Principal component analysis on Indian currency recognition

Indian Currency Classification Using Speeded Up Robust Features

“…For segmentation, they used canny edge detector and for classification they used NN pattern recognition tool, which gives 95.6% accuracy. Vishnu R, Bini Omman [8] proposed a method in which firstly histogram equalization is used to normalize the images. Then they extract five features (Shape, Center, RBI seal, Micro Letter, Latent image) from images of currency by using appropriate Region of Interest (ROI) mask.…”

“…From this block, they extract the features and then apply neural network for classification. Vishnu R, Bini Omman [5] used PCA (Principal Component Analysis) method and for data Validation WEKA Classifier is used. In this method to generate training model, extracted features in training set are loaded.…”

A Review on Indian Currency Recognition

“…Vishnu R, Bini Omman [2] proposed a method where first by using histogram equalization images are template image normalized. Then they extract features (Shape, Micro Letter, Center, Latent image, RBI seal) by placing a rectangular box of specific dimensions from images of currency which discovers the Region of Interest (ROI).…”

“…Vishnu R, Bini Omman [3] use PCA (Principal Component Analysis) method [2] and for data Validation WEKA Classifier is used. In this method to generate training model features extracted in training set is loaded.…”

“…For currencies of each denomination there is a specific color and size followed by Reserve bank of India. [1,2] It is a very simple for human to identify the denomination of currency note because our brain is extremely skillful in determining new matters and discovering them later without much trouble. But this currency recognition task turns to very challenging in computer vision, in case of when currencies becomes damaged, old, and faded due to wear and tear.…”