stomata after taking images, but there are tens of thousands of pictures taken, and it is time-consuming and laborious to count the number of stomata, and the long-term statistics will greatly increase the probability of errors , affecting the progress and efficiency of scientific research. Contents of the invention [0003] The invention provides a method and device for identifying stomata in photos of plant leaves taken under an inverted microscope, which are used to automatically identify the stomatal areas in the photos of plant leaves and make statistics, thereby reducing the operations of scientific researchers and improving the speed and efficiency of scientific research. ...
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 Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/20G06K9/32G06N3/04
CPCG06V10/22G06V10/25G06N3/045
Inventor 唐贺万平
Owner CAPITAL NORMAL UNIVERSITY