Beginner-Friendly Topic

Take your time - it's perfectly normal to re-read this topic 2-3 times. Try the interactive code editor below to run code yourself. Use the Q&A section to check your understanding before moving on.You've got this!

Flipping Images

Flipping creates mirror images. It is simple, fast, and one of the most common data augmentation techniques used to increase training data diversity.

6 min•By Priygop Team•Updated 2026

Flipping with cv2.flip()

import cv2

image = cv2.imread("photo.jpg")

# Flip codes:
# 1  = horizontal flip (left-right mirror)
# 0  = vertical flip (upside down)
# -1 = both horizontal and vertical

horizontal = cv2.flip(image, 1)   # Mirror left-right
vertical   = cv2.flip(image, 0)   # Flip upside down
both       = cv2.flip(image, -1)  # Rotate 180 degrees

cv2.imwrite("flip_horizontal.jpg", horizontal)
cv2.imwrite("flip_vertical.jpg", vertical)
cv2.imwrite("flip_both.jpg", both)
print("Flip operations complete")

# Data augmentation example:
# Flipping effectively doubles your training data
def augment_image(image):
    """Create augmented versions of an image."""
    augmented = [image]
    augmented.append(cv2.flip(image, 1))   # Horizontal flip
    augmented.append(cv2.flip(image, 0))   # Vertical flip
    return augmented

augmented_set = augment_image(image)
print(f"Original: 1 image → Augmented: {len(augmented_set)} images")

Diagram

Loading diagram…

Machine Learning follows a structured pipeline from data to deployment

Topics in This Module

Flipping with cv2.flip()

import cv2

image = cv2.imread("photo.jpg")

# Flip codes:
# 1  = horizontal flip (left-right mirror)
# 0  = vertical flip (upside down)
# -1 = both horizontal and vertical

horizontal = cv2.flip(image, 1)   # Mirror left-right
vertical   = cv2.flip(image, 0)   # Flip upside down
both       = cv2.flip(image, -1)  # Rotate 180 degrees

cv2.imwrite("flip_horizontal.jpg", horizontal)
cv2.imwrite("flip_vertical.jpg", vertical)
cv2.imwrite("flip_both.jpg", both)
print("Flip operations complete")

# Data augmentation example:
# Flipping effectively doubles your training data
def augment_image(image):
    """Create augmented versions of an image."""
    augmented = [image]
    augmented.append(cv2.flip(image, 1))   # Horizontal flip
    augmented.append(cv2.flip(image, 0))   # Vertical flip
    return augmented

augmented_set = augment_image(image)
print(f"Original: 1 image → Augmented: {len(augmented_set)} images")

Diagram

Loading diagram…

Machine Learning follows a structured pipeline from data to deployment

Topics in This Module