Skip to main content Skip to navigation
Manoj Karkee Agricultural Automation and Robotics Lab

BSysE 530 – Machine Vision for Biological Systems

Spring 2018 Course Policy and Syllabus


Meeting Time and Place:

  • Class meets on Wednesday and Friday at 2:10PM to 3:25PM in Room 125 Ag Tech Building, Center for Precision and Automated Agricultural Systems (CPAAS) – Prosser, WA and via Telecommunications (AMS) to Pullman and TriCities

Instructor:  Manoj Karkee

·         Office Hours: Friday 3:30PM to 4:30PM or by appointment (remote students can reach me via Skype, Whatsapp, Viber, Wechat or any medium of communication as preferred; ID will be provided)

·         Office: 105 Ag Tech Building

·         Phone:  509-786-9208

·         Email:



The major objective of BSysE 530 is to help students understand and apply image processing techniques and machine vision systems to solve engineering and scientific problems of their interest. Most of the examples and homework problems will be related to agricultural and biological systems. However, the concept learned in this class can be applied to solve a wide range of problems in various disciplines including science, engineering and medicine.



It is anticipated that the students have taken two or more undergraduate level math classes including exposure to calculus and linear algebra. It is also expected that the students have some programming background and/or interest to learn Matlab-based programming.


Required Texts:

  • [1] L. Shapiro and G. Stockman, Computer Vision. Prentice-Hall. 2001.
  • [2] Gonzalez, Woods and Eddins, Digital Image Processing with Matlab.


Required Reading (Each Wednesday, one student will be randomly selected for brief discussion on the reading from previous week):


Week#01: Aloimonos and Rosenfeld, 1991. Computer Vision. Science, 253 (5025): 1249-1254 – Sep 1991.

Week#02_01: Sistler, 1987. Robotics and intelligent machines in agriculture. IEEE Journal of Robotics and Automation, 3(1):3-6.

Week#02_02: Narendra and Hareesh, 2010. Prospects of computer vision, automated grading and sorting systems in agricultural and food products for quality evaluation. International Journal of Computer Applications, 1(4): 1-9.

Week#03: Gongal, A., S. Amatya, M. Karkee, Q. Zhang, and K. Lewis. 2014. Sensors and Systems for Fruit Detection and Localization: A Review. Computers and Electronics in Agriculture, 116:8-19.

Week#04: Milella, Reina and Foglia, 2006. Computer vision technology for agricultural robotics. Sensor Review, 24(4): 290-300.

Week#05: Bolle, Connell, Haas, Mohan and Taubin, 1996. Veggie vision: a produce recognition system. WACV 1996. IEEE.

Week#06: Mehl, Chen, Kim and Chan. 2004. Development of hyperspectral imaging technique for the detection of apple surface defects and contaminations. Journal of Food Engg, 61: 67-81.

Week#07: Leemans, Megein and Destain, 2002. On-line fruit grading according to their external quality using machine vision. Biosystems Engineering, 83(4): 397-404.

Week#08: Lottes, P., Hörferlin, M., Sander, S., & Stachniss, C. (2017). Effective Vision‐based Classification for Separating Sugar Beets and Weeds for Precision Farming. Journal of Field Robotics, 34(6): 160-178.

Week#09: Bargoti, S. and Underwood, J.P., 2017. Image segmentation for fruit detection and yield estimation in apple orchards. Journal of Field Robotics.

Week#10: Reid, Zhanga,  Noguchi,  Dickson, 2000. Agricultural automatic guidance research in North America. Computers and Electronics in Agriculture, 25(2): 155-167.

Week#11: Week#11: Shrestha, D. S., Steward, B. L., & Birrell, S. J. (2004). Video processing for early stage maize plant detection. Biosystems engineering, 89(2), 119-129.

Week#13: A Method for Three Dimensional Reconstruction of Apple Trees for Automated Pruning. Transactions of the ASABE, 58(3): 565-574.



  • Jain, R. Kasturi and B. Schunck, Machine Vision,McGraw Hill, 1995
  • Forsyth and Ponce, Computer Vision: a modern approach, Prentice-Hall 2002 (available online at University of Washington homepage).
  • Gonzalez and R. Woods, Digital Image Processing, 3rd edition, Prentice Hall, 2008.
  • Trucco and A. Verri, Introductory Techniques for 3-D Computer Vision, Prentice Hall, 1998.
  • Kecman, Learning and Soft Computing (Available for online reading through WSU library)


Matlab References:

  • Pratap, Getting Started with MATLAB 7: A Quick Introduction for Scientists and Engineers, Oxford University Press.
  • Matlab Online Resources.


Relevant Journals:

  • Transactions of the ASABE
  • Computers and Electronics in Agriculture
  • Biosystems Engineering
  • International Journal of Computer Vision
  • IEEE Workshop on Applications of Computer Vision
  • IEEE Journal of Robotics and Automation
  • IEEE International Conference on Intelligent Robots and Systems (IROS)
  • Journal of Field Robotics


Course Assignments:

Homework:  Seven homework assignments have been scheduled for the semester.  Some homework assignments need formal written report, others need just well-commented code and results. Please see the schedule to find out which homework requires a formal report. Suggested format for the formal report will be provided. Students may report in a different format as long as all necessary information is included.

Class Project:  You are required to prepare an individual project proposal with a clearly identified need or problem that will be addressed through the techniques and algorithms learned in this course. Your project will be presented to the class at end of the semester.  A written project proposal and a final report will also be required. Format will be provided.

Exams: There will be NO formal exams. It is expected that students will have learned enough material to complete homework assignments and class project.


Web Page and E-mail:

The course has a Blackboard Page ( where you can find all the class materials. Code and results for all the assignments and soft copy of formal reports will be uploaded to Blackboard page. Only if there is a technical problem to work on Blackboard, these materials can be submitted to with subject line including keywords BSysE530 and/or Machine Vision.

Basic course materials is also available at


Component Percent of Final Grade
Class Participation 10%
Homework 45%
Project Proposal 10%
Final Project Presentation 15% (Partly Peer Evaluation)
Final Project Report 20%


Expected breakdown of the grade is as follows

Score                           At least a letter grade of:

≥ 90                                         A-

≥ 80                                         B-

≥ 70                                         C-

≥ 60                                         D-

Course Policies:

Homework and Project Assignments:  Homework are due at 11:59 on the due date indicated on the assignment.  Late homework/assignment may receive a 10 % reduction for each day it is late, with no credit given to the assignment handed in after subsequent homework is due.

Grading disagreements: Any disagreements on the grading need to be given to me in writing.  Disagreements will only be considered up to a week after the graded material is returned.


Safety Statement

Classroom and campus safety are of paramount importance at Washington State University, and are the shared responsibility of the entire campus population.  WSU urges students to follow the “Alert, Assess, Act” protocol for all types of emergencies and the “Run, Hide, Fight” response for an active shooter incident. Remain ALERT (through direct observation or emergency notification), ASSESS your specific situation, andACT in the most appropriate way to assure your own safety (and the safety of others if you are able).

Schedule of Classes:                          Note: Schedule may be adjusted slightly as the class progresses!

Week Date Topic Reading [One Article Per Week +] Assignment
Wk 1


Jan 17 1.      Introduction [2]-Ch2,Wikipedia,

[1]*-Ch1; [2]**-Ch1

Jan 19 2.      Matlab Tutorial [2]-Ch2 HW1 Out
Wk 2


Jan 24 3.      Binary Image Processing [1]-Ch3; [2]-Ch10
Jan 26 4.      Morphology [1]-Ch3; [2]-Ch9 HW2 Out
Wk 3 Jan 31 5.      Image Acquisition [1]-Ch2 HW1 Due
Feb 02 6.      Image calibration and Registration [2]-Ch5 HW3 Out
Wk 4 Feb 07 7.      Image Enhancement [1]-Ch5; [2]-Ch3


HW2 Due: Formal report
Feb 09 8.      Spatial Filtering [1]-Ch5; [2]-Ch3 HW4 Out
Wk 5 Feb 14 9.      Edge detection [1]-Ch5; [2]-Ch4 HW3 Due
Feb 16 10.     FFT and Frequency Domain Filtering [1]-Ch5; [2]-Ch10 HW5 Out
Wk 6 Feb 21 11.     Color and Color Image Processing [1]-Ch6; [2]-Ch6 HW4 Due: Formal report
Feb 23 12.     Multi/Hyper Spectral Image Analysis
Wk 7 Feb 28 13.     Texture and Shape Analysis [1]-Ch7 ; [2]-Ch11 HW5 Due
Mar 02 14.     Segmentation [1]-Ch10; [2]-Ch10 HW6 Out
Wk 8 Mar 07 15.     Hough Transform Project Proposal Due
Mar 09 16.     Classification and Recognition 1 [1]-Ch4; [2]-Ch12 HW7 Out
Wk 9 Mar 14 17.     Classification and Recognition 2 [1]-Ch4 HW6 Due: Formal report
Mar 16 18.     Soft Computing Techniques:

-Neural Network

[1]-Ch10; [2]-Ch10  
Mar 19-23 Classes Recessed: Spring Vacation
Wk 10 Mar 28 19.     Motion/Video Processing [1]-Ch 9; [2]-Ch1 HW7 Due
Mar 30 20.     Tracking – Kalman Filtering
Wk 11 Apr 04 21.     3D Vision Techniques and Sensors [1]-Ch12 – Ch13 Project Time
Apr 06 22.     Stereo Vision [1]-Ch12 –Ch13
Wk 12 Apr 11 23.     3D Transformation [1]-Ch13
Apr 13 24.     3D Reconstruction 1 [1]-Ch13  
Wk 13 Apr 18 25.     3D Reconstruction 2 [1]-Ch13 Project Time
Apr 20 26.     Fuzzy Logic [1]-Ch4
Wk 14 Apr 25 27.     Fuzzy Logic/Genetic Algorithm Project Time
Apr 27 28.     Genetic Algorithm
Wk 15 May 02 Project Time
May 04 Project Time
Wk 16 May 09 Project Presentation
May 11 Project Report Due

* [1] L. Shapiro and G. Stockman, Computer Vision. **[2] Gonzalez et al. DIP with Matlab.