Learning outcomes

The course is thought of as a natural continuation of Pattern Recognition, and it approaches considerably more difficult classification problems. The course objectives are to make the student able to understand and modify professional recognition code (OpenCV, VLFeat, Tensorflow), and understand the underlying theory. At the end of the course, the student will have to face a real recognition problem (derived from an industrial application), presenting the most proper solution. The languages used will be MATLAB and Python, with some references to C.

Program

The course presents a series of state-of-the-art topics in the field of recognition. Each topic will be explained through updated articles together with the lesson slides. The following books are suggested as a reference:
- Christopher M. Bishop. 2006. Pattern Recognition and Machine Learning (Information Science and Statistics). Springer-Verlag New York, Inc., Secaucus, NJ, USA.
- Ian Goodfellow, Yoshua Bengio, and Aaron Courville. Deep learning. MIT Press, 2016.

Topics:
- Classification validation tools: Confusion matrix and derivative measurements, ROC and CMC curves, average precision, average quadratic error, label correlation, grading and regression measures
- Kernel machines, Support Vector Machines
- VLFeat for object recognition: Dense object recognition through multiclass discriminatory models
- Dense classification features as bag of words
- Shape descriptors for object tracking: B-spline and Condensation
- Deep learning in Tensorflow: Multinomial Logistic Classifier, Neural Networks, Convolutional Neural Network

Examination Methods

The exam involves the discussion of a code project, which proposes a solution to an industrial classification problem. The final score will depend on the classification figure of merits achieved by the classifier and the theoretical motivations that prompted the student to choose a particular algorithm.

Teaching materials

•   Lab 1 - Valutazione dei classificatori supervisionati   (zip, it, 400 KB, 06/10/16)
•   Lab 2 - Funzioni discriminanti lineari ed SVM   (zip, it, 1925 KB, 20/10/16)
•   Lab 3 - Riconoscimento di oggetti con BoW   (zip, it, 14 KB, 17/11/16)
•   Lab 4 - Riconoscimento di oggetti con PLSA   (zip, it, 1 KB, 24/11/16)
•   Lab 6 - Shape descriptors   (zip, it, 1877 KB, 19/12/16)
•   Lezione 0 - Introduzione al corso   (pdf, it, 719 KB, 02/10/16)
•   Lezione 1 - Valutazione dei classificatori supervisionati   (zip, it, 2874 KB, 02/10/16)
•   Lezione 2 - Classificatori discriminativi   (zip, it, 5315 KB, 10/10/16)
•   Lezione 4 - Riconoscimento di Oggetti - Classificatori generativi (PLSA)   (zip, it, 17248 KB, 24/11/16)
•   Lezione 5 - Motion Detection   (zip, it, 7103 KB, 30/11/16)
•   Lezione 7 - Deep Networks   (zip, it, 8017 KB, 12/01/17)
•   Lezione 8 - Deep Networks - Going Deep   (zip, it, 1344 KB, 11/01/17)
•   Lezione 9 - Deep Networks - CNNs   (zip, it, 8047 KB, 23/01/17)