Biologically inspired object selection technique based on attractor selection

Satoru Irie; Yusuke Ogura; Jun Tanida

doi:10.1117/12.680392

8 September 2006 Biologically inspired object selection technique based on attractor selection

Satoru Irie, Yusuke Ogura, Jun Tanida

Proceedings Volume 6310, Photonic Devices and Algorithms for Computing VIII; 63100L (2006) https://doi.org/10.1117/12.680392
Event: SPIE Optics + Photonics, 2006, San Diego, California, United States

Abstract

Information techniques featuring adaptability, autonomy, and diversity found in the behavior of livings are promising. The purpose of this study is to explore object selection method adaptable to unexpected change of the environment. An attractor selection is used as an algorithm for flexible adjustment to various change of the environment. An attractor is a convergence point in a state space and corresponds to a stable point of a given system. The attractor selection chooses an attractor according to the suitability for a given environmental condition. The proposed object selection algorithm finds a solution from several images captured with different focus settings. To obtain these images a compound-eye imaging system is assumed to be used. In the object selection, an object is regarded as an attractor. The location and the features of the object are expressed as variables in the state space. In this study, hue in the Hue-Saturation-Value color model is used as a parameter of an environmental condition. In the simulation, two objects of different hue were located at different distances. One of the objects might be selected by the proposed algorithm. The correct operations of the algorithm are confirmed. The results show that the attentive object is correctly switched according to the change of selecting condition. The adaptability and the robustness of the method has been confirmed.

Citation Download Citation

Satoru Irie, Yusuke Ogura, and Jun Tanida "Biologically inspired object selection technique based on attractor selection", Proc. SPIE 6310, Photonic Devices and Algorithms for Computing VIII, 63100L (8 September 2006); https://doi.org/10.1117/12.680392

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available