Why is the integral image representation used in Viola-Jones?

- It stores where faces lie in an image
- It allows features to be concatenated into a feature vector
It allows Haar features to be calculated in constant time

- It stores the sum of all the pixels in an image

What are Haar features?

- The sum of differences between a pair of images
- The number of corners in a region
Differences between the sums of pixels in rectangular regions

- Measures of the number of edges in a region

What does Principal Component Analysis (PCA), as used in eigenfaces, do?

Finds the directions in feature space with the largest variations

- Splits up features into components
- Finds the most similar set of features in a database
- Finds the most important direction in an image

Faces are allegedly more attractive if:

The shape matches the golden ratio

- Facial features are slightly asymmetrical
- The lips are oval in shape
- The hair and skin are in the same region in HSV space

What is covariance?

- A pair of images having similar variances
- A pair of images having dissimilar variances
- Another name for cross-correlation
A measure of the similarity of variations in the images

The Viola-Jones face detection algorithm is based around the use of which type of features?

- Edges detected using Canny's edge detector
- SIFT features
- ORB features
Haar features

What is Adaptive Boosting?

A method for combining multiple weak classifiers into one strong classifier

- A method for improving the performance of a single weak classifier
- An adaptive way of choosing the best single classifier for a task
- A way of improving the contrast of an image based on the local grey levels

What is Affective Computing?

- A way of recognising facial expressions
Taking into account the emotional state of the user

- A face recognition algorithm
- A way of performing computer vision that is more accurate

How is Principal Component Analysis performed?

- By Linear Discriminant Analysis of the variance of an image
- By Eigen decomposition of the variance of an image
By Eigen decomposition of the covariance matrix

- By Linear Discriminant Analysis of the covariance matrix

Which of the following techniques is "eigenfaces" built on?

- Support Vector Machine
- Linear Discriminant Analysis
Principal Component Analysis

- Convolutional Neural Network