What computer vision encompasses - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

Core tasks in computer vision

Which of the following is NOT a common task in computer vision?

A Speech recognition

B Object detection

C Image classification

D Image segmentation

💡 Hint

Think about what computer vision deals with: images and videos, not sounds.

Speech recognition deals with audio data, not images or videos, so it is outside the scope of computer vision.

🧠 Conceptual

intermediate

Applications of computer vision

Which of these is a real-world application of computer vision?

A Translating languages in real-time

B Generating music automatically

C Predicting stock market trends

D Detecting faces in photos

💡 Hint

Computer vision helps computers understand images and videos.

Detecting faces in photos is a classic computer vision task where the system identifies and locates faces.

❓ Model Choice

advanced

Choosing a model for image classification

You want to build a system that recognizes different types of animals in photos. Which model type is best suited for this task?

A Recurrent Neural Network (RNN)

B K-Means Clustering

C Convolutional Neural Network (CNN)

D Linear Regression

💡 Hint

Think about which model type is designed to process images effectively.

CNNs are designed to analyze images by detecting patterns like edges and shapes, making them ideal for image classification.

❓ Metrics

advanced

Evaluating object detection models

Which metric is commonly used to evaluate the accuracy of object detection models?

A Mean Squared Error (MSE)

B Intersection over Union (IoU)

C BLEU Score

D Perplexity

💡 Hint

This metric measures how well the predicted bounding box overlaps with the true bounding box.

IoU calculates the overlap between predicted and actual bounding boxes, which is key for object detection accuracy.

🔧 Debug

expert

Debugging image preprocessing code

What error will this Python code raise when preprocessing images for a CNN?

import numpy as np
from PIL import Image

img = Image.open('cat.jpg')
img_array = np.array(img)
img_array = img_array / 255.0
img_array = img_array.reshape((224, 224, 3))

A ValueError due to incorrect reshape size

B TypeError because division by 255 is invalid

C FileNotFoundError because 'cat.jpg' does not exist

D No error, code runs successfully

💡 Hint

Check the original image size and the reshape dimensions.

The reshape size must match the total number of pixels. If the image is not 224x224, reshape will fail.