Final Project Presentations:

Flower Recognition: Feature Analysis and Fusion [Shun-Xuan Wang and Wenqian Liu]
(best results to date on the Oxford Flowers Dataset)

Automated Axon Segmentation Using Spatio-Temporal Independent Component Analysis
[John Bowler and Mo Zhou]

Identifying Animals in the Wild [Chia Kang Chao and Yen‐Cheng Chou]

From ImageNet to Serengeti: Recognizing Animals in Wild Scenes [Guangnan Ye and Maja Rudolph]

Recognition of Animal Skin Texture Attributes in the Wild [Amey Dharwadker and Kai Zhang]

Safer Driving through Gesture Control [Kartik Darapuneni, Shuheng Gong, and Jianze Wang]

---

General Info

Projects will be done in groups of two or three students depending on the total number of students in class. We expect students to spend significant time on their projects. Each team will have to write a paper (4-8 pages) as a final technical report.

Project Proposal

Students will have to prepare a project proposal presentation describing their project plan. You may check a few project ideas that we prepared for you. Each team may also come up with their own project idea, which should be related to the syllabus and approved by the instructors. You may check the resources link for publicly available source code and datasets, which can serve as basis for projects.

Project Updates

Each group of students will have to give two short update presentations in class describing their progress. Check the deadlines and the required content for the Project Update 1 and Project Update 2.

Final Project Presentation and Technical Report

Each team will have to write a Project Paper (4-8 pages) and give a Final Project Presentation in class summarizing the main project goals and accomplishments.

Project Grading

Projects will be graded according to the following criteria:

• Project Proposal (10%)
• Project Update I (20%)
• Project Update II (20%)
• Final Project Report and Presentation (50%)
  • Write-up (15%) - Clarity, language, organization, literature survey, references, discussion
  • Technical (15%) - Originality, correctness, depth
  • Evaluation and Results (10%) - Thoroughness in analysis and experimentation, results and performance
  • Project Presentation (10%)

Spring 2013 EECS 6890 Final Project Presentations:

Macro-Scale Vision: Morphology Classification in Galaxy Imagery [Brendan Jou, Joseph G. Ellis, and Jie Feng]

Large-Scale Galaxy Image Retrieval [Yin Cui, Yongzhou Xiang, and Kun Rong]

Fusing Feature Descriptors for Action Recognition in Videos [Qian Liang, Chen Xue, and Jiawei Chen]

Historical Building Finder (Columbia Tour VIDEO DEMO) [Yanling Zhang, Yaqing Mao, Yan Peng]

RGBD Face Detection [ZhongJie Bi]

---