Project Description

Throughout Marquette University's 10-week summer REU program, Computation Across the Disciplines, I will be researching applications of graph theory to computer vision and image segmentation problems. More specifically, I hope to be able to utilize the graph-cut technique in order to isolate images of the heart and its components from CT scans provided by local hospitals. I will be working under the guidance of Dr. Naveen Bansal.

Week 1 (5/29 - 6/1)

Tuesday 5/29

Attended REU orientation
Met briefly with Dr. Bansal to begin planning the summer's research

Wednesday 5/30

Read introduction to Neural Networks: a Comprehensive Foundation
Met with Dr. Bansal and graduate student to begin learning about statistical applications to image segmentation

Thursday 5/31

Met with graduate student to obtain preliminary research publications
Met with Dr. Bansal to clarify research goals and outline the structure of the project
Read several research articles and located five articles for further reading

Friday 6/1

Familiarized myself with several graph-theoretic terms and concepts, in preparation for future research
Completed Fast Approximate Energy Minimization via Graph Cuts (Boykov et al.)
Located and obtained the Ford-Fulkerson publication on flow networks in Memorial Library

Week 2 (6/4 - 6/8)

Monday 6/4

Completed Interactive Graph Cuts for Optimal Boundary & Region Segmentation of Objects in N-D Images (Boykov et al.)
Completed An Omptimal Graph Theoretic Approach to Data Clustering: Theory and Its Applications to Image Segmentation (Wu et al.)
Began Graph Cuts and Efficient N-D Image Segmentation (Boykov et al.)

Tuesday 6/5

Completed Graph Cuts and Efficient N-D Image Segmentation (Boykov et al.)
Completed Normalized Cuts and Image Segmentation (Shi et al.)

Wednesday 6/6

Began writing code for GraphCut algorithm, completed about 350 lines

Thursday 6/7

Finished a rough draft of the GraphCut algorithm, totaling about 700 lines
Attended weekly REU luncheon and learned about the do's and don't's of research presentations
Met with Dr. Bansal to give a progress report and discuss next steps
Completed module 1 of the Responsible Conduct of Research training

Friday 6/8

Completed modules 2 and 3 of the Responsible Conduct of Research training
Began to modify GraphCut algorithm (fixing various syntax errors and adding small improvements)

Week 3 (6/11 - 6/15)

Monday 6/11

Continued to fix GraphCut algorithm
Found more efficient storage for Graph data structure
Fixed several initialization errors
Added several fringe cases onto the algorithm, now totals about 1200 lines
Finished second draft of GraphCut algorithm

Tuesday 6/12

Met with grad student to discuss generalities of GraphCut algorithm
Worked with grad student to implement algorithm

Wednesday 6/13

Attended the Ethics in Research training session, proctored by Dr. Brylow

Thursday 6/14

Continued revisions of GraphCut algorithm in preparation for its first test run
Met with Dr. Bansal for our weekly progress report
Took preliminary steps to obtain image data for future use with the GraphCuts algorithm
Sought out different implementations of the max-flow/min-cut algorithm to compare to (and possibly combine with) my current GraphCut algorithm

Friday 6/15

Continued to modify GraphCut algorithm
Added condensation method to GraphCut algorithm in an attempt to conserve memory

Week 4 (6/18 - 6/22)

Monday 6/18

Read An Experimental Comparison of Min-Cut/Max-Flow Algorithms for Energy Minimization in Vision (Boykov et al.)
Modified GraphCut algorithm based on Boykov's active node method of operation
The GraphCut algorithm is approaching completion, should be ready for testing by next week

Tuesday 6/19

Fixed several syntax and arithmetical errors in the GraphCut algorithm
Met with Dr. Bansal and graduate student to obtain image segmentation data set
With new image data as reference, I began to write main method for reading in image and implementing the graphCut method (completed about 600 lines)

Wednesday 6/20

Completed code for handling the graphics of the GraphCut algorithm, algorithm now totals about 2500 lines
Encountered import errors involving the graphics package, began to search for an appropriate library download

Thursday 6/21

Began to create a new Java library to handle graphics of GraphCut
Acquired necessary source code for new library from GitHub
Attended weekly REU luncheon to share progress and attended a presentation on computer science education
Met with Dr. Bansal for our weekly progress report and showed him the GraphCut algorithm as it currently stands

Friday 6/22

Continued to work on constructing graphics library from source code

Week 5 (6/25 - 6/29)

Monday 6/25

Finished constructing the graphics library from source code
Began to fix residual errors resulting from new graphics library
Began to prepare presentation for Thursday's midterm presentation

Tuesday 6/26

Continued fixing residual errors resulting from new graphics library
Continued to work on presentation for Thursday's midterm presentation

Wednesday 6/27

Finished rough draft of midterm presentation
Began practicing midterm presentation and making appropriate modifications
Continued fixing residual errors resulting from new graphics library

Thursday 6/28

Finished final edits of midterm presentation
Attended the weekly REU luncheon and presented my midterm presentation

Friday 6/29

Finished fixing residual errors resulting from new graphics library
Finished debugging GraphCut algorithm
Prepared main method of GraphCut algorithm for testing on imagery

Week 6 (7/2 - 7/6)

Monday 7/2

Began writing main method of GraphCut algorithm
Finished constructing handling of GraphCut class within the main method
Struggled to construct handling of Graph_Cut class (graphics implementation) within the main method

Tuesday 7/3

Finished first instance of main method
Performed a trial run of the completed GraphCut algorithm, but trial was unsuccessful
Began to read through pertinent code to search for sources of error
Began to do background reading/research on GUIs in order to better understand the graphics packages and library of the GraphCut algorithm

Thursday 7/5

Continued to search code for sources of error in GraphCut algorithm
Concluded that the error must be coming from the Graph_Cut class
Attended the weekly REU luncheon and listened to a Latex tutorial
Met with Dr. Bansal for our weekly progress report

Friday 7/6

Continued to search code for sources of error in Graph_Cut class
Continued with background reading on GUIs

Week 7 (7/9 - 7/13)

Monday 7/9

Continued searching code for error
Fixed minor error regarding instance variables in the main method, but algorithm still did not run properly

Tuesday 7/10

Continued to search code for error
Overhauled the main method, fixing all but one (crucial) error
Ran a test of the GraphCut algorithm, was able to open the gui window, but was unable to add to it any content
After reworking main method, entire algorithm is now error-free, and yet it now fails to build

Wednesday 7/11

Located and fixed several errors in GraphCut algorithm
Identified several class cast exceptions and began searching through different packages to find solutions

Thursday 7/12

Identified one class cast exception that was indirectly causing nearly all other such exceptions in the algorithm
Sought out solutions to this originating class cast exception
Attended weekly REU luncheon
Met with Dr. Bansal for our weekly progress report

Friday 7/13

Discovered that the originating class cast exception may have been caused by an import error with the graphics library
Began making appropriate changes to graphics library

Week 8 (7/16 - 7/20)

Monday 7/16

Finished making documentation and import corrections to graphics library
Began fixing newfound inconsistencies between updated graphics library and GraphCut algorithm

Tuesday 7/17

Began putting together poster for REU poster presentation in two weeks

Wednesday 7/18

Continued working on poster
Met with Dr. Bansal to discuss recent challenges pertaining to GraphCut algorithm and also to get feedback/ideas for poster and report

Thursday 7/19

Put finishing touches on poster
Attended weekly REU luncheon
Continued to fix inconsistencies between updated graphics library and GraphCut algorithm

Friday 7/20

Revised certain elements of poster after realizing dimensions needed to be adjusted
Continued to fix inconsistencies between updated graphics library and GraphCut algorithm
began outline and formatting of research paper (due 8/3)

Week 9 (7/23 - 7/27)

Monday 7/23

Continued outlining and writing research paper
Finished rough drafts of the introduction and background on graph theory subsection
Began writing the applications of graph theory subsection
Continued debugging GraphCut algorithm

Tuesday 7/24

Finished writing the applications of graph theory subsection
Finished writing the algorithm introduction, as well as the algorithm overview subsection
Continued debugging GraphCut algorithm

Wednesday 7/25

Completed the current status and challenges subsection
Completed the conclusions section
Began the abstract
Began reviewing the paper and making minor edits
Continued debugging GraphCut algorithm

Thursday 7/26

Continued to review and edit paper
Added visual aids (with captions) to both the graph theory and algorithm sections
Attended the weekly REU luncheon
Received printed poster and began to prepare for poster presentation on Monday
Continued debugging GraphCut algorithm

Friday 7/27

Continued to review and edit paper
Began working on final presentation
Continued debugging GraphCut algorithm

Week 10 (7/30 - 8/3)

Monday 7/30

Presented poster during the morning presentation session
Finished rough draft of final paper, sent it to Dr. Bansal for critiques/feedback
Continued debugging GraphCut algorithm

Tuesday 7/31

Finished final presentation slides, began practicing for Wednesday/Thursday presentation
Continued debugging GraphCut algorithm

Wednesday 8/1

Final presentation before REU students and mentors
Continued debugging GraphCut algorithm

Thursday 8/2

Continued to edit final paper
Continued debugging GraphCut algorithm

Friday 8/3

Finalized and submitted paper

User:Saweiner

Contents