Identification of Pathological Disease in Plants — Powered by Intel® Distribution of OpenVINO™…

Source: Deep Learning on Medium


Go to the profile of Risab Biswas

This project uses an algorithm for the easy identification or classification of pathological diseases in plant species via a mobile or web application. The entire system is an intelligent framework that enables users to identify a pathological disease via a deep learning and computer vision based smart system– users merely need to open the app, click a picture, and view the result. Input for the system can be either an image or live video feed of the plant species, and the result is in the form of a bounding box with the name of the identified pathological disease and the accuracy of the identification. Once the identification is accurately done the user can get more insights into the cause of the disease and also how to do a proper medication.

Figure 1: Identification of Blister Blight in Tea Leaves

This article examines how the solution is built using deep learning and computer vision algorithms powered by the Intel® Distribution of OpenVINO™ toolkit Model Optimizer.

Use Case for the Application

In modern Agriculture and Forestry purposes Plant Pathological Research is very much essential for the crop improvement. Every year, a huge number of crops are damaged by pathogen attack. In most of the cases, Farmers suffer huge losses due to severe pathogenic infestation. For crop improvement, the first and foremost key point is disease identification. After proper identification of diseases, we will be able to treat the diseases. Most of the cases lab-oriented research is time taking and very much expendable but instant identification of plant diseases by using modern technology is more suitable by being cost effective and nearly instantaneous. This methodology will help us to identify the diseases in various parts of the plants. Above 95 % accuracy and most probable identification is possible by using this methodology. The results can be authenticated by lab-oriented experimentation’s or can be cross validated by some expert in the field.

Identified Diseases

1. Blister Blight of Tea (Family: Theaceae)

2. Citrus Canker (Happens in Citrus Plants, Family: Rutaceae)

3. Early Blight (Happens in Tomato, Potato and Egg Plant, Family: Solanaceae)

4. Late Blight (Happens in Tomato, Potato and Egg Plant, Family: Solanaceae)

5. Powdery Mildew (Happens in Wheat, Barley and other Cereals, Legumes, Grape, Gourds and melons, infection happens more in Cucurbitaceae family)

The reason why we are focusing particularly on these disease at the first place is because these are the pathogenic diseases that effects the crops in a large scale and the crops that they effect are grown in the largest scale. These plants are very common in the agricultural line-up. We are identifying diseases both in Commercially important plants such as Tea, which is both consumed and exported on a huge scale. Also we are considering Non-Commercial plants such as Tomato, Potato, Egg Plant, Legumes, Gourds etc.

Overview and Architecture

As illustrated above, the primary objective of the project is to identify pathological disease in plant species correctly and with the utmost precision. The output of the model is the correctly identified name of the pathological disease along with the degree of confidence/accuracy. The input can be an image, video, or live camera feed of a flower, fruit, or leaf of the plant that is seen effected by some disease.

The overall architecture is shown below:

Figure 2: Architectural flow

1. Generate the data for training and testing the classifications from Google Images* search service. The optimal way to do this is to write a web crawler in Python* and download the images as .jpeg files. Next, label all the images and generate an .xml file corresponding to each image.

2. Once the images are labeled, generate the TensorFlow* records that will serve as the input data for the training model to train the new object detection classifier. The image .xml data is used to create .csv files containing all the data for the training and testing images. Prior to training, create a label map and edit the training configuration file. The label map tells the trainer what each object is by defining a mapping of class names to class ID numbers.

3. Train the classification model by using the Intel® Optimization for TensorFlow* to create a model. If everything is set up correctly, TensorFlow will initialize the training. The initialization can take up to 30 seconds before the actual training begins, once it does it will look like this:

Figure 3: Training of the Model

4. Each step of training reports the loss, which starts high and declines steadily as the training progresses. For example, training on the Faster-RCNN-Inception-V2 model started at about 3.0 and quickly dropped below 0.8. It is recommended to train until the loss consistently falls below 0.05; which takes approximately 40,000 steps, or about two hours (depending on CPU and GPU performance).

Note: The loss numbers will vary if a different model is used. MobileNet-SSD starts with a loss of about 20 and should be trained until the loss is consistently under two.

View the progress of the training job by using TensorBoard*.

This step creates a webpage on the local machine at YourPCName:6006 and can be viewed via your web browser. The TensorBoard page provides information and graphs that show how the training is progressing. One important chart is the Loss graph, which shows the overall loss of the classifier over time.

Figure 4: Log-loss graph visualization on TensorBoard*

The training routine saves checkpoints periodically, about every five minutes. To terminate the training, press Ctrl+C while in the command prompt window. Wait until just after a checkpoint has been saved to terminate the training; it can be resumed later, restarting from the last saved checkpoint. The checkpoint at the highest number of steps will be used to generate the frozen inference graph.

5. Now that training is complete, the last step is to generate the frozen inference graph (. pb file) which creates a frozen_inference_graph.pb file in the \object_detection\inference_graph folder. The. pb file contains the object detection classifier.

6. The next focus is on using the Intel® Distribution of OpenVINO™ toolkit to run interfaces. The classifier algorithm helps to identify the plant correctly. First, optimize the model to create an *.xml and *.bin file.

Figure 5: Diagram of the Intel® Distribution of OpenVINO™ toolkit flow

7. Use the script from the <INSTALL_DIR>/deployment_tools/model_optimizer directory to run the model optimizer and convert the model to the intermediate representation (IR).

Note: Some models require using additional arguments to specify conversion parameters, such as — scale, — scale_values, — mean_values, — mean_file. To learn when to use these parameters, refer to Converting a Model Using General Conversion Parameters.

8. The script is the universal entry point that can deduce the framework that has produced the input model by a standard extension of the model file:

· .caffemodel — Caffe* models

· .pb — TensorFlow* models

· .params — MXNet* models

· .onnx — ONNX* models

· .nnet — Kaldi* models.

9. Since the model is built on TensorFlow and the frozen inference graph is already generated (. pb file) as mentioned in step 5, use that particular file and run the script.

10. This approach uses a model optimizer to fine-tune the model for a user application to consume. The .xml and .bin files generated from the model optimizer are consumed by the inference engine using the Python API, which is essentially a wrapper built on top of C++ core codes.

Workflow Steps:

Gather Data

When training a robust classifier, the training images should have random objects in the image along with the desired objects, as well as a variety of backgrounds and lighting conditions. In some images, the desired object should be partially obscured, overlapped with something else, or only halfway in the picture. This article uses the package icrawler, which is provided by pypi. For details, go to icrawler pypi.

To install icrawler, run the following command on the Anaconda* prompt:

pip install icrawler

Next, import the icrawler package and write a small snippet of code in Python to fetch the images from Google*.

The command shown below uses a keyword for the web crawler to gather all the results from Google Images* search service and saves them in .jpeg format on the disk. Provide the number of desired images as an input to the code.

from icrawler.builtin import GoogleImageCrawler
for keyword in ['Hibiscus rosa-sinensis', Marigold]:
google_crawler = GoogleImageCrawler(parser_threads=2,
keyword=keyword, max_num=300, min_size=(200, 200))

Make sure the images are each less than 200KB, and their resolution does not exceed 720×1280. The larger the images, the longer it will take to train the classifier. Use a Python script to reduce the size of the images.

Label Pictures

Here’s the fun part: labeling the desired objects in every picture. LabelImg is a useful tool for this purpose; its GitHub* page has clear instructions on how to install and use it.

  1. LabelImg GitHub Documentation

2. LabelImg Download File

Point LabelImg to your \images\train directory, and then draw a box around the object in each image. Repeat the process for all the images in the \images\test directory. This process will take a while!

Figure 6: Labeling the objects in an image
Figure 7: Labeling the object in the image

LabelImg saves an .xml file containing the label data for each image. These .xml files will be used to generate TensorFlow records, which are among the inputs to the TensorFlow trainer. As each image is labeled and saved, there will be one .xml file for each image in the \test and \train directories.

Here are 300 images for each class of pathological disease, split for training and testing.

Capture Frames for Processing

For any application that involves the use of image, video, or live camera feed, it is necessary to capture the frames. This process is easy and straightforward to do using OpenCV. Once the frames are captured, iterate through each frame, and pass it through the recognition engine for detection.

To provide an image as an input to the model, use the code described below:

import cv2
IMAGE_NAME = 'test1.jpg'
# Grab path to current working directory
CWD_P # Path to image
PATH_TO_IMAGE = os.path.join(CWD_PATH,IMAGE_NAME)ATH = os.getcwd()
image = cv2.imread(PATH_TO_IMAGE)
image_expanded = np.expand_dims(image, axis=0)

To provide videos as an input to the model, use the following code:

import cv2
cap = cv2.VideoCapture(0)
ret, image_np =

To provide live camera feed as an input to the model, use the code below:

import cv2
# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,1280)
ret = video.set(4,720)

The above piece of code captures the video frames. The third line is the one that must be inside a loop as it captures frames.

Pathological Disease Identification Using TensorFlow Classifier

First, include all the required packages:

# Import packages
import os
import cv2
import numpy as np
import tensorflow as tf
import sys
# This is needed since the notebook is stored in the object_detection folder.
# Import utilites
from utils import label_map_util
from utils import visualization_utils as vis_util
# Name of the directory containing the object detection module we're using
MODEL_NAME = 'inference_graph'
# Grab path to current working directory
CWD_PATH = os.getcwd()
# Path to frozen detection graph. pb file, which contains the model that is used for object detection.
PATH_TO_CKPT = os.path.join(CWD_PATH,MODEL_NAME,'frozen_inference_graph.pb')
# Path to label map file
PATH_TO_LABELS = os.path.join(CWD_PATH,'training','labelmap.pbtxt')

Include in the classifier code how many classes of pathological diseases to recognize. For this experimental research purpose, we are targeting five pathological diseases: Blister Blight in Tea, Citrus Canker, Early Blight, Late Blight, Powdery Mildew in Cucurbitaceae.

# Number of classes the object detector can identify

Next, load the TensorFlow model:

# Load the Tensorflow model into memory.
detection_graph = tf.Graph()
with detection_graph.as_default():
od_graph_def = tf.GraphDef()
with tf.gfile.GFile(PATH_TO_CKPT, 'rb') as fid:
serialized_graph =
tf.import_graph_def(od_graph_def, name='')
sess = tf.Session(graph=detection_graph)
# Define input and output tensors (i.e. data) for the object detection classifier
# Input tensor is the image
image_tensor = detection_graph.get_tensor_by_name('image_tensor:0')
# Output tensors are the detection boxes, scores, and classes
# Each box represents a part of the image where a particular object was detected
detection_boxes = detection_graph.get_tensor_by_name('detection_boxes:0')
# Each score represents level of confidence for each of the objects.
# The score is shown on the result image, together with the class label.
detection_scores = detection_graph.get_tensor_by_name('detection_scores:0')
detection_classes = detection_graph.get_tensor_by_name('detection_classes:0')
# Number of objects detected
num_detections = detection_graph.get_tensor_by_name('num_detections:0')

Load the input and view the output window initiated by the model:

# Initialize webcam feed
video = cv2.VideoCapture(0)
ret = video.set(3,1280)
ret = video.set(4,720)
while (True):
# Acquire frame and expand frame dimensions to have shape: [1, None, None, 3]
# i.e. a single-column array, where each item in the column has the pixel RGB value
ret, frame =
frame_expanded = np.expand_dims(frame, axis=0)
# Perform the actual detection by running the model with the image as input
(boxes, scores, classes, num) =[detection_boxes, detection_scores, detection_classes, num_detections],
feed_dict= {image_tensor: frame_expanded})
 # Draw the results of the detection (aka 'visulaize the results')
# All the results have been drawn on the frame, so it's time to display it.
cv2.imshow(Plant Anatomy, frame)
# Press 'q' to quit
if cv2.waitKey(1) == ord('q'):
# Clean up

Characteristics and Architectural Details:

1. Architecture: The model is having two variants, one built in Faster RCNN and the other in SSD Mobile net (ssd_mobilenet_v2_coco). Final one is on the SSD Mobile net, as SSD Mobile net model is well supported by both Intel® Distribution of OpenVINO™ Toolkit and TensorFlow Lite.

2. Back-end Framework: Intel® Optimization for TensorFlow*.

3. OpenCV for the Computer Vision Algorithm building.

4. Dataset: High Quality Images taken from Google Images using Web Crawling. This is one of the bottleneck’s I am facing. Since going into the fields and clicking images is one of the most tedious and time-consuming approach that’s why I went for the images available on the internet. But, for my present approach I need high quality and a huge amount of data, as the classes are increasing. I will gather the images and create my own Dataset. In future that can be open sourced so that people can use that.

5. Log Loss: I am able to drop down the log loss up-to 0.0173 at a step count of 32,517 after 14 hours of training. In terms of accuracy, as the inference shows that it ranges between 85–95%, depending upon the image or image that has been provided for the inference.

6. Mobile Application: The mobile application is being built for the Android Platform as of now. I am using TensorFlow Lite and Android Studio for building it.

7. Model Optimization and Inference on PC/Laptop or any other edge device other than Smart phone is being carried out by Intel® Distribution of OpenVINO™ Toolkit.

Sample Images from the Test Inference on Edge Device

Observe how the model has successfully identified the pathological disease:

· Blister Blight in Tea:

Figure 8: Pathological Disease Identifier in action

The above image from the test run shows that the model successfully detects the disease in the effected region of the plant. It creates a bounding box and displays the name of the pathological disease along with the accuracy in percentage. The above pathological disease is Blister Blight of Tea and is correctly identified by the model. It also shows the accuracy of detection in percentage; in this case, the recognition accuracy is 95% and 87% respectively.

Figure 9: Identifying Blister Blight in Tea Plants
Figure 10: Identifying Blister Blight in Tea Plants

· Citrus Canker:

Figure 11: Identifying Citrus Canker in Oranges

As shown in the above image, the model identifies the other class of pathological disease correctly and accurately as well. Moreover, it is evident that if more than one plant is affected by the disease, it separates them by creating a bounding box. The above pathological disease is Citrus Canker, it particularly happens mostly in citrus plants. It is correctly identified by the model as shown on the above image. The accuracy of this test case is 98% and 99%.

Figure 12: Identifying Citrus Canker in Citrus Leave
Figure 13: Identifying Citrus Canker in Oranges

· Early Blight:

Figure 14: Identifying Early Blight in Tomato

As shown in the above image, the model identifies the other class of pathological disease correctly and accurately as well. The above pathological disease is Early Blight, it can majorly effect Fruits, Leaves as well as Stems of the affected plant. It is correctly identified by the model as shown on the above image. The accuracy of this test case is again 98% and 99%.

Figure 15: Identifying Early Blight affecting a Leaf

· Late Blight:

Figure 16: Identifying Late Blight in a Tomato Leaf

As shown in the above image, the model identifies the other class of pathological disease correctly and accurately as well. The above pathological disease is Late Blight, it too can majorly effect Fruits, Leaves as well as Stems of the affected plant. It is correctly identified by the model as shown on the above image. The accuracy of this test case is 97%.

Figure 17: Identifying Late Blight Affecting Stem of a Plant

· Powdery Mildew:

Figure 18: Identifying Powdery Mildew in leaves of Cucurbitaceae
Figure 19: Identifying Powdery Mildew in leaves of Cucurbitaceae


The above illustrates the importance of identifying pathological diseases in plants in the modern world agricultural practice and how this solution shows accurate results in identifying the diseases in plant species correctly. The model gives a good use case of deep learning and computer vision; introducing a computer vision recipe using the model optimizer and inference engine of the Intel® Distribution of OpenVINO™ toolkit. Model Optimization helps us in getting good frames per second (FPS) while doing inference on live video feed. The project is into its next phase, adding more features such as identification of more diseases and prototyping it into a mobile application.

Link to related Publications

· Earth Day Special Coverage

· How Novozymes and Intel use citizen scientists

· Publication on LiveMint

· Publication on FutureFive, NewZealand

· Earth Day Publication

· Publication on Economics Time