Dip/cv syllabus (fall 2020)
Course instructor
Dr. Venkat N. Gudivada
Dr. Venkat N. Gudivada
http://www.cs.ecu.edu/gudivada/, Email: gudivadav15@ecu.edu, Phone: (252) 328 - 9680, Office: SciTech Room 106
Office hours and course communications
TR, 3:00 PM - 5:00 PM and W 8:00 PM - 10:00 PM. All office hours will be held on Microsoft Teams. All communications about the course will occur on Microsoft Teams. Please install Microsoft Teams on your personal computer (it is free for ECU students).
Course description
This is a Fall 2020 cross-listed course of the following: CSCI 4150-001, CSCI 4150-601, CSCI 6040-001, CSCI 6040-601, DASC 6040-001, and DASC 6040-601.
This is a 15-week, full-term course. The course will be offered in hybrid face-to-face (HF2F) mode for students enrolled in CSCI 4150-001, CSCI 6040-001, and DASC 6040-001. The course will meet on TR, 11:00 AM - 12:15 PM. Hybrid delivery means that the course will employ both in-person and online classes. Details will be forthcoming.
For students enrolled in CSCI 6040-601 and DASC 6040-601, the course will be delivered 100% online, asynchronously.
Course teaching assistant
- Von Ithipathachai, email: ithipathachaiv16@students.ecu.edu
Recommended books
- Kaehler, A., & Bradski, G. (2017). Learning OpenCV: Computer Vision in C++ with the OpenCV Library. O’Reilly.
- Gonzalez, R. C., & Woods, R. E. (2017). Digital Image Processing (Fourth ed.). Pearson. http://www.imageprocessingplace.com/
Reference books
- Translational College of LEX. (1995). Who is Fourier? A Mathematical Adventure. Language Research Foundation.
- McAndrew, A. (2015). A Computational Introduction to Digital Image Processing. CRC Press.
- McAndrew, A. (2004). Introduction to Digital Image Processing with Matlab. Thompson Course Technology.
- Smith, S. W. (1997). The Scientist and Engineer’s Guide to Digital Signal Processing. California Technical Publications. http://www.dspguide.com/
- Tanimoto, S. L. (2012). An Interdisciplinary Introduction to Image Processing: Pixels, Numbers, and Programs. MIT Press. https://mitpress.mit.edu/books/interdisciplinary-introduction-image-processing
- Umbaugh, S. E. (2018). Digital Image Processing and Analysis: Human and Computer Vision Applications with CVIPtools (Third ed.). CRC Press.
Student learning outcomes
After successful completion of the course, the students will be able to do the following:
-
Determine the required imaging modalities, image storage requirements, image sampling and quantization rates, and image compression schemes for digital imaging applications.
-
Enhance visual quality of gray scale and color digital images using intensity transformations, spatial filtering, and frequency domain techniques.
-
Solve smoothing and boundary detection problems in binary images using morphological filtering methods.
-
Solve edge detection and image segmentation problems using a range of techniques including thresholding, region growing, region splitting and merging, active contours, and conditional random fields.
-
Develop neural network and deep learning-based solutions to image processing tasks.
Major course topics
- Sensing, acquisition, sampling, and quantization
- Spatial domain filtering
- Frequency domain filtering
- Image restoration and reconstruction
- Color image processing
- Morphological image processing
- Image compression
- Image segmentation
- Deep learning for image processing tasks
Respect for Diversity
It is my intent to serve well in this course all students from diverse backgrounds and perspectives. Students’ learning needs will be addressed both in and out of class. The diversity that students bring to this class be viewed as a resource, strength and benefit. I will strive to present the course content and learning activities that are respectful of diversity: gender, sexuality, disability, age, socioeconomic status, ethnicity, race, and culture. Your suggestions are encouraged and appreciated. Please let me know ways to improve the effectiveness of the course for you personally or for other student groups.
Course assessment and grading scale
Undergraduate students
- Problem-based learning (PBL) assignments (70%)
- Take-home midterm exam (10%)
- Take-home final exam (20%)
Score range | Letter grade |
---|---|
93 - 100 | :A: |
90 - 92 | :A-: |
87 - 89 | :B+: |
83 - 86 | :B: |
80 - 82 | :B-: |
77 - 79 | :C+: |
73 - 76 | :C: |
70 - 72 | :C-: |
67 - 69 | :D+: |
63 - 66 | :D: |
60 - 62 | :D-: |
59 or below | :F: |
Graduate students
- Problem-based learning (PBL) assignments (70%)
- Take-home midterm exam (10%)
- Take-home final exam (15%)
- Innovative contribution to online course content (5%)
Score range | Letter grade |
---|---|
90.0 - 100 | :A: |
80.0 - 89.9 | :B: |
70.0 - 79.9 | :C: |
< 69.9 | :F: |
Extra credit (up to 5%) assignments are available to both graduate and undergraduate students. Those who wish to seek extra credit, check with the course instructor.