Classification of gold bangles based on tamura texture features

Mortgaging gold for money in the bank is common in India. Banks rely on assessor´s skills to test the purity of gold, its weight and provide a description of the items. The absence of skilled assessor makes the loan granting process tedious and time consuming when the quantum of gold items is mortgaged. This paper provides an image processing solution to automatically provide a description of the mortgage of gold bangle that would become a handy note for borrowers as well. This work classifies the gold bangles by circularity and texture features. The proposed work is oriented towards classifying the bangle into different classes as plain bangle, Stone bangle and kada bangle using SVM classifier. Its accuracy is obtained as 86.66% and KNN classifier is used for comparison.