Scribd
Upload
11 views2 pages

Corn Det

This document outlines a Python script for loading a dataset of images related to corn diseases, training a K-Nearest Neighbors classifier, and evaluating its performance. It includes functions for predicting the class of a single image and handling potential errors during image processing and prediction display. The script utilizes libraries such as OpenCV, NumPy, Matplotlib, and Scikit-learn.

Uploaded by

jonard.tigas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
11 views2 pages

Corn Det

This document outlines a Python script for loading a dataset of images related to corn diseases, training a K-Nearest Neighbors classifier, and evaluating its performance. It includes functions for predicting the class of a single image and handling potential errors during image processing and prediction display. The script utilizes libraries such as OpenCV, NumPy, Matplotlib, and Scikit-learn.

Uploaded by

jonard.tigas
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as TXT, PDF, TXT or read online on Scribd
You are on page 1/ 2

import os

import cv2
import numpy as np
import matplotlib
matplotlib.use('TkAgg') # Use a GUI backend for matplotlib
import matplotlib.backends.backend_agg as agg
import matplotlib.pyplot as plt
from sklearn.neighbors import KNeighborsClassifier
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report

# Config
IMG_SIZE = 100
DATASET_PATH = "corn_dataset" # Folder containing subfolders: 'blight', 'rust',
etc.

# Load Dataset
print("[INFO] Loading images...")
images = []
labels = []

classes = os.listdir(DATASET_PATH)
print(f"[INFO] Classes found: {classes}")

for label in classes:


folder = os.path.join(DATASET_PATH, label)
for file in os.listdir(folder):
path = os.path.join(folder, file)
img = cv2.imread(path)
if img is not None:
img = cv2.resize(img, (IMG_SIZE, IMG_SIZE))
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
flat = gray.flatten() / 255.0
images.append(flat)
labels.append(label)

images = np.array(images)
labels = np.array(labels)
print(f"[INFO] Loaded {len(images)} images.")

# Train Model
X_train, X_test, y_train, y_test = train_test_split(images, labels, test_size=0.2,
random_state=42)
knn = KNeighborsClassifier(n_neighbors=3)
print("[INFO] Training model...")
knn.fit(X_train, y_train)
print("[INFO] Model trained.")

# Evaluate
print("\n[INFO] Evaluating model:")
y_pred = knn.predict(X_test)
print(classification_report(y_test, y_pred))

# Predict Single Image


def predict_image(image_path):
try:
if not os.path.exists(image_path):
raise FileNotFoundError(f"Image not found: {image_path}")
img = cv2.imread(image_path)
if img is None:
raise ValueError("Image is unreadable or corrupted.")

img_resized = cv2.resize(img, (IMG_SIZE, IMG_SIZE))


gray = cv2.cvtColor(img_resized, cv2.COLOR_BGR2GRAY)
flat = gray.flatten() / 255.0
prediction = knn.predict([flat])[0]

# Display the image and prediction


try:
plt.figure()
plt.imshow(cv2.cvtColor(img, cv2.COLOR_BGR2RGB))
plt.title(f"Predicted: {prediction}")
plt.axis("off")
plt.show()
except Exception as e:
print(f"[WARNING] GUI backend failed, saving image instead: {e}")
output_path = "prediction_output.png"
plt.savefig(output_path)
print(f"[INFO] Prediction saved to: {output_path}")

print(f"[RESULT] The image is predicted as: {prediction}")

except Exception as e:
print(f"[ERROR] Couldn't predict image: {e}")

You might also like