Face detection with deep learning in Computer Vision - Practice Problems & Coding Challenges

Challenge - 5 Problems

🧠 Conceptual

intermediate

What is the main role of the bounding box in face detection?

In face detection using deep learning, what does the bounding box represent?

A It enhances the image contrast for better face recognition.

B It marks the area in the image where a face is detected.

C It generates the facial landmarks like eyes and nose positions.

D It normalizes the pixel values of the detected face region.

💡 Hint

Think about what a box drawn on an image usually shows.

The bounding box is a rectangle that shows where the face is located in the image. It helps the model or system focus on that area for further processing.

❓ Predict Output

intermediate

Output of face detection model prediction array

Given the following output array from a face detection model, what does the first element represent?

Computer Vision

predictions = [[0.95, 0.1, 0.2, 0.5, 0.6], [0.80, 0.4, 0.3, 0.7, 0.8]]
# Each sublist: [confidence, x_min, y_min, x_max, y_max]

A The y-coordinate of the bottom-right corner of the bounding box.

B The x-coordinate of the top-left corner of the bounding box.

C The confidence score that a face is detected in the bounding box.

D The width of the detected face bounding box.

💡 Hint

The first number in each prediction usually tells how sure the model is.

The first element in each prediction array is the confidence score, showing how likely the detected box contains a face.

❓ Hyperparameter

advanced

Choosing the confidence threshold in face detection

Why is setting a confidence threshold important when using a deep learning face detector?

A It filters out detections with low confidence to reduce false positives.

B It increases the size of the bounding boxes for better coverage.

C It normalizes the input images before detection.

D It adjusts the learning rate during model training.

💡 Hint

Think about how to avoid wrong face detections.

The confidence threshold helps ignore detections that the model is not sure about, reducing false alarms.

❓ Metrics

advanced

Evaluating face detection with Intersection over Union (IoU)

What does a high Intersection over Union (IoU) score indicate when comparing predicted and ground truth bounding boxes?

A The predicted bounding box closely matches the actual face location.

B The predicted bounding box is much larger than the actual face.

C The model has low confidence in the detection.

D The predicted bounding box is completely outside the actual face.

💡 Hint

IoU measures how much two boxes overlap.

A high IoU means the predicted box and the real face box overlap a lot, showing good detection accuracy.

🔧 Debug

expert

Why does this face detection model fail on some images?

Consider a deep learning face detector that works well on frontal faces but fails on side profiles. What is the most likely reason?

A The confidence threshold is set too low, missing side profiles.

B The model uses too many convolutional layers causing overfitting.

C The input images are normalized incorrectly before detection.

D The training data lacked diverse face angles, causing poor generalization.

💡 Hint

Think about what affects a model's ability to recognize different face poses.

If the model only saw frontal faces during training, it won't learn features for side views, so it fails on those.