Asian Stamps Identification and Classification System

TL;DR

This paper presents a new stamp recognition system that classifies stamps by country and year using color histograms and texture features like SIFT and HOG, achieving reasonable accuracy.

Contribution

It introduces a novel combination of color and texture features for stamp classification and recognition, improving accuracy over previous methods.

Findings

Effective classification using combined color and texture features

Color histogram, SIFT, and HOG features improve recognition accuracy

Initial results show promising performance in stamp recognition

Abstract

In this paper, we address the problem of stamp recognition. The goal is to classify a given stamp to a certain country and also identify the year it is published. We propose a new approach for stamp recognition based on describing a given stamp image using color information and texture information. For color information we use color histogram for the entire image and for texture we use two features. SIFT which is based on local feature descriptors and HOG which is a dens texture descriptor. As a result on total we have three different types of features. Our initial evaluation shows that give these information we are able to classify the images with a reasonable accuracy.