A hybrid approach based on Fuzzy Logic and
neural networks with the combination of the classic Hu &
Zernike moments joined with Geodesic descriptors is used to
keep the maximum amount of information that are given by the
color of the image. These moments are calculated for each
color level and geodesic descriptors are applied directly to
binary images to get information about the general shape of the
object. The extracted features are given as input to the General
Fuzzy Min-Max Neural Network architecture. General Fuzzy
Min-Max Neural Network is The fusion of clustering and
classification resulted in an algorithm that can be used as pure
clustering, pure classification, or hybrid clustering
classification.
Shilpa Bane : PG student, Department of computer engineering, Pune University, Sinhgad college of engineering,
Pune, Maharashtra, India
D. R. Pawar : Department of computer engineering, Pune University , Sinhgad college of engineering,
Pune, Maharashtra, India
Component
Neural Network
Zernike moments
Hu moments
Geodesic descriptors
Object recognition and
Coil-100 Database
Simple moments are not orthogonal, thus it is difficult to
reconstruct the image from them. To overcome this
drawback and to get the distribution of gray levels in the
color image combination of Zernike and Hu moments is
used. Zernike moments are used for less information
redundancy. It allow a better description of objects than
simple moments. These moments are joined together
with Geodesic descriptors to get boundary of the object.
[1] P.K.Simpson, “Fuzzy Min-Max Neural Network-
Part 1: Classification,” IEEE Trans. Neural Network,
vol. 3, no. 5, pp. 776-786, sep.1992. “PDCA12-70
data sheet,” Opto Speed SA, Mezzovico,
Switzerland.
[2] Simpson, P.K.: Fuzzy Min-Max Neural Network –
Part II: Clustering, IEEE Tran. Fuzzy System, Vol.1,
no.1, Feb. (1993) 32-45
[3] A. V. Nandedkar and P. K. Biswas, " A Fuzzy Min-
Max Neural Network Classifier with Compensatory
Neuron Architecture," IEEE Transactions on Neural
Networks,vol. 18, pp. 42-54, 2007.
[4] B. Gabrys and A. Bargiela, “General Fuzzy Min-
Max Neural Network for Clustering and
Classification,”IEEE Transactions on Neural
Networks, vol. 11, no. 3 pp. 769-783, 2000.
[5] Gonzalez R. C and Woods R.E.: Digital Image
Processing, 2nd edition, Pearson Education Pvt.
Ltd.,Delhi (2002).
[6] Anil k. Jain, “Feature Extraction methods for
character recognition-A survey,Appeared in pattern
Recognition”,vol.29,no.4,pp.641-662,1996
[7] SimonX.Liao,Department of Business
computing,The University of Winnipeg
Winnipeg,Manitoba,Canada,”A Study of Moment
Functions and Its Use in Character Recognition”,
IEEE Trans.,Inform. Theory,1997 [8] S. Kumar and C. Singh, “A Study of Zernike
Moments and its use in Devanagri Handwritten
Character Recognition”, In Proc. Intl. Conf. on
Cognition and Recognition, pp. 514-520, 2005.
[9] O.Bencharef, M.Fakir, B.Minaoui Moulay Slimane
University, FST de Beni Mellal, Computer science
department, TIT team, Beni Mellal, Morocco.,
“Color Objects Recognition System based on
Artificial Neural Network with Zernike, Hu &
Geodesic Descriptors” 2012.
[10] Reza D., Mostafa P., et. al. Computer Engineering,
“M-FMCN: Modified Fuzzy Min- Max Classifier
using Compensatory Neurons. Recent Researches in
Artificial Intelligence and Database Management”.
[11] http://www1.cs.columbia.edu/CAVE/software/softlib
/coil-100.php