WO2020181706A1

WO2020181706A1 - Plant species identification method and apparatus

Info

Publication number: WO2020181706A1
Application number: PCT/CN2019/097891
Authority: WO
Inventors: 任嘉祥; 马进; 王健宗
Original assignee: 平安科技（深圳）有限公司
Priority date: 2019-03-12
Filing date: 2019-07-26
Publication date: 2020-09-17
Also published as: CN110059715A

Abstract

Disclosed in the present application are a plant species identification method and apparatus, the method comprising: performing resolution pre-processing on plant sample images to obtain plant sample images of a first preset resolution; acquiring a corresponding plurality of plant sample sub-images of a second preset resolution at a plurality of preset positions on the plant sample images of a first preset resolution; using the plant sample sub-images of a second preset resolution corresponding to the plurality of preset positions to respectively establish a training sample set and a test sample set corresponding to the plurality of preset positions; respectively using the training sample set corresponding to the plurality of preset positions to train a plurality of ResNet50 convolutional neural network models until the identification results of identification of the corresponding test sample set by each trained model corresponding to the plurality of preset positions satisfies a preset training finishing condition; and receiving plant images to be recognised and using the trained models to identify the species of the plant images to be identified.

Description

Method and device for identifying plant species

This application claims the priority of the Chinese patent application filed with the Chinese Patent Office on March 12, 2019, the application number is 201910185074.X, and the application name is "Methods and devices for identifying plant species, storage media, and computer equipment". All of them The content is incorporated in the application by reference.

Technical field

This application relates to the technical field of plant species identification, and in particular to a method and device for plant species identification.

Background technique

How to identify plant species is the demand of the vast number of growers. During the planting process, growers need to remove other types of plants and only retain the required types of plants in the planting area. For example, in the process of planting Atractylodes, it is often mixed with Atractylodes, which belongs to the genus Atractylodes of the Atractylaceae, and the two plants have different medicinal effects, but the appearance is very similar. Or other plants mixed with atractylodes japonicus affect the efficacy of atractylodes japonicus.

In the prior art, an experienced person needs to observe carefully to distinguish, so as to preserve atractylodes. But because atractylodes is a high-demand medicinal material, manual classification is slow and requires high personnel experience. It is difficult for inexperienced staff to recognize the accuracy of atractylodes and atractylodes, which affects the quality of planted atractylodes.

Summary of the invention

In view of this, the present application provides a method and device for identifying plant species, which helps to improve the accuracy of plant species identification.

According to one aspect of this application, a method for identifying plant species is provided, including:

Performing resolution preprocessing on the plant sample image to obtain a plant sample image with a first preset resolution;

A plurality of corresponding plant sample sub-images of a second preset resolution are respectively acquired at a plurality of preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the The first preset resolution, the plurality of preset positions are different, one of the plurality of preset positions is the center position of the plant sample image of the first preset resolution, and the other presets The plant sample sub-images of the second preset resolution corresponding to the positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

Using the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training sample set and the test sample set corresponding to the plurality of preset positions ；

Training multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions respectively, until each trained model corresponding to the multiple preset positions identifies the corresponding test sample set The recognition result meets the preset training termination condition;

The plant image to be recognized is received, and the type of the plant image to be recognized is recognized by using the trained model.

According to another aspect of the present application, there is provided a plant species identification device, which is characterized in that it comprises:

The sample resolution processing module is used to perform resolution preprocessing on the plant sample image to obtain the plant sample image of the first preset resolution;

The sample block processing module is configured to obtain corresponding multiple plant sample sub-images of the second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, wherein the The second preset resolution is smaller than the first preset resolution, the plurality of preset positions are different from each other, and one of the plurality of preset positions is a plant sample image of the first preset resolution The plant sample sub-images of the second preset resolution corresponding to other preset positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

The sample set establishment module is configured to use the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training samples corresponding to the plurality of preset positions Set and the test sample set;

The model training module is used to train multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions, until each trained model corresponding to the multiple preset positions recognizes the corresponding The recognition result of the test sample set meets a preset training termination condition;

The image recognition module is used to receive the plant image to be recognized, and use the trained model to recognize the type of the plant image to be recognized.

According to another aspect of the present application, a computer non-volatile readable storage medium is provided, on which computer readable instructions are stored, and when the program is executed by a processor, the following steps are implemented:

According to another aspect of the present application, there is provided a computer device, including a memory, a processor, and computer-readable instructions stored in the memory and executable on the processor. The processor implements The following steps:

With the above technical solutions, the plant species identification method and device provided in this application process the resolution of the plant sample image, and after the plant sample image is divided into blocks according to the preset position, it is established with each The training sample set and test sample set corresponding to the preset position are used to train the corresponding ResNet50 model with the training sample set corresponding to each preset position, so that the trained model can achieve the recognition effect of the test sample set at the corresponding position After the training termination condition is preset, the classification of the new plant image to be recognized is realized through the trained model. Compared with the prior art relying on experienced technicians to manually classify plants, this application only needs to take images of the plants to be identified, and the types of plants can be identified through models, which improves the efficiency of identifying plant species and saves money. The labor cost is reduced, and the deep convolutional neural network model using ResNet50 structure also has high accuracy for the recognition of complex images.

The above description is only an overview of the technical solution of this application. In order to understand the technical means of this application more clearly, it can be implemented in accordance with the content of the specification, and to make the above and other purposes, features and advantages of this application more obvious and understandable. , The following specifically cite the specific implementation of this application.

Description of the drawings

The drawings described here are used to provide a further understanding of the application and constitute a part of the application. The exemplary embodiments and descriptions of the application are used to explain the application and do not constitute an improper limitation of the application. In the attached picture:

Fig. 1 shows a schematic flowchart of a method for identifying plant species provided by an embodiment of the present application;

Figure 2 shows a schematic flow chart of another method for identifying plant species provided by an embodiment of the present application;

Fig. 3 shows a block diagram of a plant sample image provided by a specific embodiment of the present application;

FIG. 4 shows a schematic structural diagram of a plant species identification device provided by an embodiment of the present application;

Figure 5 shows a schematic structural diagram of another plant species identification device provided by an embodiment of the present application;

Fig. 6 shows a schematic diagram of the physical structure of a computer device provided by an embodiment of the present application.

detailed description

Hereinafter, the application will be described in detail with reference to the drawings and in conjunction with embodiments. It should be noted that the embodiments in this application and the features in the embodiments can be combined with each other if there is no conflict.

In this embodiment, a method for identifying plant species is provided. As shown in FIG. 1, the method includes:

Step 101: Perform resolution preprocessing on a plant sample image to obtain a plant sample image with a first preset resolution.

The embodiment of this application is explained by taking the distinction between atractylodes image and atractylodes macrocephala image as an example. The embodiment of this application is only used as an example. Those skilled in the art can replace the atractylodes macrocephala image and the atractylodes macrocephala image with one or more other plant images. There is no limitation here.

In the above embodiment, the plant sample image may include atractylodes lanceolata sample image and Atractylodes lanceolata sample image. After the plant sample image is obtained, in order to use the sample image to train the classification model and improve the training efficiency, it is necessary to normalize the resolution of the sample image. The size of the sample images is unified, and specifically, all the plant sample images can be processed into images of the first preset resolution.

Step 102: Acquire corresponding multiple plant sample sub-images of a second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the first The preset resolution, multiple preset positions are different, one of the multiple preset positions is the center position of the plant sample image with the first preset resolution, and the other preset positions correspond to the second preset resolution The plant sample sub-images do not overlap each other and can be combined into a complete plant sample image of the first preset resolution.

Because when shooting plant sample images, the focus is usually at the center of the plant. Therefore, the image information corresponding to different positions of the sample image may be quite different. For example, the bottom of the image may contain more plants. The top of the image may contain more plant leaf images, and the root characteristics of plants are quite different from the leaf characteristics of plants. Therefore, in order to obtain a more accurate classification result, this embodiment performs more detailed analysis on different parts of plants. Specific modeling analysis, after processing the resolution of the plant sample image to the first preset resolution, the image is divided into blocks according to the preset position, and each plant sample image is divided into blocks according to multiple preset positions Then, a complete plant sample image can be divided into multiple plant sample image blocks, where each preset position corresponds to one image block. And in order to preserve the complete image features, the image blocks obtained after the block processing can completely cover the original plant sample image with the first preset resolution.

Step 103: Using a plurality of plant sample sub-images of a second preset resolution corresponding to a plurality of preset positions, respectively establish a training sample set and a test sample set corresponding to the plurality of preset positions.

After performing block processing on each plant sample image, the image block corresponding to each preset position is used to establish a training sample set and a test sample set corresponding to the preset position. For example, preset 5 positions in the sample image, which are marked as position 1, position 2, position 3, position 4, and position 5. After the plant sample image is divided into blocks, the image blocks corresponding to the 5 positions are obtained. The image blocks corresponding to positions 1, 2, 3, 4, and 5 establish the training sample set of positions 1, 2, 3, 4, and 5 and the test sample set of positions 1, 2, 3, 4, and 5. Generally speaking, training samples The number of images in the set is greater than the number of images in the test sample set. In this embodiment, the number of images in the training sample set can be preset to 2000, and the number of images in the test sample set is preset to 300. In this embodiment, the training sample Both the set and the test sample set contain samples of Atractylodes Rhizome and Atractylodes Rhizome sample image blocks corresponding to preset positions.

Step 104: Train multiple ResNet50 convolutional neural network models with training sample sets corresponding to multiple preset positions respectively, until each trained model corresponding to multiple preset positions recognizes the recognition result of the corresponding test sample set Meet the preset training termination conditions.

In order to accurately identify the image of each specific preset location, a ResNet50 convolutional neural network model corresponding to each preset location is established, and the training sample set corresponding to each preset location is used to train the corresponding preset location Model. For example, use the training sample set corresponding to position 1 to train the model in position 1.

Use the test sample set to test the model to verify the classification effect of the model on the sample images in the test sample set. If the classification effect of the model does not reach the preset training termination condition after one training, adjust the relevant training parameters of the model and continue Use the test sample set to train the model until the preset training termination condition is met.

Step 105: Receive the plant image to be recognized, and use the trained model to recognize the type of plant image to be recognized.

After the model is successfully trained, the trained model can be used to classify the plant image to be recognized. Specifically, after obtaining multiple image blocks of the plant image to be recognized according to the preset position, the plant to be recognized can be obtained through the corresponding trained model Identify the plant species corresponding to the image. In the embodiment of the present application, after inputting the plant image to be recognized into the model, the probability that the image is an Atractylodes lancea image and the probability that the image is an Atractylodes macrocephala image can be obtained.

By applying the technical solution of this embodiment, by processing the resolution of the plant sample image, and performing block processing on the plant sample image according to the preset position, a training sample set and a test sample corresponding to each preset position are established The training sample set corresponding to each preset position is used to train the corresponding ResNet50 model, so that the trained model can recognize the test sample set at the corresponding position after reaching the preset training termination condition. The latter model classifies the new plant image to be recognized. Compared with the prior art relying on experienced technicians to manually classify plants, this application only needs to take images of the plants to be identified, and the types of plants can be identified through models, which improves the efficiency of identifying plant species and saves money. The labor cost.

Further, as a refinement and extension of the specific implementation of the foregoing embodiment, in order to fully explain the specific implementation process of this embodiment, another method for identifying plant species is provided. As shown in FIG. 2, the method includes:

Step 201: If the resolution of the plant sample image is greater than the first preset resolution, down-sampling is performed on the plant sample image to obtain a plant sample image of the first preset resolution.

The ResNet50 convolutional neural network model used in the embodiments of this application requires an image with a resolution of 720×540 for training. Therefore, the preset resolution is 720×540 to ensure the clarity of the image so that the plant sample image can be processed For further processing, in this embodiment of the application, the first preset resolution is set to 1440×1080.

If the resolution of the plant sample image is greater than the first preset resolution, the image should be down-sampled to reduce it to the first preset resolution, so that the resolution of all the plant sample images is unified, and the subsequent image segmentation is convenient Processing and other operations and the establishment of training sample sets and test sample sets.

In this embodiment, specifically, the ResNet50 model includes a 50-layer convolutional layer and a 1-layer fully connected layer that are sequentially connected, where the 50-layer convolutional layer is divided into 5 blocks, and the 5 blocks are respectively denoted as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 includes a convolutional layer with a 7×7 convolution kernel, conv2_x includes a convolution layer with a 3×3 convolution kernel and 3 bottleneck building blocks; conv3_x includes 4 bottleneck building blocks; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, and each bottleneck building block includes 3 layers of convolution kernels as 3×3 convolutional layers.

ResNet50 is a deep convolutional neural network structure, which uses residual connection to increase the depth of the network structure and improve the recognition accuracy. Using this network structure can achieve accurate classification of complex images. Specifically, it includes 50 layers of convolutional layer and 1 layer of fully connected layer (or called up-sampling layer). Specifically, conv1 consists of a single convolution kernel of 7×7 fully convolutional layers; conv2_x consists of a 3×3 convolution The convolutional layer of the convolution kernel and 3 bottleneck building blocks are composed of a total of 10 layers (each bottleneck building block contains a convolution kernel of 1×1, a convolution layer with 64 channels, and a convolution kernel of 3 ×3, a convolutional layer with 64 channels, and a convolutional layer with a convolution kernel of 1×1 and 256 channels); conv3_x is composed of 4 bottleneck building blocks and a total of 12 layers (each bottleneck building block It contains a convolution kernel of 1×1, a convolutional layer with 128 channels, a convolution kernel of 3×3, a convolutional layer with 128 channels, and a convolution kernel of 1×1 , A convolutional layer with 512 channels); conv4_x is composed of 6 bottleneck building blocks and a total of 18 layers (each bottleneck building block includes a convolution kernel of 1×1, a convolutional layer with 256 channels, a The layer convolution kernel is 3×3, the number of channels is 256 convolutional layers, and the convolution kernel is 1×1, the number of channels is 1024 convolution layers); conv5_x consists of 3 bottleneck building blocks, a total of 9 layers (Each bottleneck building block includes a convolution kernel of 1×1, a convolutional layer with 512 channels, a convolution kernel of 3×3, a convolutional layer with 512 channels, and a layer of convolution The product kernel is a 1×1 convolutional layer with a channel number of 2048); in the embodiment of the present application, a 2-dimensional fully connected layer is finally passed to obtain prediction results for two classification categories (Atractylodes and Atractylodes). Of course, those skilled in the art can adjust the number of categories according to the number of plant categories contained in the plant sample image according to actual needs, and this is just an example for illustration.

Step 202: If the resolution of the plant sample image is less than the first preset resolution, perform an up-sampling process on the plant sample image to obtain a plant sample image of the first preset resolution.

If the resolution of the plant sample image is less than the first preset resolution, the resolution of the image should also be adjusted to the first preset resolution. Specifically, the up-sampling process can be used to perform bilinear on the original image. Interpolate and upsample to the first preset resolution.

It should be noted that performing up-sampling processing on an image may cause a certain loss of image performance. Therefore, an image with a resolution greater than or equal to the first preset resolution is preferred as the sample image.

Step 203: Acquire corresponding multiple plant sample sub-images of a second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the first The preset resolution, multiple preset positions are different, one of the multiple preset positions is the center position of the plant sample image of the first preset resolution, and the other plant samples of the second preset resolution The sub-images do not overlap each other.

The embodiment of the present application performs block processing on the plant sample image, and obtains multiple plant sample sub-images with a resolution of 720×540 corresponding to multiple preset positions according to each plant sample image with a first preset resolution. Among them, the multiple preset positions include the center position of the plant sample image. The plant sample image corresponding to the center position may overlap with plant sample images corresponding to other positions, but the plant sample images corresponding to other positions do not overlap each other and other positions The corresponding plant sample sub-image should include the entire plant sample image, so that the training sample set and the test sample set can be established based on the divided plant sample image, so that each pixel in the image is used as a training sample to avoid loss of image Feature information, and because the central position of the image is usually the part where the key feature information for distinguishing plant species is relatively concentrated, extracting the image at the central position separately for training will help improve the recognition accuracy of the model.

For example, according to the 1440×1080 resolution plant sample image, five 720×540 resolution plant sample image blocks are obtained. The specific block method is shown in Figure 3, where the center of block 1 coincides with the center of the 1440×1080 resolution plant sample image, and the pixels in the upper left corner of block 2 correspond to the 1440×1080 resolution plant sample image. The pixels at the top corner coincide, and blocks 3, 4, and 5 are similarly obtained.

Step 204, according to the RGB value normalization processing formula, normalize the RGB value of each pixel of the plant sample sub-images with the second preset resolution ratio, and the RGB value normalization processing formula is:

Among them, N is the maximum component value of the RGB channel, and x and y are the R, G, and B of any pixel corresponding to the original and normalized second preset resolution plant sample sub-image. The component value of a channel.

Before establishing the training sample set and the test sample set, it is also necessary to use the above RGB value normalization processing formula to normalize the RGB value of the plant sample image obtained after block, so that each pixel of the sample image is in R, The component values on the G and B three channels are transformed from the original [0,255] to [-1,1], which makes the data distribution more uniform, which helps to speed up the training process of the model. Among them, N takes 255.

Step 205: Use the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions after the normalization of the RGB values, to respectively establish training sample sets and test samples corresponding to the plurality of preset positions set.

After the plant sample image is normalized by RGB values, a corresponding training sample set and a test sample set are established according to the plant sample image with a resolution of 720×540 corresponding to each preset position. In the embodiment of the present application, 5 training sample sets corresponding to preset positions and 5 corresponding test sample sets are respectively established. Each training sample set includes 2000 images of the same position of different samples, and each test sample The set includes 300 images of the same position of samples different from the training sample set.

Step 206: Use training sample sets corresponding to a plurality of preset positions to train corresponding models according to a preset learning rate.

The model is trained according to a preset learning rate using a training sample set, for example, a training sample set corresponding to position 1 is used to train a model corresponding to position 1 at a learning rate of 0.01. Among them, different learning rates can be set for models corresponding to different positions, or the same learning rate can be set, which is not limited here.

Step 207: If the accuracy of the trained model to identify the corresponding test sample set is less than the preset accuracy and/or the recall rate is less than the preset recall rate, then the preset learning rate is reduced, and the reduced preset learning rate is continued The model is trained until the accuracy rate of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy rate and the recall rate is greater than or equal to the preset recall rate.

After training the model according to the preset learning rate, use the trained model to test the corresponding test sample set. If the recognition accuracy and recall rate of the model are greater than or equal to the preset accuracy and recall rates, then the model After the training is completed, the model can be further used to classify the plant images to be recognized. If the recognition accuracy of the model is less than the preset accuracy and the recall rate is less than the preset recall rate, you need to continue to train the model. Use a learning rate lower than the original preset learning rate for training, thereby improving the recognition accuracy and recall rate of the model until the corresponding presets are reached.

For example, suppose that the preset learning rate is 0.01, and the preset accuracy and recall rates are both 90%. First use the learning rate of 0.01 to train the model 3000 times, and each pass contains 30 plant sample images randomly selected from the training sample set. After the recognition accuracy and/or recall rate of the model is less than 90%, the model will be trained 1000 times with a learning rate of 0.001. Each pass contains 30 plant sample images randomly selected from the training sample set, and then test the recognition of the trained model If the accuracy and recall rates still do not meet the preset conditions, you can reduce the learning rate again to continue learning.

In addition, it should be noted that the model corresponding to each preset position can use the same initial learning rate, or different initial learning rates can be set separately, and the preset accuracy and recall rate corresponding to each model can be the same or can be Different, for example, the accuracy rate and recall rate corresponding to the center position are set to 95%, and the accuracy rate and recall rate corresponding to other positions are set to 90%. Test the classification accuracy and recall of each model separately, until the classification accuracy and recall of each model after training reach the corresponding preset.

Step 208: Perform resolution preprocessing on the received plant image to be recognized, so that the resolution of the plant image to be recognized is consistent with the first preset resolution;

Step 209: Acquire corresponding multiple plant sub-images to be recognized at multiple preset positions of the processed plant image to be recognized, wherein the resolution of any one of the multiple plant images to be recognized and the first 2. The preset resolution is consistent;

Step 210: Perform normalization processing on the RGB value of each pixel of the plant sub-image to be identified corresponding to a plurality of preset positions according to the RGB value normalization processing formula;

Step 211: Input the plant sub-images to be identified corresponding to the multiple preset positions after the normalization of the RGB values into the corresponding trained model to obtain the to-be-identified plant sub-images corresponding to the multiple preset positions respectively. Multiple recognition results of plant sub-images.

In the above steps 208 to 211, after the model training is completed, the classification of the plant image to be recognized can be realized. Specifically, after receiving the plant image to be identified, the processing procedure is similar to that of the plant sample image. The resolution of the image is first processed to the first preset resolution, and then the image is divided into blocks according to multiple preset positions. Obtain the plant image to be identified corresponding to each preset position, and then normalize the RGB value of each pixel of each plant image to be identified, and finally, respectively, the image to be identified corresponding to each preset position Input into the corresponding model to obtain the recognition result corresponding to each preset position.

For example, the images to be recognized corresponding to 5 preset positions are input into the corresponding models respectively, and the recognition results of the images to be recognized corresponding to the 5 preset positions are obtained respectively.

Step 212: Perform a weighted sum calculation on the multiple recognition results according to the preset weights corresponding to the multiple preset positions to obtain the recognition result of the image to be recognized, where the plant sub-image at the center position corresponds to the The preset weight is greater than the preset weight corresponding to the plant sub-images to be identified at other locations.

After obtaining the recognition result corresponding to each preset position, the recognition result is weighted and calculated according to the corresponding preset weight to obtain the final recognition result of the image to be recognized. Among them, the central location may contain more key feature information, which should be used as the main reference factor to determine the final recognition result. Therefore, its corresponding weight should be higher than the corresponding weights at other locations to obtain more accurate recognition results.

For example, the weight corresponding to the center position in the 5 preset positions is set to 0.4, and the weight corresponding to the remaining 4 positions is set to 0.15 respectively. Assuming that the recognition result at the center position is that the image corresponding to the center position is atractylodes, the probability is 80% , The probability of Atractylodes macrocephala is 10%, and the recognition results of the remaining 4 positions are 40%, 90%, 80%, 80% of the corresponding image; the probability of Atractylodes macrocephala is 80%, 20%, 30%. , 20%. Then the probability that the plant image to be identified is Atractylodes is 80%*0.4+40%*0.15+90%*0.15+80%*0.15+80%*0.15=75.5%, and the probability that the image is Atractylodes is 10%* 0.4+80%*0.15+20%*0.15+30%*0.15+20%*0.15=26.5%. Then, the type of plant image to be recognized can be determined according to the 75.5% probability of atractylodes and 26.5% probability of atractylodes.

Specifically, a rule can be set as follows: if the probability of the recognition result of the first type of plant is greater than or equal to the first preset probability and the probability of the second type of plant is less than the second preset probability, determine the plant corresponding to the plant image to be recognized The species is the first kind of plant. For example, the first preset probability is 70% and the second preset probability is 30%, then it can be determined that the type corresponding to the above-mentioned plant image to be recognized is atractylodes. If the recognition result is that the probability of atractylodes is 60% and the probability of atractylodes is 40%, then manual judgment can be involved or continue to judge whether the image is another plant image.

In addition, it is also possible to compare the probabilities corresponding to the plant species of the two plant identification results, and determine the plant species with a higher probability as the species of the plant image to be recognized. For example, if the recognition result is that the probability of atractylodes is 60% and the probability of atractylodes is 40%, it is determined that the image is atractylodes image.

By applying the technical solution of this embodiment, a piece of plant sample image is processed into blocks to obtain multiple plant sample images corresponding to multiple preset positions, thereby establishing training sample sets and test samples corresponding to different preset positions The training sample set corresponding to each preset position is used to train the corresponding classification model, so that the recognition accuracy and recall rate of each classification model for the corresponding training sample set meet the corresponding preset conditions, and the final It can be used as a model for classifying plant images to be recognized. When the plant image to be recognized is received, the plant image to be recognized is divided into blocks according to the preset position and then input into the corresponding classification model, so as to determine the final plant image to be recognized according to the recognition result of each classification model The classification results. The embodiments of this application help solve the problem of low efficiency caused by artificial recognition of plant species in the prior art, and separately train classification models corresponding to different preset positions, and integrate the recognition results of multiple classification models to determine the final The classification result of the image to be recognized improves the accuracy and efficiency of recognition.

Further, as a specific implementation of the method in FIG. 1, an embodiment of the present application provides a plant species identification device. As shown in FIG. 4, the device includes: a sample resolution processing module 41, a sample block processing module 42, and a sample Set building module 43, model training module 44, and image recognition module 45.

The sample resolution processing module 41 is configured to perform resolution preprocessing on the plant sample image to obtain a plant sample image of the first preset resolution;

The sample block processing module 42 is configured to obtain corresponding multiple plant sample sub-images of the second preset resolution at multiple preset positions of the plant sample image of the first preset resolution. Suppose the resolution is smaller than the first preset resolution, and the multiple preset positions are different. One of the multiple preset positions is the center position of the plant sample image with the first preset resolution, and the other preset positions correspond to The plant sample sub-images of the second preset resolution do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

The sample set establishment module 43 is configured to use a plurality of plant sample sub-images of a second preset resolution corresponding to a plurality of preset positions to respectively establish a training sample set and a test sample set corresponding to the plurality of preset positions;

The model training module 44 is used to train multiple ResNet50 convolutional neural network models using training sample sets corresponding to multiple preset positions, until each trained model corresponding to multiple preset positions recognizes a corresponding test sample The recognition result of the set meets the preset training termination condition;

The image recognition module 45 is used to receive the plant image to be recognized, and use the trained model to recognize the type of the plant image to be recognized.

In a specific application scenario, as shown in FIG. 5, the sample resolution processing module 41 specifically includes: a sample down-sampling unit 411 and a sample up-sampling unit 412.

The sample down-sampling unit 411 is configured to perform down-sampling processing on the plant sample image if the resolution of the plant sample image is greater than the first preset resolution to obtain a plant sample image of the first preset resolution;

The sample up-sampling unit 412 is configured to perform an up-sampling process on the plant sample image if the resolution of the plant sample image is less than the first preset resolution to obtain a plant sample image of the first preset resolution.

In a specific application scenario, as shown in FIG. 5, the device further includes: an RGB value normalization module 46.

The RGB value normalization module 46 is configured to obtain corresponding multiple plant sample sub-images of the second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, and then according to the RGB value The normalization processing formula is to normalize the RGB value of each pixel of a plurality of plant sample sub-images with a second preset resolution. The RGB value normalization processing formula is:

Among them, N is the maximum component value of the RGB channel, and x and y are the R, G, and B of any pixel corresponding to the original and normalized second preset resolution plant sample sub-image. The component value of a channel;

The sample set establishment module 43 is specifically configured to use the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions after the normalization of the RGB values to establish the respective sub-images corresponding to the plurality of preset positions Training sample set and test sample set.

In a specific application scenario, as shown in FIG. 5, the image recognition module 45 specifically includes: an image resolution processing unit 451, an image block unit 452, an image RGB value normalization unit 453, an image recognition unit 454, and a recognition result Calculating unit 455.

The image resolution processing unit 451 is configured to perform resolution preprocessing on the received plant image to be recognized, so that the resolution of the plant image to be recognized is consistent with the first preset resolution;

The image segmentation unit 452 is configured to obtain corresponding multiple plant images to be recognized at multiple preset positions of the processed plant images to be recognized, where any one of the multiple plant images to be recognized The resolution is consistent with the second preset resolution;

The image RGB value normalization unit 453 is configured to perform normalization processing on the RGB value of each pixel of the plant sub-image to be identified corresponding to a plurality of preset positions according to the RGB value normalization processing formula;

The image recognition unit 454 is configured to input the sub-images of plants to be recognized corresponding to the multiple preset positions after the normalization of the RGB values into the corresponding trained model, and obtain the sub-images corresponding to the multiple preset positions. Multiple recognition results of the plant sub-images to be recognized;

The recognition result calculation unit 455 is configured to perform a weighted sum calculation on the multiple recognition results according to the preset weights corresponding to the multiple preset positions to obtain the recognition result of the image to be recognized. The preset weights corresponding to the plant sub-images are greater than the preset weights corresponding to the plant sub-images to be identified at other locations.

In a specific application scenario, as shown in FIG. 5, the model training module 44 specifically includes: a first model training unit 441 and a second model training unit 442.

The first model training unit 441 is configured to use training sample sets corresponding to multiple preset positions to train the corresponding model according to the preset learning rate;

The second model training unit 442 is configured to reduce the preset learning rate if the accuracy of the trained model to identify the corresponding test sample set is less than the preset accuracy rate and/or the recall rate is less than the preset recall rate, and according to the reduced Continue to train the model until the accuracy rate of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy rate and the recall rate is greater than or equal to the preset recall rate.

In the above embodiment, specifically, the network structure of the model includes 50 layers of convolutional layers and 1 layer of fully connected layers that are sequentially connected, where the 50 layers of convolutional layers are divided into 5 blocks, and the 5 blocks are respectively denoted as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 includes a convolutional layer with a 7×7 convolution kernel, conv2_x includes a convolutional layer with a 3×3 convolution kernel and 3 bottleneck building blocks; conv3_x includes 4 bottleneck constructions Block; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, and each bottleneck building block includes 3 convolutional layers with a 3×3 convolution kernel.

It should be noted that, for other corresponding descriptions of the functional units involved in the device for identifying plant species provided in the embodiments of the present application, reference may be made to the corresponding descriptions in FIG. 1 and FIG. 2, and details are not repeated here.

Based on the above-mentioned method shown in Figure 1 and Figure 2, correspondingly, an embodiment of the present application also provides a computer non-volatile readable storage medium, on which computer readable instructions are stored, and the computer readable instructions are processed The following steps are implemented when the device is executed: the resolution preprocessing of the plant sample image is performed to obtain the plant sample image of the first preset resolution; the corresponding plant sample images of the first preset resolution are obtained at multiple preset positions. A plurality of plant sample sub-images of a second preset resolution, wherein the second preset resolution is less than the first preset resolution, the plurality of preset positions are different, and one of the plurality of preset positions is the first At the center position of a plant sample image of a preset resolution, the plant sample sub-images of the second preset resolution corresponding to other preset positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution ; Using a plurality of sub-images of plant samples of a second preset resolution corresponding to a plurality of preset positions to respectively establish a training sample set and a test sample set corresponding to the plurality of preset positions; respectively using a plurality of preset positions The corresponding training sample set trains multiple ResNet50 convolutional neural network models, until the recognition result of the test sample set corresponding to the model identification corresponding to multiple preset positions meets the preset training termination condition; receive the to-be-identified Plant images, and use the trained model to recognize the types of plant images to be recognized.

Based on this understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, U disk, mobile hard disk, etc.), including several The instructions are used to make a computer device (which may be a personal computer, a server, or a network device, etc.) execute the methods described in each implementation scenario of this application.

Based on the above-mentioned method shown in FIG. 1 and the embodiment of the apparatus shown in FIG. 4, an embodiment of the present application also provides a physical structure diagram of a computer device. As shown in FIG. 6, the computer device includes: a processor 51, The memory 52 and computer-readable instructions stored on the memory 52 and capable of running on the processor, wherein the memory 52 and the processor 51 are both set on the bus 53 and the processor 51 implements the following steps when the processor 51 executes the program: Resolution preprocessing to obtain a plant sample image of a first preset resolution; obtain a plurality of corresponding plant samples of a second preset resolution at a plurality of preset positions of the plant sample image of the first preset resolution A sub-image, wherein the second preset resolution is smaller than the first preset resolution, the multiple preset positions are different, and one of the multiple preset positions is the center position of the plant sample image with the first preset resolution Where, the plant sample sub-images of the second preset resolution corresponding to other preset positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution; multiple The plant sample sub-images of the second preset resolution are respectively established for training sample sets and test sample sets corresponding to multiple preset positions; training multiple ResNet50 convolutional nerves are respectively used with the training sample sets corresponding to multiple preset positions Network model, until the recognition result of the test sample set corresponding to each trained model corresponding to multiple preset positions meets the preset training termination condition; receive the plant image to be recognized, and use the trained model to recognize the target The type of plant image is recognized. The computer device also includes a bus 53 configured to couple the processor 51 and the memory 52.

Optionally, the computer device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, and so on. The user interface may include a display screen (Display), an input unit such as a keyboard (Keyboard), etc., and the optional user interface may also include a USB interface, a card reader interface, and the like. The network interface can optionally include a standard wired interface, a wireless interface (such as a Bluetooth interface, a WI-FI interface), etc.

The memory may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of computer equipment, and supports the operation of information processing programs and other software and/or programs. The network communication module is used to realize the communication between the various components in the memory and the communication with other hardware and software in the physical device.

Through the description of the above embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus a necessary general hardware platform, or can be implemented by hardware by applying the technical solutions of this embodiment.

Claims

A method for identifying plant species, characterized in that it includes:

Performing resolution preprocessing on the plant sample image to obtain a plant sample image with a first preset resolution;

A plurality of corresponding plant sample sub-images of a second preset resolution are respectively acquired at a plurality of preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the The first preset resolution, the plurality of preset positions are different, one of the plurality of preset positions is the center position of the plant sample image of the first preset resolution, and the other presets The plant sample sub-images of the second preset resolution corresponding to the positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

Using the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training sample set and the test sample set corresponding to the plurality of preset positions ；

Training multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions respectively, until each trained model corresponding to the multiple preset positions identifies the corresponding test sample set The recognition result meets the preset training termination condition;

The plant image to be recognized is received, and the type of the plant image to be recognized is recognized by using the trained model.
The method according to claim 1, wherein the training sample sets corresponding to the plurality of preset positions are used to train a plurality of ResNet50 convolutional neural network models, until each trained and the plurality of The recognition result of the model recognition corresponding to the test sample set corresponding to the preset positions meets the preset training termination condition, which specifically includes:

Training the corresponding model according to the preset learning rate by respectively using the training sample sets corresponding to the multiple preset positions;

If the accuracy rate of the model identification corresponding to the test sample set after training is less than the preset accuracy rate and/or the recall rate is less than the preset recall rate, then the preset learning rate is reduced, and according to the decrease After the preset learning rate, continue to train the model until the accuracy rate of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy rate and the recall rate is greater than or equal to the preset recall rate until.
The method according to claim 1, wherein the network structure of the model includes 50 layers of convolutional layers and 1 layer of fully connected layers that are sequentially connected, wherein the 50 layers of convolutional layers are divided into 5 blocks, and 5 The blocks are represented as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 includes a convolutional layer with a 7×7 convolution kernel, and conv2_x includes a convolutional layer with a 3×3 convolution kernel and 3 bottleneck building blocks; conv3_x includes 4 bottleneck building blocks; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, and each bottleneck building block includes 3 layers of convolution kernels with 3×3 convolutional layers.
The method according to any one of claims 1 to 3, wherein the performing resolution preprocessing on the plant sample image to obtain a plant sample image with a first preset resolution specifically comprises:

If the resolution of the plant sample image is greater than the first preset resolution, performing down-sampling processing on the plant sample image to obtain a plant sample image of the first preset resolution;

If the resolution of the plant sample image is less than the first preset resolution, performing upsampling processing on the plant sample image to obtain a plant sample image of the first preset resolution.
The method according to claim 4, wherein the corresponding multiple plant samples of the second preset resolution are respectively obtained at multiple preset positions of the plant sample image of the first preset resolution After the image, the method further includes:

According to the RGB value normalization processing formula, the RGB value of each pixel of the plurality of plant sample sub-images with the second preset resolution ratio is normalized, and the RGB value normalization processing formula is:

Where, N is the maximum component value of the RGB channel, and x and y are the original and normalized R, G, and G of any pixel corresponding to the plant sample sub-image of the second preset resolution, respectively. The component value of any channel of B;

Using the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training sample set and the test sample set corresponding to the plurality of preset positions , Specifically including:

The plurality of plant sample images of the second preset resolution corresponding to the plurality of preset positions after RGB value normalization processing are used to respectively establish the training samples corresponding to the plurality of preset positions Set and the test sample set.
The method according to claim 5, wherein the receiving the plant image to be recognized and using the trained model to recognize the type of the plant image to be recognized specifically comprises:

Performing resolution preprocessing on the received plant image to be recognized, so that the resolution of the plant image to be recognized is consistent with the first preset resolution;

Acquire corresponding multiple plant sub-images to be recognized at the multiple preset positions of the processed plant image to be recognized, wherein any one of the multiple plant sub-images to be recognized is The resolution is consistent with the second preset resolution;

According to the RGB value normalization processing formula, the RGB value of each pixel of the plant sub-image to be recognized corresponding to the plurality of preset positions is respectively normalized;

The sub-images of plants to be recognized corresponding to the plurality of preset positions after the normalization of the RGB values are input into the corresponding trained model to obtain the sub-images respectively corresponding to the plurality of preset positions Multiple recognition results of plant sub-images to be recognized;

According to the preset weights corresponding to the multiple preset positions, the multiple recognition results are weighted and calculated to obtain the recognition result of the image to be recognized, wherein the to-be-recognized image at the center position The preset weight corresponding to the recognized plant sub-image is greater than the preset weight corresponding to the plant sub-image to be recognized at other locations.
A plant species identification device, characterized in that it comprises:

The sample resolution processing module is used to perform resolution preprocessing on the plant sample image to obtain the plant sample image of the first preset resolution;

The sample block processing module is configured to obtain corresponding multiple plant sample sub-images of the second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, wherein the The second preset resolution is smaller than the first preset resolution, the plurality of preset positions are different from each other, and one of the plurality of preset positions is a plant sample image of the first preset resolution The plant sample sub-images of the second preset resolution corresponding to other preset positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

The sample set establishment module is configured to use the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training samples corresponding to the plurality of preset positions Set and the test sample set;

The model training module is used to train multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions, until each trained model corresponding to the multiple preset positions recognizes the corresponding The recognition result of the test sample set meets a preset training termination condition;

The image recognition module is used to receive the plant image to be recognized, and use the trained model to recognize the type of the plant image to be recognized.
The device according to claim 7, wherein the model training module specifically comprises:

The first model training unit is configured to use training sample sets corresponding to the multiple preset positions to train the corresponding model according to the preset learning rate;

The second model training unit is configured to reduce the accuracy rate of the test sample set corresponding to the model recognition after training is less than the preset accuracy rate and/or the recall rate is less than the preset recall rate Preset learning rate, and continue training the model according to the reduced preset learning rate until the accuracy of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy and the recall rate is greater than Or equal to the preset recall rate.
The device according to claim 7, wherein the network structure of the model includes 50 layers of convolutional layers and 1 layer of fully connected layers that are sequentially connected, wherein the 50 layers of convolutional layers are divided into 5 blocks, and 5 The blocks are represented as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 includes a convolutional layer with a 7×7 convolution kernel, and conv2_x includes a convolutional layer with a 3×3 convolution kernel and 3 bottleneck building blocks; conv3_x includes 4 bottleneck building blocks; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, and each bottleneck building block includes 3 layers of convolution kernels with 3×3 convolutional layers.
The device according to any one of claims 7 to 9, wherein the sample resolution processing module specifically comprises:

A sample down-sampling unit, configured to perform down-sampling processing on the plant sample image if the resolution of the plant sample image is greater than the first preset resolution to obtain a plant sample of the first preset resolution image;

A sample up-sampling unit, configured to perform up-sampling processing on the plant sample image if the resolution of the plant sample image is less than the first preset resolution to obtain a plant sample of the first preset resolution image.
The device according to claim 10, further comprising:

The RGB value normalization module is used to obtain corresponding multiple plant sample images of the second preset resolution at multiple preset positions of the plant sample image of the first preset resolution, and then according to the RGB value The normalization processing formula is to perform normalization processing on the RGB value of each pixel of the plant sample sub-images of the plurality of the second preset resolution ratios, and the RGB value normalization processing formula is:

Where, N is the maximum component value of the RGB channel, and x and y are the original and normalized R, G, and G of any pixel corresponding to the plant sample sub-image of the second preset resolution, respectively. The component value of any channel of B;

The sample set establishment module 43 is specifically configured to use the RGB value normalized processing and the plurality of plant sample images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the The training sample set and the test sample set corresponding to a plurality of preset positions.
The device according to claim 11, wherein the image recognition module specifically comprises:

An image resolution processing unit, configured to perform resolution preprocessing on the received plant image to be recognized, so that the resolution of the plant image to be recognized is consistent with the first preset resolution;

The image segmentation unit is configured to obtain corresponding multiple plant sub-images to be recognized at the multiple preset positions of the processed plant image to be recognized, wherein the multiple plants to be recognized The resolution of any one of the sub-images is consistent with the second preset resolution;

The image RGB value normalization unit is used to normalize the RGB value of each pixel of the plant sub-image to be identified corresponding to the multiple preset positions according to the RGB value normalization processing formula Chemical treatment

The image recognition unit is configured to input the sub-images of plants to be recognized corresponding to the plurality of preset positions after the normalization of the RGB values into the corresponding trained models to obtain the Multiple recognition results of plant sub-images to be recognized corresponding to each preset position;

The recognition result calculation unit is configured to perform a weighted sum calculation on the multiple recognition results according to the preset weights corresponding to the multiple preset positions to obtain the recognition result of the image to be recognized, wherein the The preset weight corresponding to the plant sub-image to be recognized at the center position is greater than the preset weight corresponding to the plant sub-image to be recognized at other positions.
A computer non-volatile readable storage medium, on which computer readable instructions are stored, characterized in that, when the computer readable instructions are executed by a processor, a method for identifying plant species includes:

Performing resolution preprocessing on the plant sample image to obtain a plant sample image with a first preset resolution;

A plurality of corresponding plant sample sub-images of a second preset resolution are respectively acquired at a plurality of preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the The first preset resolution, the plurality of preset positions are different, one of the plurality of preset positions is the center position of the plant sample image of the first preset resolution, and the other presets The plant sample sub-images of the second preset resolution corresponding to the positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

Using the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training sample set and the test sample set corresponding to the plurality of preset positions ；

Training multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions respectively, until each trained model corresponding to the multiple preset positions identifies the corresponding test sample set The recognition result meets the preset training termination condition;

The plant image to be recognized is received, and the type of the plant image to be recognized is recognized by using the trained model.
The computer non-volatile readable storage medium according to claim 13, wherein when the computer readable instructions are executed by a processor, the respective training sample sets corresponding to the plurality of preset positions are used Training multiple ResNet50 convolutional neural network models until the recognition result of the test sample set corresponding to each trained model corresponding to the multiple preset positions meets the preset training termination condition, which specifically includes:

Training the corresponding model according to the preset learning rate by respectively using the training sample sets corresponding to the multiple preset positions;

If the accuracy rate of the model identification corresponding to the test sample set after training is less than the preset accuracy rate and/or the recall rate is less than the preset recall rate, then the preset learning rate is reduced, and according to the decrease After the preset learning rate, continue to train the model until the accuracy rate of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy rate and the recall rate is greater than or equal to the preset recall rate until.
The computer non-volatile readable storage medium according to claim 13, wherein when the computer readable instructions are executed by a processor, the network structure for executing the model comprises 50 layers of convolutions connected in sequence. Layer and 1 layer fully connected layer, of which, the 50 layer convolutional layer is divided into 5 blocks, and the 5 blocks are represented as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 including a convolution kernel of 7×7 Layer, conv2_x includes a convolutional layer with a convolution kernel of 3×3 and 3 bottleneck building blocks; conv3_x includes 4 bottleneck building blocks; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, each bottleneck The building block includes 3 convolutional layers with a 3×3 convolution kernel.
The computer non-volatile readable storage medium according to any one of claims 13 to 15, wherein the computer readable instruction is executed by a processor to realize the resolution preprocessing of the plant sample image To obtain a plant sample image of the first preset resolution, which specifically includes:

If the resolution of the plant sample image is greater than the first preset resolution, performing down-sampling processing on the plant sample image to obtain a plant sample image of the first preset resolution;

If the resolution of the plant sample image is less than the first preset resolution, performing upsampling processing on the plant sample image to obtain a plant sample image of the first preset resolution.
A computer device, including a memory, a processor, and computer readable instructions stored on the memory and running on the processor, wherein the processor executes the computer readable instructions to realize a plant species identification method ,include:

Performing resolution preprocessing on the plant sample image to obtain a plant sample image with a first preset resolution;

A plurality of corresponding plant sample sub-images of a second preset resolution are respectively acquired at a plurality of preset positions of the plant sample image of the first preset resolution, wherein the second preset resolution is smaller than the The first preset resolution, the plurality of preset positions are different, one of the plurality of preset positions is the center position of the plant sample image of the first preset resolution, and the other presets The plant sample sub-images of the second preset resolution corresponding to the positions do not overlap each other and can be combined into a complete plant sample image of the first preset resolution;

Using the plurality of plant sample sub-images of the second preset resolution corresponding to the plurality of preset positions to respectively establish the training sample set and the test sample set corresponding to the plurality of preset positions ；

Training multiple ResNet50 convolutional neural network models using the training sample sets corresponding to the multiple preset positions respectively, until each trained model corresponding to the multiple preset positions identifies the corresponding test sample set The recognition result meets the preset training termination condition;

The plant image to be recognized is received, and the type of the plant image to be recognized is recognized by using the trained model.
The computer device according to claim 17, wherein when the processor executes the computer-readable instructions, the processor implements the training of multiple ResNet50 convolutions using training sample sets corresponding to the multiple preset positions. The neural network model until the recognition result of the test sample set corresponding to each trained model corresponding to the multiple preset positions meets the preset training termination condition, which specifically includes:

Training the corresponding model according to the preset learning rate by respectively using the training sample sets corresponding to the multiple preset positions;

If the accuracy rate of the model identification corresponding to the test sample set after training is less than the preset accuracy rate and/or the recall rate is less than the preset recall rate, then the preset learning rate is reduced, and according to the decrease After the preset learning rate, continue to train the model until the accuracy rate of the trained model identifying the corresponding test sample set is greater than or equal to the preset accuracy rate and the recall rate is greater than or equal to the preset recall rate until.
The computer device according to claim 17, wherein the network structure for implementing the model when the processor executes the computer-readable instructions includes 50 layers of convolutional layers and 1 layer of fully connected in sequence. The 50 layers of convolutional layers are divided into 5 blocks, and the 5 blocks are represented as conv1, conv2_x, conv3_x, conv4_x, conv5_x, conv1 includes a convolutional layer with a convolution kernel of 7×7, and conv2_x includes a convolution The product core is a 3×3 convolutional layer and 3 bottleneck building blocks; conv3_x includes 4 bottleneck building blocks; conv4_x includes 6 bottleneck building blocks; conv5_x includes 3 bottleneck building blocks, each bottleneck building block includes 3 layers of volume The product kernel is a 3×3 convolutional layer.
The computer device according to any one of claims 17 to 19, wherein when the processor executes the computer-readable instruction, the resolution preprocessing is performed on the plant sample image to obtain the first preset Resolution plant sample images, including:

If the resolution of the plant sample image is greater than the first preset resolution, performing down-sampling processing on the plant sample image to obtain a plant sample image of the first preset resolution;

If the resolution of the plant sample image is less than the first preset resolution, performing upsampling processing on the plant sample image to obtain a plant sample image of the first preset resolution.