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.

Practice

1. What is the main purpose of face detection in deep learning?

easy

A. To find and locate faces in images or videos

B. To recognize the identity of a person

C. To generate new face images

D. To remove faces from images

Solution

1. Step 1: Understand face detection

   Face detection means finding where faces are in an image, not who they belong to.

2. Step 2: Differentiate from face recognition

   Face recognition identifies who the face belongs to, which is different from detection.

3. Final Answer:

   To find and locate faces in images or videos -> Option A

4. Quick Check:

   Face detection = Find faces [OK]

Hint: Face detection locates faces, recognition identifies them [OK]

Common Mistakes:

• Confusing detection with recognition
• Thinking detection creates new images
• Assuming detection removes faces

2. Which of the following is the correct way to load a Haar Cascade face detector in OpenCV (Python)?

easy

A. face_cascade = cv2.FaceDetector('haarcascade_frontalface_default.xml')

B. face_cascade = cv2.loadCascade('haarcascade_frontalface_default.xml')

C. face_cascade = cv2.Cascade('haarcascade_frontalface_default.xml')

D. face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

Solution

1. Step 1: Recall OpenCV syntax for Haar Cascade

   OpenCV uses cv2.CascadeClassifier to load Haar Cascade XML files.

2. Step 2: Check each option's method name

   Only cv2.CascadeClassifier is correct; others are invalid or do not exist.

3. Final Answer:

   face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml') -> Option D

4. Quick Check:

   Use CascadeClassifier to load Haar cascades [OK]

Hint: Use CascadeClassifier to load Haar cascades in OpenCV [OK]

Common Mistakes:

• Using wrong method names like loadCascade or Cascade
• Confusing face detector with face recognizer
• Missing the .xml file extension

3. Given this code snippet, what will be the output if the image contains two faces?

import cv2
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
img = cv2.imread('group_photo.jpg')
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = face_cascade.detectMultiScale(gray, scaleFactor=1.1, minNeighbors=5)
print(len(faces))

medium

A. 2

B. 1

C. 0

D. Error

Solution

1. Step 1: Understand detectMultiScale output

   detectMultiScale returns a list of rectangles for each detected face.

2. Step 2: Count detected faces in the image

   Since the image has two faces, len(faces) will be 2.

3. Final Answer:

   2 -> Option A

4. Quick Check:

   Faces detected = 2 [OK]

Hint: detectMultiScale returns all faces found; count them [OK]

Common Mistakes:

• Assuming detectMultiScale returns a boolean
• Confusing number of faces with confidence scores
• Forgetting to convert image to grayscale

4. What is wrong with this face detection code snippet?

import cv2
face_cascade = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
img = cv2.imread('photo.jpg')
faces = face_cascade.detectMultiScale(img)
print(len(faces))

medium

A. detectMultiScale requires a color image

B. The XML file path is incorrect

C. The image should be converted to grayscale before detection

D. print(len(faces)) should be print(faces)

Solution

1. Step 1: Check input type for detectMultiScale

   detectMultiScale expects a grayscale image, not a color image.

2. Step 2: Identify missing grayscale conversion

   The code misses converting img to grayscale before detection.

3. Final Answer:

   The image should be converted to grayscale before detection -> Option C

4. Quick Check:

   detectMultiScale needs grayscale input [OK]

Hint: Always convert images to grayscale before face detection [OK]

Common Mistakes:

• Passing color images directly to detectMultiScale
• Assuming detectMultiScale works on any image format
• Confusing print(len(faces)) with print(faces)

5. You want to improve face detection accuracy in a crowded photo using Haar Cascades. Which approach is best?

hard

A. Increase minNeighbors parameter to reduce false positives

B. Decrease scaleFactor to detect smaller faces more precisely

C. Use color images instead of grayscale for detection

D. Skip preprocessing and use raw images directly

Solution

1. Step 1: Understand scaleFactor effect

   Lower scaleFactor means the detector checks more scales, helping find smaller faces.

2. Step 2: Compare with other options

   Increasing minNeighbors reduces false positives but may miss faces; color images and skipping preprocessing reduce accuracy.

3. Final Answer:

   Decrease scaleFactor to detect smaller faces more precisely -> Option B

4. Quick Check:

   Lower scaleFactor = better small face detection [OK]

Hint: Lower scaleFactor to catch smaller faces in crowded images [OK]

Common Mistakes:

• Increasing minNeighbors too much misses faces
• Using color images instead of grayscale
• Skipping image preprocessing steps