Why processing prepares images for analysis in Computer Vision - Challenge Your Understanding

Challenge - 5 Problems

🧠 Conceptual

intermediate

Why do we normalize pixel values before feeding images into a model?

Imagine you have a photo with pixel values ranging from 0 to 255. Why is it helpful to normalize these values to a smaller range like 0 to 1 before analysis?

A It removes all noise from the image automatically.

B It increases the image size to improve detail.

C It helps the model learn faster by keeping numbers small and consistent.

D It changes the colors to black and white for simplicity.

💡 Hint

Think about how computers handle very large or very different numbers during learning.

Normalizing pixel values scales them to a consistent range, which helps the model process data more efficiently and learn patterns faster.

❓ Predict Output

intermediate

What is the output shape after resizing an image?

Given a color image with shape (300, 400, 3), what will be the shape after resizing it to (150, 200)?

Computer Vision

import numpy as np
from PIL import Image

original_image = np.zeros((300, 400, 3), dtype=np.uint8)
resized_image = Image.fromarray(original_image).resize((200, 150))
output_shape = np.array(resized_image).shape

A (150, 200, 3)

B (200, 150, 3)

C (150, 200)

D (300, 400, 3)

💡 Hint

Remember the order of width and height in the resize function.

The resize function takes size as (width, height), so resizing to (200, 150) means width=200 and height=150. The output shape keeps the 3 color channels.

❓ Model Choice

advanced

Which model is best for image classification tasks?

You want to classify images of animals into categories like cats, dogs, and birds. Which model type is most suitable?

A Recurrent Neural Network (RNN)

B Convolutional Neural Network (CNN)

C Linear Regression

D K-Means Clustering

💡 Hint

Think about which model type is designed to understand spatial patterns in images.

CNNs are designed to capture spatial features in images, making them ideal for image classification tasks.

❓ Metrics

advanced

Which metric best measures image classification accuracy?

After training an image classifier, you want to know how often it predicts the correct label. Which metric should you use?

A Perplexity

B Mean Squared Error

C Silhouette Score

D Accuracy

💡 Hint

Consider a metric that counts correct predictions over total predictions.

Accuracy measures the proportion of correct predictions, making it suitable for classification tasks.

🔧 Debug

expert

Why does this image preprocessing code raise an error?

Consider this code snippet that tries to convert an image to grayscale and normalize it:

import cv2
image = cv2.imread('photo.jpg')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
norm = gray / 255.0
print(norm.shape)

What is the cause of the error if the image file is missing?

A cv2.imread returns None, causing cvtColor to fail with an error.

B Division by 255.0 is not allowed on grayscale images.

C print(norm.shape) is invalid syntax.

D cv2.cvtColor cannot convert color images to grayscale.

💡 Hint

What happens if the image file path is wrong or file is missing?

If the image file is missing, cv2.imread returns None. Passing None to cv2.cvtColor causes an error because it expects an image array.