Geometric transforms (rotate, flip, crop) in Computer Vision - Cheat Sheet & Quick Revision

Recall & Review

beginner

What is the purpose of geometric transforms like rotate, flip, and crop in computer vision?

They help change the position or shape of images to augment data, improve model robustness, or focus on important parts of the image.

beginner

How does rotating an image affect its pixel positions?

Rotating an image moves each pixel around a center point by a certain angle, changing their coordinates but keeping the image content intact.

beginner

What is the difference between horizontal flip and vertical flip?

Horizontal flip mirrors the image left to right, while vertical flip mirrors it top to bottom.

beginner

Why is cropping useful in image processing?

Cropping cuts out a part of the image to focus on important details or remove unwanted areas, which can help models learn better.

intermediate

What should you be careful about when applying geometric transforms during training?

Ensure transforms do not distort important features or labels, and keep the image size consistent if required by the model.

Which geometric transform flips an image top to bottom?

A Vertical flip

B Rotate 90 degrees

C Horizontal flip

D Crop

Vertical flip mirrors the image along the horizontal axis, flipping it top to bottom.

What happens to pixel positions when you rotate an image by 90 degrees?

A Pixels stay in the same place

B Pixels move around the center point

C Pixels are flipped horizontally

D Pixels are cropped

Rotation moves pixels around the image center by the rotation angle.

Why do we crop images in computer vision tasks?

A To focus on important parts

B To add noise

C To flip the image

D To rotate the image

Cropping helps focus on important details or remove irrelevant parts.

Which transform would you use to create a mirror image left to right?

A Vertical flip

B Rotate 180 degrees

C Horizontal flip

D Crop

Horizontal flip mirrors the image along the vertical axis.

What is a key caution when applying geometric transforms during training?

A Transforms always improve accuracy

B Transforms remove labels

C Transforms reduce image size

D Transforms can distort important features

Transforms can distort features if not applied carefully, affecting model learning.

Explain how rotating, flipping, and cropping images help in training computer vision models.

Think about how changing images can help models see more variety.

Describe the difference between horizontal flip and vertical flip and when you might use each.

Imagine flipping a photo like a page in a book or turning it upside down.

Practice

1. Which geometric transform flips an image horizontally, like looking in a mirror?

easy

A. Horizontal flip

B. Rotate 90 degrees

C. Crop center

D. Vertical flip

Solution

1. Step 1: Understand horizontal flip

   Horizontal flip reverses the image left to right, like a mirror reflection.

2. Step 2: Compare with other transforms

   Rotate changes orientation, crop cuts part of image, vertical flip flips top to bottom.

3. Final Answer:

   Horizontal flip -> Option A

4. Quick Check:

   Mirror image = Horizontal flip [OK]

Hint: Mirror effect means horizontal flip [OK]

Common Mistakes:

• Confusing vertical flip with horizontal flip
• Thinking rotate is flipping
• Mixing crop with flip

2. Which Python code correctly rotates an image by 90 degrees clockwise using OpenCV?

easy

A. rotated = cv2.crop(image, (0,0,100,100))

B. rotated = cv2.flip(image, 1)

C. rotated = cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE)

D. rotated = cv2.rotate(image, cv2.ROTATE_180)

Solution

1. Step 1: Identify OpenCV rotate syntax

   cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE) rotates image 90 degrees clockwise.

2. Step 2: Check other options

   Flip flips image, crop is not a cv2 function, ROTATE_180 rotates 180 degrees, not 90.

3. Final Answer:

   rotated = cv2.rotate(image, cv2.ROTATE_90_CLOCKWISE) -> Option C

4. Quick Check:

   Rotate 90 clockwise = cv2.ROTATE_90_CLOCKWISE [OK]

Hint: Use cv2.rotate with ROTATE_90_CLOCKWISE for 90° turn [OK]

Common Mistakes:

• Using flip instead of rotate
• Wrong rotate constant
• Trying crop as a cv2 function

3. What will be the shape of the image after applying this code?

import cv2
image = cv2.imread('img.jpg')
cropped = image[50:150, 30:130]

medium

A. (100, 100, 3)

B. (150, 130, 3)

C. (80, 100, 3)

D. (100, 80, 3)

Solution

1. Step 1: Calculate crop height

   Height = 150 - 50 = 100 pixels.

2. Step 2: Calculate crop width

   Width = 130 - 30 = 100 pixels.

3. Step 3: Confirm channels

   Image has 3 color channels (RGB/BGR).

4. Final Answer:

   (100, 100, 3) -> Option A

5. Quick Check:

   Crop size = (height, width, channels) = (100, 100, 3) [OK]

Hint: Subtract start from end index for height and width [OK]

Common Mistakes:

• Mixing width and height order
• Forgetting zero-based indexing
• Ignoring color channels

4. This code tries to flip an image vertically but causes an error. What is wrong?

import cv2
image = cv2.imread('img.jpg')
flipped = cv2.flip(image, 2)

medium

A. image must be grayscale for flip

B. Flip code 2 is invalid; use 0 for vertical flip

C. cv2.flip requires three arguments

D. cv2.flip does not flip images

Solution

1. Step 1: Check cv2.flip flipCode values

   flipCode=0 flips vertically, 1 flips horizontally, -1 flips both axes.

2. Step 2: Identify invalid flipCode

   flipCode=2 is invalid and causes error.

3. Final Answer:

   Flip code 2 is invalid; use 0 for vertical flip -> Option B

4. Quick Check:

   Vertical flip = flipCode 0 [OK]

Hint: Use flipCode 0 for vertical flip in cv2.flip [OK]

Common Mistakes:

• Using wrong flipCode values
• Thinking flip needs grayscale
• Assuming cv2.flip needs extra args

5. You want to rotate an image 90 degrees clockwise and then crop the central 100x100 pixels. Which code correctly does this?

hard

A. crop = img[50:150, 50:150]
rot = cv2.rotate(crop, cv2.ROTATE_90_CLOCKWISE)

B. rot = cv2.flip(img, 1)
crop = rot[rot.shape[0]//2-50:rot.shape[0]//2+50, rot.shape[1]//2-50:rot.shape[1]//2+50]

C. rot = cv2.rotate(img, cv2.ROTATE_180)
crop = rot[0:100, 0:100]

D. rot = cv2.rotate(img, cv2.ROTATE_90_CLOCKWISE)
crop = rot[rot.shape[0]//2-50:rot.shape[0]//2+50, rot.shape[1]//2-50:rot.shape[1]//2+50]

Solution

1. Step 1: Rotate image 90 degrees clockwise

   Use cv2.rotate with ROTATE_90_CLOCKWISE on original image.

2. Step 2: Crop center 100x100 pixels

   Calculate center indices and slice 50 pixels before and after center in both dimensions.

3. Step 3: Verify order and correctness

   Rotation first, then crop center; other options rotate wrong angle or crop before rotate.

4. Final Answer:

   Rotate then crop center 100x100 -> Option D

5. Quick Check:

   Rotate 90° clockwise then center crop = rot = cv2.rotate(img, cv2.ROTATE_90_CLOCKWISE) crop = rot[rot.shape[0]//2-50:rot.shape[0]//2+50, rot.shape[1]//2-50:rot.shape[1]//2+50] [OK]

Hint: Rotate first, then crop center using shape indices [OK]

Common Mistakes:

• Cropping before rotating changes crop area
• Using wrong rotate angle
• Using flip instead of rotate