 |
|
New software advances photo search and management in online systems
October 16, 2007Searching for digital photographs could become easier with a Penn State-developed software system that not only automatically tags images as they are uploaded, but also improves those tags by "learning" from users' interactions with the system.
"Tagging itself is challenging as it involves converting an image's pixels to descriptive words," said James Wang, lead researcher and associate professor of information sciences and technology (IST). "But what is novel with the 'Tagging over Time' or T/T technology is that the system adapts as people's preferences for images and words change."
In other words, the system can accommodate evolving vocabulary and interpretations to images that people have uploaded and are uploading to systems such as Yahoo's Flickr. This allows the T/T system's vocabulary to grow, replacing old tags with more relevant and more specific new tags, Wang said.
In tests, the T/T technology correctly annotated four out of every 10 images, a significant improvement over the researchers' earlier annotation system, ALIPR or Automatic Linguistic Indexing of Pictures-Real Time. That system offered users a list of 15 possible annotations or words for an image-one of which was correct for 98 percent of images tested.
"The bottom line is that the system makes it easier to find photographs and is able to improve its performance by itself as time passes," said Ritendra Datta, a graduate student in computer science working with Wang. "The advancement means time savings for consumers as well as improved searching and referral capabilities."
The system was described in a paper, "Tagging Over Time: Real-world Image Annotation by Lightweight Meta-learning," presented at the recent ACM Multimedia 2007 conference in Augsburg, Germany. The authors were Datta; Dhiraj Joshi, a former graduate student in computer science; Jia Li, associate professor, Department of Statistics; and Wang. Penn State has filed a provisional patent application on this invention.
In the researchers' previous system, pixel content of images was analyzed to suggest annotations. In the new software, researchers have added a machine-learning component that enables the computer to learn from the user's interactions with photo-sharing systems.
Images of the World Trade Center, for instance, once would have been tagged with "financial center," "business" or "market success." Users today, however, have different associations or tags for the Twin Towers. The researchers' new system has the capability to learn from such changes and reflect them automatically in refining the old tags and generating future tags.
As the system adapts to such changes, it also enhances tagging performance. With an initial accuracy of 40 percent, the system's precision improves over time and can reach a level of up to 60 percent correct, Datta said.
In a companion paper, "Learning the Consensus on Visual Quality for Next-Generation Image Management," which also was presented at the ACM conference, the researchers described a new system which can automatically select "aesthetically pleasing" images and isolate out those images of low or poor quality. To do this, the system uses visual features such as contrast, depth-of-field indicators, brightness and region composition from publicly rated photographs to learn the statistical models for high- and low-quality images.
"With this system, users can more easily identify the best photographs in their collections," Datta said. "The system also suggests images which should be deleted from the digital cameras to make storage space for new photographs, for example."
The system can also improve image search engines by prioritizing visually pleasing images among the search results, Wang added. The National Science Foundation supported research on both systems.
Penn State
In tests, the T/T technology correctly annotated four out of every 10 images, a significant improvement over the researchers' earlier annotation system, ALIPR or Automatic Linguistic Indexing of Pictures-Real Time. That system offered users a list of 15 possible annotations or words for an image-one of which was correct for 98 percent of images tested.
"The bottom line is that the system makes it easier to find photographs and is able to improve its performance by itself as time passes," said Ritendra Datta, a graduate student in computer science working with Wang. "The advancement means time savings for consumers as well as improved searching and referral capabilities."
The system was described in a paper, "Tagging Over Time: Real-world Image Annotation by Lightweight Meta-learning," presented at the recent ACM Multimedia 2007 conference in Augsburg, Germany. The authors were Datta; Dhiraj Joshi, a former graduate student in computer science; Jia Li, associate professor, Department of Statistics; and Wang. Penn State has filed a provisional patent application on this invention.
In the researchers' previous system, pixel content of images was analyzed to suggest annotations. In the new software, researchers have added a machine-learning component that enables the computer to learn from the user's interactions with photo-sharing systems.
Images of the World Trade Center, for instance, once would have been tagged with "financial center," "business" or "market success." Users today, however, have different associations or tags for the Twin Towers. The researchers' new system has the capability to learn from such changes and reflect them automatically in refining the old tags and generating future tags.
As the system adapts to such changes, it also enhances tagging performance. With an initial accuracy of 40 percent, the system's precision improves over time and can reach a level of up to 60 percent correct, Datta said.
In a companion paper, "Learning the Consensus on Visual Quality for Next-Generation Image Management," which also was presented at the ACM conference, the researchers described a new system which can automatically select "aesthetically pleasing" images and isolate out those images of low or poor quality. To do this, the system uses visual features such as contrast, depth-of-field indicators, brightness and region composition from publicly rated photographs to learn the statistical models for high- and low-quality images.
"With this system, users can more easily identify the best photographs in their collections," Datta said. "The system also suggests images which should be deleted from the digital cameras to make storage space for new photographs, for example."
The system can also improve image search engines by prioritizing visually pleasing images among the search results, Wang added. The National Science Foundation supported research on both systems.
Penn State
Software Current Events and Software News RSSNew tool enables powerful data analysis
A powerful computing tool that allows scientists to extract features and patterns from enormously large and complex sets of raw data has been developed by scientists at University of California, Davis, and Lawrence Livermore National Laboratory. The tool - a set of problem-solving calculations known as an algorithm - is compact enough to run on computers with as little as two gigabytes of memory.
New visualization techniques yield star formation insights
New computer visualization technology developed by the Harvard Initiative in Innovative Computing has helped astrophysicists understand that gravity plays a larger role than previously thought in deep space's vast, star-forming molecular clouds.
Scientists Identify New Congenital Neutropenia Syndrome and Causative Gene Mutation
A team of scientists has discovered a new syndrome associated with severe congenital neutropenia (SCN), a rare disorder in which children lack sufficient infection-fighting white cells, and identified the genetic cause of the syndrome: mutations in the gene Glucose-6-phosphatase, catalytic subunit 3 (G6PC3).
A breakthrough in diagnosis of enteric lesions
Capsule endoscopy (CE), which is virtually a micro-camera, is a revolutionary diagnostic tool in diagnosing small bowel diseases, and CE can obtain 40-60 thousand images of the GI tract, though the number of the images for the lesions is smaller than 500 in most of the patients.
Application quantifies carbon sequestration of urban trees
U.S. Forest Service scientists at the Center for Urban Forest Research are providing online software that can show users how much carbon dioxide an urban tree in California has sequestered in its lifetime and the past year.
CT colonography offers 1-stop screening for cancer and osteoporosis
New research reveals that computed tomography (CT) colonography, also known as virtual colonoscopy, has the potential to screen for two diseases at once-colorectal cancer and osteoporosis, both of which commonly affect adults over age 50.
New approach eliminates software deadlocks using discrete control theory
Software deadlocks are the Catch-22s of the computer world. These common bugs can freeze the machine when different parts of a program end up in an endless cycle of waiting for one another as they access shared data.
Study identifies double-balloon enteroscopy as cost-effective approach for obscure GI bleeding
A cost-effectiveness analysis conducted by researchers at Stanford University Hospital in Calif., shows that an initial double-balloon enteroscopy (DBE) is a cost-effective approach for patients with obscure gastrointestinal (GI) bleeding.
"Gray's Paradox" Solved: Researchers Discover Secret of Speedy Dolphins
There was something peculiar about dolphins that stumped prolific British zoologist Sir James Gray in 1936.
Quantum computers could excel in modeling chemical reactions
Quantum computers would likely outperform conventional computers in simulating chemical reactions involving more than four atoms, according to scientists at Harvard University, the Massachusetts Institute of Technology, and Haverford College.
More Software Current Events and Software News Articles
 | Java Software Solutions: Foundations of Program Design (6th Edition) by John Lewis, William Loftus As the worldwide best seller for introductory programming using the Java programming language, Java Software Solutions is the premiere model of text that teaches a foundation of programming techniques to foster well-designed object-oriented software. Heralded for its integration of small and large realistic examples, the authors' emphasize building solid problem-solving and design skills. The... |
 | Software Engineering: A Practitioner's Approach by Roger Pressman, Roger Pressman For over 20 years, Software Engineering: A Practitioner's Approach has been the best selling guide to software engineering for students and industry professionals alike. . The sixth edition continues to lead the way in software engineering. A new Part 4 on Web Engineering presents a complete engineering approach for the analysis, design, and testing of Web Applications, increasingly important... |
 | Software Engineering: (Update) (8th Edition) (International Computer Science Series) by Ian Sommerville Sensible choice and organization of topics, made all the more authoritative by the author's credentials as a senior academic in the area Prof. David S. Rosenblum, University College London I find Somerville inviting and readable and with more appropriate content Julian Padget, University of Bath Sommerville takes case studies from radically different areas of SE. This avoids excessive... |
| A+ Guide to Software: Managing, Maintaining and Troubleshooting by Jean Andrews This text is designed to be the most through, step-by-step book available for learning the fundamentals of supporting and troubleshooting computer operating systems. Maps to CompTIAÆs A+ OS... | |
 | Testing Computer Software, 2nd Edition by Cem Kaner, Jack Falk, Hung Q. Nguyen This book will teach you how to test computer software under real-world conditions. The authors have all been test managers and software development managers at well-known Silicon Valley software companies. Successful consumer software companies have learned how to produce high-quality products under tight time and budget constraints. The book explains the testing side of that success. Who... |
 | Software Estimation: Demystifying the Black Art (Best Practices (Microsoft)) by Steve McConnell Often referred to as the "black art" because of its complexity and uncertainty, software estimation is not as hard or mysterious as people think. However, the art of how to create effective cost and schedule estimates has not been very well publicized. While the average software organization can struggle with project costs that run double their original estimates, some of the more sophisticated... |
 | Software Requirements, Second Edition (Pro-Best Practices) by Karl E. Wiegers Learn proven, real-world techniques for managing the software requirements engineering process. This award-winning book has been expanded with new topics, including use cases, up-to-date tools, more field examples, and a new troubleshooting... |
 | Implementing Lean Software Development: From Concept to Cash (Addison-Wesley Signature Series) by Mary Poppendieck, Tom Poppendieck "This remarkable book combines practical advice, ready-to-use techniques, anda deep understanding of why this is the right way to develop software. I haveseen software teams transformed by the ideas in this book."--Mike Cohn, author of Agile Estimating and Planning"As a lean practitioner myself, I have loved and used their first book for years.When this second book came out, I was delighted that... |
 | Software Architecture in Practice (2nd Edition) (SEI Series in Software Engineering) by Len Bass, Paul Clements, Rick Kazman The first edition of this book established itself as the leading book on this topic of growing importance. It was critically acclaimed (recipient of the Software Development Magazine Productivity Award) and widely embraced by customers. The second edition maintains the goals of the first edition: to define and explain software architecture, and to demonstrate, through real-world case studies, its... |
 | Head First Software Development (Brain-Friendly Guides) by Dan Pilone, Russ Miles Even the best developers have seen well-intentioned software projects fail -- often because the customer kept changing requirements, and end users didn't know how to use the software you developed. Instead of surrendering to these common problems, let Head First Software Development guide you through the best practices of software development. Before you know it, those failed projects will be a... |
| © 2009 BrightSurf.com |