Authors: Hamdi A. Mahmoud; Hagar Mohamed Reda El Hadad
Addresses: Faculty of Computers and Information, BeniSuef University, Cairo, Egypt ' Faculty of Computers and Information, BeniSuef University, Cairo, Egypt
Abstract: Cattle muzzle classification can be considered as a biometric identifier to maintain the livestock and guarantee the safety of cattle products. This paper presents a muzzle-based classification system using multiclass support vector machines (MSVMs). The proposed MSVMs system consists of three phases; namely preprocessing, feature extraction and classifications. Preprocessing techniques, histogram equalisation and mathematical morphology filtering have been used to increase image contrast and removing noise respectively. The proposed system uses box-counting algorithm for detecting feature of each muzzle image. For a strong classification system and achieving more accurate classification result, MSVMs has been used. The experimental evaluation prove the advancement of the presented system as it achieve 96% classification accuracy in case of increase number of classified group to ten groups compared to 90% classification accuracy achieved by traditional classification system.
Keywords: muzzle classification; image processing; support vector machines; multiclass SVM; box-counting; histogram equalisation; cattle muzzles; biometrics; feature extraction; preprocessing; morphology filtering; image contrast; noise removal; muzzle images; feature matching; cattle traceability; food safety.
International Journal of Image Mining, 2015 Vol.1 No.1, pp.126 - 140
Received: 21 Nov 2014
Accepted: 24 Jan 2015
Published online: 23 Jun 2015 *