525.724.8VL - Introduction to Pattern Recognition

Expanded Course Description

Prerequisites

Required - 525.414 Probability and Stochastic Processes

Recommended – a course in digital signal or image processing, such as:

• 525.427 Digital Signal Processing
• 525.746 Image Engineering
• 525.419 Introduction to Digital Image and Video Processing
• 525.443 Real Time Computer Vision

Course Structure

The course materials are divided into modules which can be accessed by clicking Modules on the course menu. A module will have several sections including the overview, content, readings, discussions, and assignments. You are encouraged to preview all sections of the module before starting. Most modules run for a period of seven (7) days, exceptions are noted in the Course Outline. You should regularly check the Calendar and Announcements for assignment due dates.

Course Topics

Week 1 (8/28/23) - Introduction to patterns and the pattern recognition application development process (Module 1, Module 3 – Part 1)

• Overview of patterns
  • Pattern recognition application development process
  • Pattern recognition problem classes
  • Parametric versus non-parametric methods, supervised versus unsupervised methods

• Feature representation
  • Signal features (min/max, peaks and valleys, moments, FFT)
  • Image features (density, color, edge, texture, frequency content)

• Data pre-processing (outlier removal, normalization, missing data, enhancement)

Week 2 (9/4/23) – Labor Day Holiday – No class –

• Assignment: Please read through Module #2 materials on Canvas

Week 3 (9/11/23) – Feature extraction I (Module 3 Part 1 - continued)

• Brief review of feature representation
• Individual feature evaluation
• Case Study #1 assigned – Fish Classification - Due in 2 weeks (9/25/23)

Week 4 (9/18/23) - Supervised, parametric pattern detection I, Feature extraction I (Module 2 – Part 1)

• Bayes decision theory
• Bayesian classification for normal distributions
• Minimum distance classifiers

Week 5 (9/25/23) – Supervised, parametric pattern detection II (Module 2 – Part 2)

• Case Study #1 Due – Review Fish Classification
• Estimating unknown probability distributions
• Naïve Bayes classifier
• Nearest neighbor classifiers

Week 6 (10/2/23) - Feature extraction II (Module 3 – Part 2)

• Image segmentation
• Shape analysis
• Case Study #2 assigned – Flag Classification - Due in 2 weeks (10/16/23)

Week 7 (10/9/23) - Feature extraction III (Module 3 – Part 3)

• HOG (Histogram of Oriented Gradients)
• SIFT (Scale Invariant Feature Transform)
• SURF (Speeded Up Robust Features)

Week 8 (10/16/23) - Multivariate feature evaluation (Module 4)

• Case Study #2 Due – Review Flag Classification
• Dimensionality reduction
• Class separability measures
• Optimal feature selection
• Case Study #3 assigned – Wine Quality - Due in 2 weeks (10/30/23)

Mid-term exam distributed (10/16/23) - Take home

Mid-term exam due into Canvas by 4:30 pm (10/23/23)

Week 9 (10/23/23) - Unsupervised, non-parametric pattern detection (Module 5 -continued)

• Clustering based on cost function optimization
• Competitive clustering
• Cluster validity

Week 10 (10/30/23) - Supervised, non-parametric pattern detection I (Module 6)

• Review midterm
• Case Study #3 Due – Review Wine Quality  
• Linear classifiers
• Neural networks
• Case Study #4 assigned – Unsupervised analysis - Due in 1 week (11/6/23)

Week 11 (11/6/23) – Supervised, non-parametric pattern detection II (Module 7)

• Case Study #4 Due – Review unsupervised analysis
• Support vector machines (SVMs)
• Comparison of neural networks and SVMs
• Combining classifiers
• Case Study #5 assigned – Agricultural pathogen detection - Due in 2 weeks (11/20/23)

Week 12 (11/13/23) – Supervised, non-parametric pattern detection III (Module 9)

• Deep Learning – Autoencoders
• Deep Learning - Convolutional Neural Networks
• Case Study #6 assigned – Concrete air-void structure – Due in 3 weeks (12/4/23)

Week 13 (11/20/23) – Thanksgiving Holiday- No class

• Case Study #5 Due (Review on 11/27/23)

Week 14 (11/27/23) – Data fusion (Module 10)

• Case Study #5 – Review agricultural pathogen detection
• Levels of fusion
• Fusion methods (multisensor, multimodal)
• Sensor fusion architectures

Week 15 (12/4/23) – Supervised, non-parametric pattern detection IV (Module 8)

• Case Study #6 Due – Review concrete air-void structure
• Fuzzy logic
• Genetic algorithms

Final exam distributed (12/4/23) – Take home

Week 16 (12/11/23) – No class – Final exam due into Canvas by 7:00pm

Course Goals

The goal of this course is to introduce the student to the basic concepts and methods for the recognition of patterns in data.  This is accomplished via the presentation of the underlying theory and algorithmic approaches for the detection and characterization of patterns in multi-dimensional data, followed by the demonstration of how these methods are employed to solve pattern recognition problems in the real-world environment.  This course will also provide the student with a working knowledge of the pattern recognition application development process which will be reinforced throughout the course via case studies using sample data from deployed applications.

Course Learning Outcomes (CLOs)

• • Understand the concept of a pattern and the basic approach to the development of pattern recognition and machine intelligence algorithms
• • Understand the basic methods of feature extraction, feature evaluation, and data mining.
• • Learn how to apply the various supervised and unsupervised methods for the detection and characterization of patterns in real-world data
• • Develop prototype pattern recognition algorithms with which they may study algorithm behavior and performance against real-world multivariate data.

Textbooks

We will use the following textbook and accompanying MATLAB workbook:

Pattern Recognition & MATLAB Intro

Sergios Theodoridis

Konstantinos Koutroumbas

Academic Press  ISBN:  978-0-12-374491-3  2010  Burlington Mass.

~$120.00

Software is also provided with these books and will be provided on the course Canvas site. 

Textbook purchase information for this course is available online through BNC Virtual Bookstore.

Other Materials & Online Resources

Computer and Technical Requirements

A basic knowledge of digital signal and image processing algorithms is assumed.  Class examples, homework assignments, and term projects will all require access to and familiarity with MATLAB.

Required Software

You will need access to a recent, full version of MATLAB. The MATLAB Total Academic Headcount (TAH) license is now in effect. This license is provided at no cost to you. Send an email to software@jhu.edu to request your license file/code. Please indicate that you need a standalone file/code. You will need to provide your first and last name, as well as your Hopkins email address. You will receive an email from Mathworks with instructions to create a Mathworks account. The MATLAB software will be available for download from the Mathworks site.

Canvas:  Will be used to post all assignments, announcements, and case study components.  All student generated materials for exams and case studies will be submitted via Canvas.  For more information on Canvas, you can access the following link:  Canvas FAQ for Students – Canvas at JHU.

PDF Viewer:

You will need the free Adobe PDF viewer software to view PDF files in this course. Go to http://www.adobe.com/products/acrobat/readstep.html.

Zip Software:

You will also need software for "zipping" and "unzipping" (compressing and uncompressing) files. Two popular shareware "zip" programs can be downloaded from the sites linked below:

For Windows - WinZip at http://www.winzip.com/

For Macintosh - ZipIt at http://www.maczipit.com/download.html

Student Coursework Requirements

Course Assessments

Midterm Exam            15%

Final Exam                 15%

Case Studies               70%

Participation Expectations

This course will consist of four basic student requirements:

1. Homework – Homework assignments will be made throughout the semester. Homework assignments will not be graded, but students are advised to work through the assigned homework problems for two reasons:  (1) the homework assignments are used to illustrate the use of MATLAB algorithms that will be required for successful completion of the case study assignments; and (2) assigned homework problems (or variations) may be included on the midterm and final exams.
2. Midterm Examination - A take home mid-term will be provided during the seventh or eighth week of class. The exam due date will be provided by the instructor.  The exam shall be an individual, not group, effort.
3. Final Examination – A take home final will be provided a week before the last class of the semester. The exam due date will be provided by the instructor. The exam shall be an individual, not group, effort.
4. Case Studies – A number of case studies will be assigned by the instructor throughout the term and will provide an opportunity for the student to work with real world data to build realistic pattern recognition applications. Students are also required to select and develop a case study of their own choosing by the end of the semester, and to present their case studies to the rest of the class during the last class of the semester.

Grading Policy

EP uses a +/- grading system (see “Grading System”, Graduate Programs catalog, p. 10).

Academic Policies

Deadlines for Adding, Dropping and Withdrawing from Courses

Students may add a course up to one week after the start of the term for that particular course. Students may drop courses according to the drop deadlines outlined in the EP academic calendar (https://ep.jhu.edu/student-services/academic-calendar/). Between the 6th week of the class and prior to the final withdrawal deadline, a student may withdraw from a course with a W on their academic record. A record of the course will remain on the academic record with a W appearing in the grade column to indicate that the student registered and withdrew from the course.

Academic Misconduct Policy

All students are required to read, know, and comply with the Johns Hopkins University Krieger School of Arts and Sciences (KSAS) / Whiting School of Engineering (WSE) Procedures for Handling Allegations of Misconduct by Full-Time and Part-Time Graduate Students.

This policy prohibits academic misconduct, including but not limited to the following: cheating or facilitating cheating; plagiarism; reuse of assignments; unauthorized collaboration; alteration of graded assignments; and unfair competition. Course materials (old assignments, texts, or examinations, etc.) should not be shared unless authorized by the course instructor. Any questions related to this policy should be directed to EP’s academic integrity officer at ep-academic-integrity@jhu.edu.

Students with Disabilities - Accommodations and Accessibility

Johns Hopkins University values diversity and inclusion. We are committed to providing welcoming, equitable, and accessible educational experiences for all students. Students with disabilities (including those with psychological conditions, medical conditions and temporary disabilities) can request accommodations for this course by providing an Accommodation Letter issued by Student Disability Services (SDS). Please request accommodations for this course as early as possible to provide time for effective communication and arrangements.

For further information or to start the process of requesting accommodations, please contact Student Disability Services at Engineering for Professionals, ep-disability-svcs@jhu.edu.

Student Conduct Code

The fundamental purpose of the JHU regulation of student conduct is to promote and to protect the health, safety, welfare, property, and rights of all members of the University community as well as to promote the orderly operation of the University and to safeguard its property and facilities. As members of the University community, students accept certain responsibilities which support the educational mission and create an environment in which all students are afforded the same opportunity to succeed academically. 

For a full description of the code please visit the following website: https://studentaffairs.jhu.edu/policies-guidelines/student-code/

Classroom Climate

JHU is committed to creating a classroom environment that values the diversity of experiences and perspectives that all students bring. Everyone has the right to be treated with dignity and respect. Fostering an inclusive climate is important. Research and experience show that students who interact with peers who are different from themselves learn new things and experience tangible educational outcomes. At no time in this learning process should someone be singled out or treated unequally on the basis of any seen or unseen part of their identity. 
 
If you have concerns in this course about harassment, discrimination, or any unequal treatment, or if you seek accommodations or resources, please reach out to the course instructor directly. Reporting will never impact your course grade. You may also share concerns with your program chair, the Assistant Dean for Diversity and Inclusion, or the Office of Institutional Equity. In handling reports, people will protect your privacy as much as possible, but faculty and staff are required to officially report information for some cases (e.g. sexual harassment).

Course Auditing

When a student enrolls in an EP course with “audit” status, the student must reach an understanding with the instructor as to what is required to earn the “audit.” If the student does not meet those expectations, the instructor must notify the EP Registration Team [EP-Registration@exchange.johnshopkins.edu] in order for the student to be retroactively dropped or withdrawn from the course (depending on when the "audit" was requested and in accordance with EP registration deadlines). All lecture content will remain accessible to auditing students, but access to all other course material is left to the discretion of the instructor.