Academic Journals Database
Disseminating quality controlled scientific knowledge

Invariant Recognition of Rectangular Biscuits with Fuzzy Moment Descriptors, Flawed Pieces Detection

ADD TO MY LIST
 
Author(s): Pulivarthi Srinivasa Rao, Sheli Sinha Chaudhuri,& Romesh Laishram

Journal: International Journal of Image Processing
ISSN 1985-2304

Volume: 4;
Issue: 3;
Start page: 232;
Date: 2010;
VIEW PDF   PDF DOWNLOAD PDF   Download PDF Original page

Keywords: Fuzzy moment descriptors | Euclidean distance | Edge detection | Flawed biscuits detection.

ABSTRACT
In this paper a new approach for invariant recognition of broken rectangularbiscuits is proposed using fuzzy membership-distance products, called fuzzymoment descriptors. The existing methods for recognition of flawed rectangularbiscuits are mostly based on Hough transform. However these methods areprone to error due to noise and/or variation in illumination. Fuzzy momentdescriptors are less sensitive to noise thus making it an effective approach andinvariant to the above stray external disturbances. Further, the normalization andsorting of the moment vectors make it a size and rotation invariant recognitionprocess .In earlier studies fuzzy moment descriptors has successfully beenapplied in image matching problem. In this paper the algorithm is applied inrecognition of flawed and non-flawed rectangular biscuits. In general theproposed algorithm has potential applications in industrial quality control.

Tango Jona
Tangokurs Rapperswil-Jona

     Affiliate Program