Wavelet transformation and vertical stacking based image classification applying machine learning

Abstract

The paper aims to classify the people who are not so famous and have a controversial background such as the politicians, the criminals/most wanted people all around India, the social reformers who are bringing the changes necessary for the nation and the sports athletes who are making the nation proud around the globe. This is done to spread awareness among the inhabitants of the country as they will come to know about these unknown people and what they did in the past, and can also be used for investigation to keep a record of the past criminals. Image classification falls under supervised machine learning technique and uses various classification algorithms to identify a particular image label. The aim of the paper is to identify the person and provide information that they did before or achieved something to be so famous to be included in this paper. This is achieved by implementing three major Machine Learning algorithms namely: Logistic Regression, Random Forest and SVM (Support Vector Machine), among which SVM classifier along with wavelet transformation, and vertical stacking of cropped raw pixel image and the cropped wavelet transformed image to achieve maximum precision and accuracy of 94.61%.