29443 - Computer Vision

Learning outcomes

The course aims at providing the notions and tools necessary for the design and implementation of automatic systems able to analyze digital images for object detection and recognition. In particular, the course focuses mainly on the techniques of feature extraction from digital images (shape, color and texture) and the application of these techniques to typical problems in computer vision such as localization, classification and similarity researches with in-depth examples in the field of biometric recognition systems (face and fingerprints).

Course contents

• Color Features:
  • color histograms and similarity metrics;
  • color moments;
  • color-based object segmentation;
• Texture feature:
  • gray-level co-occurrence matrix and related measures (enthropy, contrast, homogeneity, etc..);
  • Gabor filters: filter banks, contextual filtering with applications to fingerprint image enhancement and iris recognition;
  • Haar features: integral image and efficient feature extraction, application to face detection;
  • Local Binary Pattern: descriptor computation and application to face recognition;
• Shape features:
  • Object countour extraction and basic indicators (baricenter, circularity ratio, convexity, Eulero number, ecc…);
  • One-dimensional shape representations (centroid distance function, etc…);
  • Beam Angle Statistics, shape matrix, Fourier descriptors;
  • Shape features for similarity searches (query by sketch);
• Keypoints e local descriptors:
  • Keypoint detection: Harris corner detector;
  • Scale invariant detectors: Harris Laplace, Laplacian of Gaussian, Difference of Gaussian;
  • Keypoints and descriptors: SIFT, SURF, BRIEF, Histogram of Oriented Gradients.
• Bag of visual Words:
  • Dictionary computation;
  • Applications to image classification;
• Object detection:
  • Rigid Template matching based on features and applications to object detection;
  • Hough transform and fingerprint alignment;
  • Deformable templates: Ransac algorithm for image alignment based on keypoints.

Readings/Bibliography

Forsyth and Ponce, Computer Vision a modern approach, Pearson 2012.

Gonzalez and Woods, Elaborazioni delle immagini digitali, Prentice Hall, 3 edizione, 2008.

Duda, Hart and Stork, Pattern classification, Wiley 2002.

Teaching methods

Lectures

Laboratory exercises based on public multi-latform computer vision libraries (e.g. OpenCV).

Assessment methods

The final exam aims to evaluate the achievement of the educational objectives:

• Knowing the main techniques of extraction of shape, color, and texture features;
• Understanding the image representation techniques based on keypoint and local descriptors;
• Reaching the ability to design and implement object detection/recognition applications, also in the application field of biometric systems.

The examination consists of the realization and discussion of a homework, individual or in group, and in an oral test. The discussion of the project will take place at the same time as the oral exam and an overall evaluation will be formulated.

Teaching tools

Teacher's slides

Python code traces for laboratory exercises

C# classes to speed-up the preparation of the assigned project

Office hours

See the website of Annalisa Franco