MOBILITY ENGINEERING Produced by SAE Media Group
MOBILITY ENGINEERING
Magazines
Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Magazine cover

Current Issue

Archives

Automatic Abstraction of Information From Digitized Images

A proposed machine vision architecture would enable automatic learning, adaptation, and generalization.

A research effort now underway addresses fundamental mathematical issues involved in a methodology of creating flexible machine vision systems that would be able to modify their behaviors and evolve in particular environments so as to recognize anything that human operators have designated as being "interesting" in those environments. It is intended that a person who is not a programmer could train such a machine vision system by drawing lines around objects in a scene (see figure) or otherwise indicating example objects and that thereafter, the system would adapt and evolve the ability to recognize such objects automatically.

Lines Would Be Drawn by a human user around objects required to be recognized by a housecleaning robot. Thereafter, without further human intervention, the robot would learn to recognize these and other objects.
Prior approaches to machine vision include algorithmic knowledge-based programming, neural-network systems that learn from examples, and combinations of both. Many practical systems are based on algorithms or procedures that make opportunistic use of special features characteristic of the particular objects and scenes required to be recognized. Although these prior approaches and systems may afford acceptable performances in specific applications, there is usually little or no ability to generalize to other, similar applications and there is no ability to generalize to different environments. For example, a machine vision system designed to inspect industrial parts is unlikely to be useful for reading car license plates.

What is sought in this research is a machine vision architecture that supports "point-and-learn" training, works for cluttered scenes, enables adaptation to changes in objects and scenes, and enables adaptation to any scene or environment. In broad terms, it has been proposed, as a basis of this research, that this be a multilevel architecture in which:

  • Machine vision systems would evolve appropriate retinal configurations, evolve connectivities to represent spatial relationships, and abstract information to generate their own higherlevel constructs; and
  • Levels would be integrated by new relational mathematics as summarized below.

The key feature of the architecture is the ability of a machine vision system to abstract its own constructs from data in a multilevel algebraic representation. This feature enables the system to learn objects that may change through time and to generalize and adapt to learn radically new objects and scenes without the need to change the underlying computer program. The computational demands imposed by the requirement to learn and adapt in this way are beyond the capabilities of any current machine vision systems.

In this research, the approach followed in attempting to satisfy the requirement to learn and adapt is based on the mathematics of multilevel hypernetworks, in which network theory is generalized to multilevel, multidimensional space. Hypernetworks naturally give rise to multilevel systems and provide the essential structural architecture for self-adapting machine vision systems. The fundamental architecture proposed is based on hypernetworks that are inherently relational but can integrate objects with geometrical properties. The hypernetwork representation accommodates relational and numerical data, and supports geometrical operations implemented at high levels of abstraction.

Thus far, the research has led to the identification of both neuronal and algorithmic data processing as being appropriate to an automatic machine vision system having the required capabilities, and to the determination that both types of processing can be integrated coherently. A machine vision system based on the proposed architecture would operate initially in bottom-up fashion, processing from pixels to features. Then intermediate and high-level operators would analyze the geometric and topological properties of the emergent features and would play a role in a dynamic bottom- up/top-down process.

This work was done by Masanori Sugisaka of Oita University for the Air Force Research Laboratory. For further information, download the free white paper at www.defensetechbriefs.com  under the Information Sciences category. AFRL-0016

Topics:
Architecture Automation Education and training Identification Information Technology Inspections Mathematical models Parts People and personalities Railway vehicles and equipment Research and development Robotics Simulation and modeling Vehicles
This Brief includes a Technical Support Package (TSP).
Document cover
Automatic Abstraction of Information From Digitized Images

(reference AFRL-0016) is currently available for download from the TSP library.

Don't have an account?

More From SAE Media Group

    Magazine cover
    Defense Tech Briefs Magazine

    This article first appeared in the February, 2007 issue of Defense Tech Briefs Magazine (Vol. 1 No. 1).

    Read more articles from the archives here.

    Overview

    The document is a final report titled "Construct Abstraction for Automatic Information Abstraction from Digital Images," authored by Dr. Masanori Sugisaka and Jeffrey Johnson. It details a research project aimed at advancing automatic machine vision, which is crucial for robotics and automated systems. The project was conducted under contract number FA5209-05-P-0171, sponsored by the US Research Laboratory (AOARD/AFOSR), and took place from December 15, 2004, to May 1, 2006.

    The report highlights the challenges faced in traditional machine vision systems, which are often hand-crafted for specific applications. These systems tend to be brittle, performing poorly outside their designed parameters and lacking adaptability. The research focuses on developing flexible machine vision systems capable of evolving and modifying their behavior based on the environment. This adaptability allows the systems to recognize objects that an operator identifies as "interesting," thereby enhancing their functionality in dynamic settings.

    The report emphasizes the importance of creating machine vision systems that can autonomously learn and adapt, moving beyond the limitations of conventional approaches. The authors discuss various architectural considerations and principles that guide the development of these systems. The goal is to create a more robust and versatile machine vision framework that can be applied across different scenarios, improving the efficiency and effectiveness of automated systems.

    The document also includes details about the performing organization, Oita University in Japan, and the collaborative efforts with other institutions, such as the Advanced Research Institute for Science and Engineering at Waseda University. The report is unclassified and approved for public release, making it accessible for further research and development in the field of image processing and machine vision.

    In summary, this report presents significant advancements in automatic machine vision, addressing the limitations of traditional systems and proposing a new approach that emphasizes flexibility and adaptability. The findings and methodologies outlined in the report contribute to the ongoing evolution of robotics and automated systems, paving the way for more intelligent and responsive technologies in the future.

    Top Stories

    INSIDERWeapons Systems

    Feature Image AUSA 2025: The Army's New Anti-Vehicle Terrain Shaping Munition is Ready for...

    INSIDERUnmanned Systems

    Feature Image Meet Arc: Inversion's New Autonomous Space Vehicle for Logistics and Hypersonic...

    INSIDERAerospace

    Feature Image Mercury Signs Embedded Production Agreement for AeroVironment’s Satellite...

    INSIDERManned Systems

    Feature Image AUSA 2025: Secretary Driscoll Wants Army to Save Time and Money by 3D-Printing...

    INSIDERSoftware

    Feature Image Helsing Unveils New Autonomous Fighter Jet 'CA-1 Europa'

    PodcastsAerospace

    Feature Image Autonomous Targeting Systems for a New Autonomous Ground Vehicle

    Webcasts