|
|
July2015 Issue Vol.5 No.7
A Novel Iris Image Retrieval with BoundaryBased Feature Using Manhattan Distance
Classifier
https://archive.org/download//v5no701/vol5no701.pdf
Dr.S.Prasath
Assistant Professor
Department of Computer Science, Erode Arts & Science College (Autonomous), Erode, Tamil Nadu, India
A.Selvakumar
Assistant Professor, Department of Commerce with Computer Application,Sree Saraswathi Thyagaraja College(Autonomous), Pollachi
Abstract:
Image processing enters into various sectors but still it is struggling in recognition issues. Iris recognition developed into a very significant research
area concentrate on how to extract and recognize iris images. Iris recognition is an extensively used biometric application for security and identification security iris is being used for recognition of humans. A mixture of method has been proposed for iris recognition and each technique has advantages and shortcoming. The
complexities in process will affects performance of existing system makes inadequate. In this paper presents iris recognition feature vector to calculate the threshold
value separately and stored in feature database. The feature is generated and matching is done by Manhattan distance classifier is used to measures a distance
between two images. The experimental result shows that proposed method provides better recognition rate when compared with the existing methods such as Local Binary
Pattern, Local Ternary Pattern.
Keywords: LBP, LTP, Iris, Manhattan Distance.
