Yu-Ting Li

PhD Candidate, Intelligent System and Assistive Technology Lab

Purdue University

yutingli@purdue.edu

My Philosophy: I am Little but I am Big -- I may look small, but I have Big ideas and Big dream. Then I execute it.

Education     Research     Work Experience     Publication      Resume

• A self-motivated, organized, and diligent researcher with extensive and multi-disciplinary background ranging from Engineering, Science, and Business.

• Solid hands-on experience and algorithm design in computer vision based human-machine interaction, pattern recognition, and image processing

Meet Yu-Ting Li at      

Education

Relevant Courses

• Computer Sciences & Engineering
  • CS 590: Statistical Machine Learning
  • ECE 637: Digital Image Processing
  • ECE 661: Computer Vision
  • ECE 662: Pattern Recognition and Decision Making Process
  • IE 590: Robotics & Machine Vision
• Mathematics
  • IE 537: Optimization Models and Algorithms 
  • IE 633: Dynamic Programming 
  • Nonlinear Programming
• Signal Processing
  • Digital Signal Processing
  • Simulation of Communication Systems
  • Data Communications

[Top]

Research

Embodied Interactions in Human-Machine Interaction

• Developed an effective interface allows the user to interact with data in intuitive ways which would support decision-making by inferring users focus of attention. When the problem is presented visually, the use of whole body movement (ex: hand gesture, facial expression, feet) provides a potential alternative interaction besides of standard interfaces such as mouse and keyboard for completing the task.
• The visual cues of body movements are detected/recognized by means of visual algorithms. Efficient embodied interactions between machine (robot, display, or other agents) and people are investigated through those meaningful visual features.
• Analyzed real-time video data to extract and annotate human body skeleton as evidence for building up cause-effect relationship between attention, physical action, and performance.

Hierarchical Elastic Graph Matching for Hand Gesture Recognition

• Hand gesture recognition has the potential to enable natural communication between human and machines. They have been used in the human–computer interaction (HCI) for the last three decades, since it allows a level of expression and naturalness comparable to that achieved in interpersonal communication
• I proposed and implemented a robust scheme for gesture and face recognition using graph matching and Adaboost.
• Obtained accuracy of 99% on hand posture classification that published on top computer vision journals (Pattern Recognition, Image and Vision Computing).

Selected Papers: HEGM: A Hierarchical Elastic Graph Matching for Hand Gesture Recognition, Recognizing Hand Gestures using the Weighted Elastic Graph Matching (WEGM) Method

Gestonurse:  Collaboration with a Robotic Scrub Nurse     

• A robotic scrub nurse has the potential to reduce errors in the OR by automating the passing of surgical instruments which allows personnel to focus on more complicated tasks such as maintaining a sterile environment, preparing required surgical supplies and monitoring the state of the patient.
• This project developed a novel robotic scrub nurse system contains a Microsoft Kinect depth sensor, robotic arm allowing the user to use natural interaction (recognized gesture and speech commands in real time) reliably.
• Prototyped and verified at the Animal Hospital at Purdue University with 99% object detection accuracy and 97% recognition accuracy, and 4 sec response time

Selected Papers: Collaboration with a Robotic Scrub Nurse, A Cyber-Physical Management System for Delivering and Monitoring Surgical Instruments in the OR, Surgical Instrument Handling and Retrieval in the Operating Room with a Multimodal Robotic Assistant

[Top]

Work Experience

Publications

[1]    Yu-Ting Li, Juan P. Wachs, "Linking Attention to Physical Action in Complex  Decision Making Problems" In Proceedings of the 2014 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2014 (to be appeared) 

[2]    Yu-Ting Li, Juan P. Wachs, “A Bayesian Approach to Determine Focus of Attention in Spatial and Time-Sensitive Decision Making Scenarios ” in Proceedings AAAI-14 Workshop on Cognitive Computing for Augmented Human Intelligence, Québec City, Québec, Canada, 2014 (to be appeared)

[3]    Yu-Ting Li, Juan P. Wachs, "HEGM: A Hierarchical Elastic Graph Matching for Hand Gesture Recognition" in Pattern Recognition (PR), vol. 47, no. 1, pp. 80-88, Jan., 2014.

[4]    Yu-Ting Li, Juan P. Wachs, "Recognizing Hand Gestures using the Weighted Elastic Graph Matching (WEGM) Method" in Image and Vision Computing, vol. 31, no. 9, pp. 649-657, Sep. 2013.

[5]    Yu-Ting Li, Mithun George Jacob, Juan P. Wachs, "A Cyber-Physical Management System for Delivering and Monitoring Surgical Instruments in the OR" in Surgical Innovation, vol. 20, no. 4, pp. 377-384, Aug. 2013.

[6]    Mithun George Jacob, Yu-Ting Li, Juan P. Wachs, George Akingba, "Collaboration with a Robotic Scrub Nurse" in Communications of the ACM (CACM), vol. 56, no. 6, pp. 68-75, May 2013.

[7]    Mithun George Jacob, Yu-Ting Li, Juan P. Wachs, "Surgical Instrument Handling and Retrieval in the Operating Room with a Multimodal Robotic Assistant" in the Proceedings of the 2013 IEEE International Conference on Robotics and Automation (ICRA), May 6-10 2013, Karlsruhe, Germany

[8]    Yu-Ting Li, Juan P. Wachs, "Hierarchical Elastic Graph Matching for Hand Gesture Recognition" in Proceedings of the 16^th Iberoamerican Congress conference on Progress in Pattern Recognition (CIARP), Image Analysis, Computer Vision, and Applications, Buenos Aires, Argentina, 2012, pp. 308-315.

[9]    Mithun George Jacob, Yu-Ting Li, Juan P. Wachs, "Gestonurse: a multimodal robotic scrub nurse" in Proceedings of the 7th Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI), Boston, MA, March 2012, pp.153-154.

[10]    Juan P. Wachs, Mithun George Jacob, Yu-Ting Li, A. George Akingba, "Does a robotic scrub nurse improve economy of movements?" in Proceeding of SPIE 8316, Medical Imaging 2012: ImageGuided Procedures, Robotic Interventions, and Modeling, 83160E, 2012

[11]    Mithun George Jacob, Yu-Ting Li, Juan P. Wachs, "Gestonurse: a robotic surgical nurse for handling surgical instruments in the operating room" in Journal of Robotic Surgery, vol. 6, no. 1, pp. 53-63, March 2012.

[12]  Mithun George Jacob, Yu-Ting Li, Juan P. Wachs, "A Gesture Driven Robotic Scrub Nurse" In Proceedings of the 2011 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2011, pp. 2039-2044. 

[Top]

Awards

[1]    Best Student Paper Finalist - 2011 IEEE International Conference on Systems, Man, and Cybernetics (SMC)

[2]    Studying Abroad Scholarship - 2010 Ministry of Education, Taipei, Taiwan

Selected Press

• "Surgeons could use his hand-gesture system to control robots" - IEEE Spectrum

• "Future surgeons may use robotic nurse, 'gesture recognition'" - Purdue Featured News 

• "Robots and people can all get along" - NPR Marketplace

• "Robotic Nurse in Development at Purdue" - Fox News

• "Camera ensures control of robotic nurse is all in hand" - The Engineer

Activities

•       2008 Mentorship Program, McKinsey & Company, Taipei, Taiwan
  • Trained as a mentee. Learned skills about problem solving techniques and logically thinking ability of consulting company

•       Organizing Member, 2005 National Chiao-Tung University Career Fair, Hsin-Chu, Taiwan
  • Arranged meetings and events over 100 companies with students