Intensity-based image registration using multiple distributed agents

TAIT, Roger J., SCHAEFER, Gerald and HOPGOOD, Adrian A. (2008). Intensity-based image registration using multiple distributed agents. Knowledge-Based Systems, 21 (3), 256-264.

[img]
Preview
PDF (As published at AI-2007 conference. Subsequently published in KBS journal.) - Submitted Version
Download (565kB) | Preview
    Official URL: http://dx.doi.org/10.1016/j.knosys.2007.11.013
    Link to published version:: 10.1016/j.knosys.2007.11.013

    Abstract

    Image registration is the process of geometrically aligning images taken from different sensors, viewpoints or instances in time. It plays a key role in the detection of defects or anomalies for automated visual inspection. A multiagent distributed blackboard system has been developed for intensity-based image registration. The images are divided into segments and allocated to agents on separate processors, allowing parallel computation of a similarity metric that measures the degree of likeness between reference and sensed images after the application of a transform. The need for a dedicated control module is removed by coordination of agents via the blackboard. Tests show that additional agents increase speed, provided the communication capacity of the blackboard is not saturated. The success of the approach in achieving registration, despite significant misalignment of the original images, is demonstrated in the detection of manufacturing defects on screen-printed plastic bottles and printed circuit boards.

    Item Type: Article
    Research Institute, Centre or Group: Materials and Engineering Research Institute > Centre for Robotics and Automation > Mobile Machine and Vision Laboratory
    Identification Number: 10.1016/j.knosys.2007.11.013
    Depositing User: Adrian Hopgood
    Date Deposited: 30 Aug 2012 16:29
    Last Modified: 17 Sep 2012 15:11
    URI: http://shura.shu.ac.uk/id/eprint/5646

    Actions (login required)

    View Item

    Downloads

    Downloads per month over past year

    View more statistics