2010 — 2013 |
Barenholtz, Elan |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Arra: Identifying Objects Within Scenes: Combining Context and Features in Visual Object Recognition @ Florida Atlantic University
This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).
Despite nearly half a century of research, the human ability to recognize objects visually remains a largely unsolved puzzle. Previous research on object recognition has primarily considered cases in which the target is viewed in isolation. However, the visual system can use contextual information -- such as the presence of other objects in the scene or knowledge about the kind of environment in which the object is found -- to determine the identity of an object as well. The contribution of this kind of information is especially clear when the image of the object itself is insufficient on its own. For example, a small yellow patch might be identified as a partially obscured banana in the context of a fruit bowl or as a leaf in the context of a tree. In an NSF-funded research project, Dr. Elan Barenholtz at Florida Atlantic University will use behavioral and computational techniques to examine two central questions regarding the role of context in object recognition: 1) How do people acquire knowledge about the relations between objects and their contextual scenes (for example, the likelihood of specific objects appearing in a certain type of context)? 2) How is this knowledge put to work in recognizing objects whose images have been degraded and cannot be recognized on their own? This research will employ two experimental methodologies: The first will use computer-generated artificial scenes in which participants must first learn the object/context relations from scratch and later use this knowledge in a recognition task. The second technique will test object recognition abilities in photographs of real world environments, including pictures of participants' own homes or workplaces. In this case, subjects will have knowledge about the expected object/context relations, based on their long-term experience, particularly when the environment is highly familiar to them. Human performance in these tasks will be assessed using statistical methods to assess the contribution of contextual information in object recognition.
Understanding human visual object recognition holds great promise for brain science -- as much as a third of the human cortex is thought to be devoted to visual processing. Such understanding is also important for designing artificial vision systems, which carry an enormous array of potential applications. However, previous theoretical techniques, which focused on specialized algorithms for extracting 3-dimensional structure from individual objects, have proven largely unsuccessful. Dr. Barenholtz's research represents a strong departure from earlier approaches, as it assumes that visual recognition relies on inferential strategies that draw on an individual's broad knowledge about the world and his or her experience with specific environments. This approach treats vision as relying on similar tools as other cognitive processes, such as inference and decision-making, suggesting that there may be a great deal of previously unexplored common ground across these different disciplines. By putting the "cognition" back into "recognition," this research has the potential to contribute to some long awaited breakthroughs in the field of visual recognition.
|
1 |
2020 — 2025 |
Furht, Borko [⬀] Khoshgoftaar, Taghi (co-PI) [⬀] Tappen, Ruth (co-PI) [⬀] Barenholtz, Elan Robishaw, Janet |
N/AActivity Code Description: No activity code was retrieved: click on the grant title for more information |
Nrt-Hdr: Graduate Traineeship in Data Science Technologies and Applications @ Florida Atlantic University
Data science and analytics is an emerging transdisciplinary area comprising computing, statistics, and various application domains including medicine, nursing, industry and business applications among others. A significant shortcoming of the current graduate curricula in the U.S. is that scientists and engineers are well trained in their own areas of specialty but lack the integrative knowledge needed for new scientific discoveries and industry applications made possible by data science and analytics. The National Science Foundation Research Traineeship award to Florida Atlantic University (FAU) will address these shortcomings by proposing a new model of convergent education through experiential learning. Transdisciplinary education brings integration of different disciplines in a harmonious manner to construct new knowledge and uplift the student to higher domains of cognitive abilities and sustained knowledge and skills. The traineeship anticipates providing a unique and comprehensive training opportunity for approximately one hundred sixty graduate students (160), including thirty five (35) funded trainees. Thirty faculty members from five colleges and ten departments will participate in the program. The program has the potential to have a significant impact on training practices for future data science professionals.
Primary training elements of the curriculum will include the development of normalization courses, the creation of different testbeds for the various application domains, boot-camps, in-depth elective courses, and professional workshops. Normalization courses will be used to address various background of students entering the program. The convergent research themes will focus on three data science and analytics areas: (i) medical and healthcare applications, (ii) industry applications, and (iii) data science and AI technologies. To address these, the goal is to create a curriculum for graduate students in data science and analytics, where each course will be developed by at least two faculty members from two different disciplines. In order to integrate research and training, multiple testbeds for different application domains will be developed in a newly created Data Science and Artificial Intelligence Laboratory. Each testbed, which relates to a research project, will include a computer platform, software tools, and a set of learning modules. Research projects will be formulated jointly with industry partners who are members of the NSF Industry/University Cooperative Research CAKE (Center for Advanced Knowledge Enablement) at FAU. The program will produce graduates with technical depth and understanding of data science technologies and applications.
The NSF Research Traineeship (NRT) Program is designed to encourage the development and implementation of bold, new potentially transformative models for STEM graduate education training. The program is dedicated to effective training of STEM graduate students in high priority interdisciplinary or convergent research areas through comprehensive traineeship models that are innovative, evidence-based, and aligned with changing workforce and research needs.
This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.
|
1 |