Computer Vision with Python

Computer Vision enables machines to interpret and understand visual information from images and videos.

OpenCV Basics

import cv2
import matplotlib.pyplot as plt

# Read and display an image
image = cv2.imread('photo.jpg')
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)

plt.figure(figsize=(8, 6))
plt.imshow(image_rgb)
plt.axis('off')
plt.show()

# Get image dimensions
print(f"Shape: {image.shape}")  # (height, width, channels)

Basic Image Processing

# Convert to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

# Blur
blurred = cv2.GaussianBlur(gray, (5, 5), 0)

# Edge detection
edges = cv2.Canny(blurred, 50, 150)

# Thresholding
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

# Resize
resized = cv2.resize(image, (224, 224))

Face Detection

# Load face cascade
face_cascade = cv2.CascadeClassifier(
    cv2.data.haarcascades + 'haarcascade_frontalface_default.xml'
)

# Detect faces
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, 1.1, 4)

# Draw rectangles
for (x, y, w, h) in faces:
    cv2.rectangle(image, (x, y), (x+w, y+h), (255, 0, 0), 2)

cv2.imshow('Face Detection', image)
cv2.waitKey(0)
cv2.destroyAllWindows()

Image Classification with CNN

from tensorflow import keras
from tensorflow.keras import layers

model = keras.Sequential([
    layers.Conv2D(32, 3, activation='relu', input_shape=(224, 224, 3)),
    layers.MaxPooling2D(),
    layers.Conv2D(64, 3, activation='relu'),
    layers.MaxPooling2D(),
    layers.Conv2D(128, 3, activation='relu'),
    layers.MaxPooling2D(),
    layers.Flatten(),
    layers.Dense(128, activation='relu'),
    layers.Dropout(0.5),
    layers.Dense(10, activation='softmax')
])

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

Summary

You learned computer vision with OpenCV and CNNs. Next, we'll explore natural language processing.