Computer Vision with Python: Analyze Images Using OpenCV and Deep Learning

 

---

🧠 Part 7: Computer Vision with OpenCV and Deep Learning

---

👁️ What Is Computer Vision?

Computer Vision (CV) enables machines to “see” and understand images or videos. It’s used in:

• Face detection

• Object recognition

• Medical imaging

• Self-driving cars

---

🧰 Tools We'll Use

• OpenCV – Image processing library

• TensorFlow/Keras – Deep learning models (CNNs)

• Pre-trained Models – For fast and accurate image classification

Install with:

pip install opencv-python tensorflow

---

🖼️ Step-by-Step: Image Classification with a CNN

---

🗂️ Step 1: Load & Preprocess the CIFAR-10 Dataset

import tensorflow as tf
from tensorflow.keras.datasets import cifar10
import matplotlib.pyplot as plt

(X_train, y_train), (X_test, y_test) = cifar10.load_data()
X_train, X_test = X_train / 255.0, X_test / 255.0

# Show a sample image
plt.imshow(X_train[0])
plt.title(f"Label: {y_train[0][0]}")
plt.show()

---

🧠 Step 2: Build a Convolutional Neural Network (CNN)

model = tf.keras.models.Sequential([
    tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(32,32,3)),
    tf.keras.layers.MaxPooling2D((2,2)),
    tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
    tf.keras.layers.MaxPooling2D((2,2)),
    tf.keras.layers.Flatten(),
    tf.keras.layers.Dense(64, activation='relu'),
    tf.keras.layers.Dense(10, activation='softmax')
])

---

⚙️ Step 3: Compile & Train the Model

model.compile(optimizer='adam',
              loss='sparse_categorical_crossentropy',
              metrics=['accuracy'])

model.fit(X_train, y_train, epochs=10, validation_split=0.2)

---

📈 Step 4: Evaluate and Predict

test_loss, test_acc = model.evaluate(X_test, y_test)
print(f"Test Accuracy: {test_acc:.2f}")

predictions = model.predict(X_test)
print("Predicted class:", predictions[0].argmax())

---

🧰 Bonus: Load and Process Custom Images with OpenCV

import cv2

image = cv2.imread('your_image.jpg')
resized = cv2.resize(image, (32, 32)) / 255.0
reshaped = resized.reshape(1, 32, 32, 3)

prediction = model.predict(reshaped)
print("Predicted class:", prediction.argmax())

---

🔄 Alternative: Use Pretrained Model (MobileNet)

from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input, decode_predictions

model = MobileNetV2(weights='imagenet')

from tensorflow.keras.preprocessing import image
import numpy as np

img = image.load_img('your_image.jpg', target_size=(224, 224))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)
print("Predicted:", decode_predictions(preds, top=1)[0])

---

🧪 Practice Challenge

• Try using other datasets like Fashion MNIST or CelebA

• Detect faces using cv2.CascadeClassifier

• Implement edge detection with OpenCV

---

🎓 What You’ve Learned:

• Image classification using CNNs

• Using OpenCV for image processing

• How to use pre-trained models for instant predictions

---

🧭 What’s Next?

In Part 8, we’ll explore Reinforcement Learning (RL)—where agents learn to make decisions through trial and error using rewards and penalties.

← Previous Next →