Spot detection using an adaptive pyramid algorithm: application to apple’s maturity state

Eric Laemmer; Aline Deruyver; Malgorzata Sowinska

doi:10.1117/12.516728

1 August 2003 Spot detection using an adaptive pyramid algorithm: application to apple's maturity state

Eric Laemmer, Aline Deruyver, Malgorzata Sowinska

Proceedings Volume 4948, 25th International Congress on High-Speed Photography and Photonics; (2003) https://doi.org/10.1117/12.516728
Event: 25th international Congress on High-Speed photography and Photonics, 2002, Beaune, France

Abstract

In this article, an image processing method to detect automatically maturity spots on apples in order to assess their maturity state, is presented. Two different techniques of segmentation are studied. The first one is mono dimensional and looks for the maxima in a sequence of pixels. The other one is a morphological technique called the watershed algorithm. The advantages and the drawbacks of the two techniques are compared. These both approaches are particularly adapted to spot detection but they are sensitive to noise and often provide an over-segmentation. To overcome this difficulty we propose a multi-scale analysis based on adjacency graph pyramid. This method has the advantage of providing a unique segmentation, which does not depend on the order of the regions scanning. The merging will be driven by criteria of a model describing spot characteristics. Experimental results have been obtained on a set of 1200 images of apples, showing the interest of the method.

Citation Download Citation

Eric Laemmer, Aline Deruyver, and Malgorzata Sowinska "Spot detection using an adaptive pyramid algorithm: application to apple's maturity state", Proc. SPIE 4948, 25th International Congress on High-Speed Photography and Photonics, (1 August 2003); https://doi.org/10.1117/12.516728

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