Face embedding and comparison in Computer Vision - Interactive Code Practice

Practice - 5 Tasks

1fill in blank

easy

Complete the code to load a face embedding model using a common deep learning library.

Computer Vision

model = [1]('facenet_keras.h5')

Drag options to blanks, or click blank then click option'

Aload_model

Bfit

Ccompile

Dpredict

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' instead of 'load_model' which tries to train the model.

Using 'predict' which runs the model but does not load it.

The load_model function loads a saved deep learning model from a file.

2fill in blank

medium

Complete the code to preprocess a face image before embedding extraction.

Computer Vision

preprocessed_face = face_image[1](size=(160, 160))

Drag options to blanks, or click blank then click option'

Arotate

Bnormalize

Cresize

Dcrop

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'normalize' which changes pixel values but not size.

Using 'crop' which cuts part of the image but may not resize.

Face embedding models usually require images resized to a fixed size, here 160x160 pixels.

3fill in blank

hard

Fix the error in the code to compute the Euclidean distance between two face embeddings.

Computer Vision

distance = np.linalg.norm(embedding1 [1] embedding2)

Drag options to blanks, or click blank then click option'

A+

B-

C*

D/

Attempts:

3 left

💡 Hint

Common Mistakes

Using '+' which sums vectors instead of finding difference.

Using '*' or '/' which do element-wise multiplication or division.

Euclidean distance is the norm of the difference between two vectors.

4fill in blank

hard

Fill both blanks to create a dictionary of face embeddings for a list of face images.

Computer Vision

embeddings = {face_id: model.[1]([2](face)) for face_id, face in faces.items()}

Drag options to blanks, or click blank then click option'

Apredict

Bresize

Cpreprocess_input

Dfit

Attempts:

3 left

💡 Hint

Common Mistakes

Using 'fit' which trains the model instead of predicting.

Using 'resize' as a model method which is incorrect.

We use preprocess_input to prepare the face image, then predict to get the embedding.

5fill in blank

hard

Fill all three blanks to compare two face embeddings and decide if they match based on a threshold.

Computer Vision

distance = np.linalg.norm(embedding1 [1] embedding2)
match = distance [2] threshold
result = 'Match' if match else [3]

Drag options to blanks, or click blank then click option'

A-

B<=

C'No Match'

D+

Attempts:

3 left

💡 Hint

Common Mistakes

Using '+' instead of '-' for distance calculation.

Using '>' instead of '<=' for threshold comparison.

Returning a boolean instead of a string for result.

We subtract embeddings to get distance, check if distance is less or equal to threshold, else return 'No Match'.

Practice

1. What is the main purpose of face embedding in face recognition systems?

easy

A. To detect faces in an image

B. To change the face image colors

C. To crop the face from the image

D. To convert a face image into a unique list of numbers

Solution

1. Step 1: Understand face embedding

   Face embedding transforms a face image into a unique numeric vector representing its features.

2. Step 2: Identify the purpose

   This numeric vector helps compare faces by their features, not by raw pixels.

3. Final Answer:

   To convert a face image into a unique list of numbers -> Option D

4. Quick Check:

   Face embedding = unique number list [OK]

Hint: Face embedding means turning face into numbers [OK]

Common Mistakes:

• Confusing embedding with face detection
• Thinking embedding changes image colors
• Assuming embedding crops the face

2. Which Python code snippet correctly computes the Euclidean distance between two face embeddings emb1 and emb2 stored as lists?

easy

A. distance = sum((a - b)**2 for a, b in zip(emb1, emb2)) ** 0.5

B. distance = abs(emb1 - emb2)

C. distance = emb1 + emb2

D. distance = max(emb1, emb2)

Solution

1. Step 1: Recall Euclidean distance formula

   Euclidean distance is the square root of sum of squared differences between corresponding elements.

2. Step 2: Match code to formula

   distance = sum((a - b)**2 for a, b in zip(emb1, emb2)) ** 0.5 uses a generator to compute squared differences, sums them, then takes square root, matching the formula.

3. Final Answer:

   distance = sum((a - b)**2 for a, b in zip(emb1, emb2)) ** 0.5 -> Option A

4. Quick Check:

   Euclidean distance = sqrt(sum of squared differences) [OK]

Hint: Euclidean distance = sqrt of sum of squared differences [OK]

Common Mistakes:

• Using abs() on lists causes error
• Adding lists concatenates, not distance
• Using max() does not measure distance

3. Given the following code, what is the printed output?

import numpy as np
emb1 = np.array([0.1, 0.2, 0.3])
emb2 = np.array([0.1, 0.25, 0.35])
distance = np.linalg.norm(emb1 - emb2)
print(round(distance, 3))

medium

A. 0.050

B. 0.100

C. 0.071

D. 0.150

Solution

1. Step 1: Calculate difference vector

   emb1 - emb2 = [0.1-0.1, 0.2-0.25, 0.3-0.35] = [0, -0.05, -0.05]

2. Step 2: Compute Euclidean norm

   Distance = sqrt(0^2 + (-0.05)^2 + (-0.05)^2) = sqrt(0 + 0.0025 + 0.0025) = sqrt(0.005) ≈ 0.0707

3. Final Answer:

   0.071 -> Option C

4. Quick Check:

   Distance ≈ 0.071 [OK]

Hint: Subtract vectors, then sqrt of sum squares for distance [OK]

Common Mistakes:

• Forgetting to square differences
• Rounding incorrectly
• Mixing up emb1 and emb2 order

4. The following code tries to compare two face embeddings but raises an error. What is the error and how to fix it?

emb1 = [0.1, 0.2, 0.3]
emb2 = [0.1, 0.25, 0.35]
distance = (emb1 - emb2).norm()
print(distance)

medium

A. Lists do not support subtraction; convert to numpy arrays first

B. norm() is not a valid method; use length() instead

C. emb1 and emb2 must be strings, not lists

D. Missing import statement for math module

Solution

1. Step 1: Identify the error cause

   Subtracting two Python lists causes a TypeError because lists do not support '-' operator.

2. Step 2: Fix by converting lists to numpy arrays

   Convert emb1 and emb2 to numpy arrays to enable element-wise subtraction and use numpy.linalg.norm() for distance.

3. Final Answer:

   Lists do not support subtraction; convert to numpy arrays first -> Option A

4. Quick Check:

   List subtraction error fixed by numpy arrays [OK]

Hint: Use numpy arrays for math on lists [OK]

Common Mistakes:

• Trying to use norm() on lists
• Ignoring TypeError from list subtraction
• Assuming norm() is built-in for lists

5. You have two face embeddings: embA = [0.3, 0.4, 0.5] and embB = [0.31, 0.39, 0.52]. You want to decide if they belong to the same person using a threshold of 0.05 on Euclidean distance. Which code correctly implements this decision?

hard

A. distance = max(abs(a - b) for a, b in zip(embA, embB))
if distance > 0.05:
print('Same person')
else:
print('Different person')

B. distance = sum((a - b)**2 for a, b in zip(embA, embB)) ** 0.5
if distance < 0.05:
print('Same person')
else:
print('Different person')

C. distance = sum(abs(a - b) for a, b in zip(embA, embB))
if distance < 0.05:
print('Different person')
else:
print('Same person')

D. distance = sum((a + b)**2 for a, b in zip(embA, embB)) ** 0.5
if distance < 0.05:
print('Same person')
else:
print('Different person')

Solution

1. Step 1: Calculate Euclidean distance correctly

   distance = sum((a - b)**2 for a, b in zip(embA, embB)) ** 0.5 if distance < 0.05: print('Same person') else: print('Different person') computes Euclidean distance as sqrt of sum of squared differences, which is the right metric.

2. Step 2: Apply threshold logic

   If distance is less than 0.05, print 'Same person'; else 'Different person'. This matches the problem statement.

3. Final Answer:

   distance = sum((a - b)**2 for a, b in zip(embA, embB)) ** 0.5 if distance < 0.05: print('Same person') else: print('Different person') -> Option B

4. Quick Check:

   Euclidean distance < threshold means same person [OK]

Hint: Use Euclidean distance and compare with threshold [OK]

Common Mistakes:

• Using max difference instead of Euclidean distance
• Reversing the if condition logic
• Adding embeddings instead of subtracting