Teaching Assistant: Yagmur Cinar
Wednesdays 11h15 - 12h45 in H203*
Verify Lecture Locations in ADE
Schedule of Classes
Class notes (pdf)04 October 2017 Learning and
Evaluation for Pattern Recognition
11 October 2017 Face Detection
using Color Histograms
11 October 2017 Lab Project 1: Face Detection with Color Histograms
of Skin Pixels (Due Wednesday 15 Nov)
11 October 2017 UMASS FDDB: Face Detection Data Set and
11 October 2017 Background Reading: [Jain and Learned-Miller 2010],
18 October 2017 Progamming Clinic: Python, OpenCV,
Face Image Data Bases (in E104)
25 October 2017 Detecting and Locating Faces with Color: Three Challenges for Project 1
8 November 2017 Lab Project 1 Project Team Presentations.
15 November 2017 No Class - Lab Project 1 written reports due by email
22 November 2017 Viola Jones
Face Detector - Image Description with Haar like features, Boosted
Learning, Cascade Classifiers.
22 November 2017 Lab Project
2: Viola Jones Faces Detector (Evaluation Criteria)
(Oral Presentations 13
December, Written reports due Wednesday 20 December)
22 november 2017 Background Reading: [Viola-Jones CVPR 2001]
29 November 2017 Eigen Faces - Face
Detection and Recognition with Principal Components Analysis
29 November 2017: Background Reading: Turk and Pentaland, Face recognition using eigenfaces, CVPR '91
6 December 2017 Clustering and Non-Supervised Learning with K-Means and EM
6 December 2017 Jeff Bilmes, A Gentle
Tutorial of the EM Algorithm
13 December 2017 Viola Jones Face Detector - Project Team
20 December 2017 Artificial Neural Networks: Introduction, Multi-layer networks, Backpropagation.
20 December 2017 Paper on Xavier GLORIOT's initialisation procedure
20 December 2017 Background Reading:
20 December 2017 Lab Project 3: Face Detection with Artificial
20 December 2017 Lab 2 Viola Jones Face Detector: Written Project
10 January 2018 Convolutional
Neural Networks, Pooling, Auto-Encoders
17 January 2018 Project Team Presentations for Lab 3
17 January 2018 Review of Course, Preparation for Exam.
25 January 2018 Written reports for Lab project 3 due
5-10 February 2018 Exams.
Annals: Exam from 2016/2017.
Some Notes on Performance Evaluation:
Performance Evaluation Metrics (supplement to lecture 2).
Face Detection Data Sets:
FDDB dataset: FDDB dataset contains the annotations for 5,171 faces in a set of 2,845 images.
A face detection benchmark dataset with 32,203 images and labels for
393,703 faces with a high degree of variability in scale, pose and
MALF dataset: Face Detection in the Wild. MALF consists of 5,250 images and 11,931 faces.
AFW dataset: Face Detetion in the Wild. AFW dataset is built using Flickr images. It has 205
images with 473 labeled faces.
For each face, annotations include a
rectangular bounding box, 6 landmarks and the pose angles.
IJB-A dataset: US NIST IJB-A dataset for face detection and face
recognition. IJB-A contains 24,327 images and 49,759 faces.
NB : Ces fichiers peuvent etre
copié, reproduit et
dans autre texte, sous condition d'inclure une citation :
These files can be copied and used in editing other text, with the
condition of including a citation:
Crowley, J. L. , "Class Notes - Pattern Recognition and Machine
Learning", ENSIMAG, Grenoble Institut Polytechnique,
Crée par James L.
Crowley. Last update 10 oct 2017