Computer vision and pattern recognition
Description: The discipline is devoted to the study of the fundamentals of computer vision, the mathematical representation of digital images, methods of image processing and analysis, and pattern recognition.
Amount of credits: 6
Пререквизиты:
- Automation of Engineering Systems
- Linear Systems of Automatic Control
Course Workload:
| Types of classes | hours |
|---|---|
| Lectures | 30 |
| Practical works | |
| Laboratory works | 30 |
| SAWTG (Student Autonomous Work under Teacher Guidance) | 30 |
| SAW (Student autonomous work) | 90 |
| Form of final control | Exam |
| Final assessment method | Oral exam |
Component: Component by selection
Cycle: Profiling disciplines
Goal
- formation students have knowledge of mathematical foundations and pattern recognition algorithms and computer vision, developing practical skills in working with images and solving applied problems of image analysis
Objective
- Introduction to the basic concepts of machine vision technology.
- Study of basic concepts and algorithms for image processing, including the use of convolution with a rectangular window, calculation of image derivatives, etc.
- Mastering the technique of highlighting image features and image segmentation.
- Mastering image recognition methods.
- Application of software tools for digital image processing and recognition.
Learning outcome: knowledge and understanding
- describe the basic concepts and methods of machine learning used in computer vision, such as neural networks, convolutional neural networks, etc.
Learning outcome: applying knowledge and understanding
- Use your knowledge of computer vision to solve real-world problems such as face recognition, object detection or medical image analysis.
Learning outcome: formation of judgments
- apply various algorithms and methods of image processing, segmentation, object detection and pattern recognition;
Learning outcome: communicative abilities
- explain computer vision concepts to peers and computer vision specialists, and participate in discussions and project presentations;
Learning outcome: learning skills or learning abilities
- analyze information from various sources for an in-depth study of the topic, as well as independently solve practical problems in the field of computer vision and pattern recognition.
Teaching methods
- interactive lecture (use of the following active forms of learning: guided (controlled) discussion or conversation; moderation; demonstration of slides or educational films; brainstorming; motivational speech);
- building scenarios for the development of various situations based on given conditions; - information and communication (for example, classes in a computer class using professional application software packages);
- search and research (independent research activities of students during the learning process);
- solving educational problems.
Assessment of the student's knowledge
Teacher oversees various tasks related to ongoing assessment and determines students' current performance twice during each academic period. Ratings 1 and 2 are formulated based on the outcomes of this ongoing assessment. The student's learning achievements are assessed using a 100-point scale, and the final grades P1 and P2 are calculated as the average of their ongoing performance evaluations. The teacher evaluates the student's work throughout the academic period in alignment with the assignment submission schedule for the discipline. The assessment system may incorporate a mix of written and oral, group and individual formats.
| Period | Type of task | Total |
|---|---|---|
| 1 rating | Laboratory work «Image Filtering» | 0-100 |
| Laboratory work «Edge detection» | ||
| Laboratory work «Image Binarization» | ||
| Laboratory work «Selecting objects in an image» | ||
| Laboratory work «Simple image segmentation» | ||
| Boundary control 1 | ||
| 2 rating | Laboratory work « Pattern Matching» | 0-100 |
| Laboratory work « Defining geometric shapes» | ||
| Laboratory work « Simple Image Classifier» | ||
| Laboratory work « Simple Data Augmentation» | ||
| Laboratory work « Determining the direction of the gradient» | ||
| Boundary control 2 | ||
| Total control | Exam | 0-100 |
The evaluating policy of learning outcomes by work type
| Type of task | 90-100 | 70-89 | 50-69 | 0-49 |
|---|---|---|---|---|
| Excellent | Good | Satisfactory | Unsatisfactory | |
| Test questions | demonstrates systematic theoretical knowledge, masters terminology, logically and consistently explains the essence of phenomena and processes, makes reasoned conclusions and generalizations, gives examples, shows fluency in monologue speech and the ability to quickly respond to clarifying questions | demonstrates strong theoretical knowledge, masters terminology, logically and consistently explains the essence of phenomena and processes, makes reasoned conclusions and generalizations, gives examples, shows fluency in monologue speech, but at the same time makes minor mistakes, which he corrects independently or with minor correction by the teacher | demonstrates shallow theoretical knowledge, shows poorly formed skills in analyzing phenomena and processes, insufficient ability to draw reasoned conclusions and give examples, shows insufficient fluency in monologue speech, terminology, logic and consistency of presentation, makes mistakes that can only be corrected by correction by the teacher. | demonstrates systematic theoretical knowledge, masters terminology, logically and consistently explains the essence of phenomena and processes, makes reasoned conclusions and generalizations, gives examples, shows fluency in monologue speech and the ability to quickly respond to clarifying questions |
| Practical work | completed the practical work in full in compliance with the required sequence of actions; in the answer, correctly and accurately completes all records, tables, pictures, drawings, graphs, calculations; performs error analysis correctly. When answering questions, he correctly understands the essence of the question, gives an accurate definition and interpretation of basic concepts; accompanies the answer with new examples, knows how to apply knowledge in a new situation; can establish a connection between the material being studied and previously studied, as well as with the material acquired in the study of other disciplines. | fulfilled the requirements for a “5” rating, but made 2-3 shortcomings. The student’s answer to the questions satisfies the basic requirements for answering 5, but is given without applying knowledge in a new situation, without using connections with previously studied material and material learned in the study of other disciplines; If one mistake or no more than two shortcomings are made, the student can correct them independently or with a little help from the teacher. | did not complete the work completely, but not less than 50% of the volume of practical work, which allows you to obtain the correct results and conclusions; Errors were made during the work. When answering questions, the student correctly understands the essence of the question, but in the answer there are some problems in mastering the course questions that do not interfere with further mastery of the program material; no more than one gross error and two omissions were made. | completed the practical work in full in compliance with the required sequence of actions; in the answer, correctly and accurately completes all records, tables, pictures, drawings, graphs, calculations; performs error analysis correctly. When answering questions, he correctly understands the essence of the question, gives an accurate definition and interpretation of basic concepts; accompanies the answer with new examples, knows how to apply knowledge in a new situation; can establish a connection between the material being studied and previously studied, as well as with the material acquired in the study of other disciplines. |
| Exam | correct and complete answers to all theoretical questions were given; -the practical task is completely solved; - the material is presented competently in compliance with a logical sequence; -demonstrated creative abilities. | correct, but incomplete answers to all theoretical questions were given, minor errors or inaccuracies were made; - the practical task was completed, but a minor mistake was made; - the material is presented competently in compliance with a logical sequence. | answers to theoretical questions are correct in principle, but incomplete, there are inaccuracies in wording and logical errors; -the practical task is not completed completely; - the material is presented correctly, but the logical sequence is broken | correct and complete answers to all theoretical questions were given; -the practical task is completely solved; - the material is presented competently in compliance with a logical sequence; -demonstrated creative abilities. |
Evaluation form
The student's final grade in the course is calculated on a 100 point grading scale, it includes:
- 40% of the examination result;
- 60% of current control result.
The final grade is calculated by the formula:
| FG = 0,6 | MT1+MT2 | +0,4E |
| 2 |
Where Midterm 1, Midterm 2are digital equivalents of the grades of Midterm 1 and 2;
E is a digital equivalent of the exam grade.
Final alphabetical grade and its equivalent in points:
The letter grading system for students' academic achievements, corresponding to the numerical equivalent on a four-point scale:
| Alphabetical grade | Numerical value | Points (%) | Traditional grade |
|---|---|---|---|
| A | 4.0 | 95-100 | Excellent |
| A- | 3.67 | 90-94 | |
| B+ | 3.33 | 85-89 | Good |
| B | 3.0 | 80-84 | |
| B- | 2.67 | 75-79 | |
| C+ | 2.33 | 70-74 | |
| C | 2.0 | 65-69 | Satisfactory |
| C- | 1.67 | 60-64 | |
| D+ | 1.33 | 55-59 | |
| D | 1.0 | 50-54 | |
| FX | 0.5 | 25-49 | Unsatisfactory |
| F | 0 | 0-24 |
Topics of lectures
- Subject of pattern recognition and computer vision
- Basics of working with the OpenCV library
- Formation and presentation of images
- Modeling the human visual system
- Analysis of binary images
- Basic concepts of pattern recognition
- Digital filtering and brightness conversions
- Search images based on content
Key reading
- Richard Szeliski. Computer Vision: Algorithms and Applications. - c 2010 Springer, 2010. - p. 979
- Simon J.D. Prince. Computer Vision: Models, Learning, and Inference - Cambridge University Press, 2012. - 581 p. ISBN-13 978-1107011793
- Joe Minichino, Joseph Howse. Learning OpenCV 4 Computer Vision with Python 3: Get to grips with tools, techniques, and algorithms for computer vision and machine learning - Packt Publishing; 3rd ed. edition (February 20, 2020). - 372 p.
