The Purdue Biometrics lab undertakes a number of different projects that are sponsored commercially. Commercial projects include work for a number of major biometric companies across a wide range of modalities. Integrating students into the negotiation with the help of these sponsored projects will provide students with real-world experiences. This would be unique and transformative for the students, as well as our lab. Here are a couple of projects that have done and are currently working on:
Jacob Hasslegren and Mike Brockly will participate in Educating the Next Generation of Standards Professionals. In an effort to foster networking and mentoring amongst ANSI members and the next generation of standards and conformity assessment professionals, ANSI is hosting a breakfast and workshop in Washington, DC on October 12, 2012, as part of the World Standards Week series of events. The invitation-only workshop will begin at 9:45 a.m. and will focus on a standards simulation exercise provided by the National Institute of Standards and Technology (NIST) entitled Setting Standards: Exercise in Strategy and Cooperation in Standardization Process that explores the analytical and practical skills needed to successfully engage in standards negotiations. The simulation will enable participants to acquire a feeling for the political-economic stakes in standardization, gain insight in standards-related interests and strategies, experience the importance of standards procedures, and understand the role of individuals in standards processes.
Under the guidance of a moderator, participants will negotiate a standard for a fictional next generation technology and simulate a real standardization process by role-playing and completing strategic tasks. Afterwards, a three-phased evaluation will be used to reflect on participants’ experiences, focusing on lessons for real-life standardization. This one-day workshop will be an excellent skill-builder for both newcomers and those already participating on standards development committees at the national or international level.
An Introduction to Standards: Why, where and how are they developed?
This course will provide a brief overview of standards, defining types as well as key definitions and terms. The course will then describe ANSI’s role in the standardization process. Lastly, the process by which ANSI participates in the international standardization arena will be covered, along with an overview of regional and international organizations. This course is divided into the following modules:
Introduction to Standards
ANSI’s Role in U.S. Standardization
ANSI’s Role in International Standardization
Title: On improving interoperability of fingerprint recognition using resolution compensation based on sensor evaluation
Authors: Jihyeon Jang, Stephen Elliott, Hakil Kim
Publication date: 2007
Journal name: Advances in Biometrics
Publisher: Springer Berlin/Heidelberg
The purpose of this paper is the development of a compensation algorithm by which the interoperability of fingerprint recognition can be improved among various different fingerprint sensors. In order to compensate for the different characteristics of fingerprint sensors, an initial evaluation of the sensors using both the ink-stamped method and the flat artificial finger pattern method was undertaken. Then the resulted image resolution was incorporated to the compensation algorithms. This paper proposes Common resolution method and …
The College of Technology is committed to creating an inclusive and intellectually stimulating environment where its faculty, staff and students, from many diverse backgrounds and life experiences, are treated equitably and with respect. Diversity is inclusive, celebrates differences and common ground, and promotes respect among all people. A culture of openness of ideas and thoughts in learning, research and engagement in the College and across campus is essential. We value the inherent possibilities in creating an environment where a range of life experiences and scholarly expertise add to our inclusiveness.
The Biometrics Lab is participating in a number of outreach programs being held this year.
Saturday, November 17, 2012
Come to campus and explore the many ways you can take advantage of technology. Technology is more than a machine or a gadget. It is a way of thinking about today’s challenges and overcoming them with innovation, creativity and hard work. Bring a family member (a parent or guardian) and discover the world of opportunity that awaits at Purdue’s College of Technology. Each of you will be able to experience technology projects firsthand. You’ll see technology applied in a variety of ways. You’ll see how technology can impact lives, individually and on a grander scale.
Saturday, October 20, 2012
8:00 a.m.—3:30 p.m. in Knoy Hall
Optional campus tour available at 3:30pm
You already know technology is fun and interesting. Let us show you how technology also moves the world forward. Technology is relevant. Technology is Responsive. And it yields results.
You and a family member are invited to discover the world of opportunity that awaits at Purdue’s College of Technology. Each of you will be able to experience technology projects firsthand.
This one-day program is designed to provide an overview of the academic programs offered at the College of Technology. You’ll see technology applied in a variety of ways. You’ll see how technology can impact lives, individually and on a grander scale. The College of Technology’s programs are centered on four broad areas: engineering principles, computing, technology management, and professional programs.
For more information, please contact the College of Technology Diversity Office at 765-494-2331.
Each semester, we embark on a number of student projects. The first process is to get the students to come up with some ideas. To accomplish this in a two-hour lab format, we ask each student for some of their ideas. The lab instructors write each of these ideas up on large Post-it notes, and then we start to listen to each of these ideas. Some ideas may overlap – so we typically merge these ideas. Once everyone understands the ideas, the instructor and lab TA’s review ideas. Their overarching desire is to complete the project (so manage the scope), make sure it aligns with the course learning objectives, and to ensure it is practical (and for data runs, to make sure we have the data). After the projects are streamlined, the students then vote on the ideas. There is a maximum of 10 students per lab section, so each lab section has a maximum of 4 projects. The projects do not have to be biometric related, nor do they have to be data runs or analysis – some projects can also be a literature review.
At the end of the lab period, we have a draft set of ideas, which will be expanded on during the next lab period.
Next week, students will work on their statement idea, the demand category (an internal metric on the projects), the pro’s and con’s (We want to emphasize the need to detect con’s because there should be more con’s than pro’s). Students will be asked whether the cons be resolved? We will also ask:
* why are you proposing this idea?;
* where was the idea generated?
* Can you find a couple of other sources to explain the need for this?
* Do you think the project can be completed?
This will give the instructors and teaching assistants an idea of where the students are going with the project. By the end of the next lab period, the students should have a firm understanding of what they will be doing over the semester.
The initial ideas presented this week, and ones that will be discussed next week will be:
* Face recognition quality
* Quality & Henry Classifications on different fingerprint sensors
* Face segmentation to standards
* RFID/NFC vulnerabilities
* Performance on different fingerprint force levels
* Signature verification and HBSI
* Vein cradle / no cradle interaction time
* Compression on image performance
* RFID & tag life expectancy
* Biometrics as a form of payment
* Interoperability of fingerprint templates
* Age & interaction time
* Survey of training instructions
If you are interested in any of these projects, please leave a comment on the webpage.
As you can see, the class covers a lot of material. To supplement the lecture material, we have students review case studies and company presentations that are shown on YouTube. We select these videos to tie into the presentations and provide information that supplements the lecture component. Also, as we have a large testing operation, students are also exposed to the specific devices that we discuss in class. For example, at the moment we are conducting a multi-modal, multi-visit, multi-sensor data collection and this includes iris recognition. Students working in the lab have designed data collection tools to maximize the accuracy of data collection, and to push the research envelope further.
One of our current studies is to examine aging of biometrics, and as part of this analysis we use iris recognition. We can tie in current research with classroom lectures providing a greater depth of interest for the students. In this lecture, we provide an overview of:
* Describe the anatomy of the eye
* Learn about history of iris recognition
* List the different types of iris acquisition devices
* Describe the steps in iris image processing
* Describe the steps in iris image matching
* List advantages/disadvantages of iris recognition
* Describe the various applications for iris recognition
For those students currently enrolled, you can access the lecture via i-Tunes.
The BSPA Lab is currently researching how people interact with biometric sensors over time. This study is a multi-sensor, multi-modal, multi-visit data collection involving fingerprint, hand geometry, face, dynamic signature verification, palm vein, and iris modalities.
As part of this data collection, researchers in the lab are using the Microsoft® Kinect(TM) technology to collect data that enables them to examine how posture affects the performance of various modalities, and subsequently how it relates to the HBSI model. The Kinect(TM) research is based on methodology developed by undergraduate students, graduate students, and faculty at Purdue University. Their findings are described in more detail here. The Kinect(TM) sensors are used to gather X, Y, and Z coordinates of a subject’s body position relative to the sensor he/she is interacting with. Using these coordinates gathered on 20 different points of the body (head, neck, right shoulder, left shoulder, etc.), researchers are able to gather quantifiable data on the subjects position in relation to the biometric sensor to better understand how the subject’s body position affects an interaction.
The analysis and refinement of the Kinect(TM) technology’s use in the data collection and the HBSI model will be updated on this webpage. Researchers also plan on highlighting this research in several teleconferences throughout the 2012-2013 academic year.
This week, we started to analyze Dr. Shimon Modi’s dissertation data and replicate it using an updated matcher.
We will be working on assessing the dataset, and examining image quality across the sensors, as well as rerunning data in a new matcher. Dr. Modi will be discussing the results in a Webex teleconference with the students.