Welcome to the upgraded BRAC University Institutional Repository. We are currently organizing collections after a recent system upgrade. Homepage category counters may temporarily show lower numbers while syncing, but over 27,000 repository items remain safe and accessible. Please use the search bar to find theses, scholarly outputs, and institutional documents.

Vehicle model identification using neural network approaches

Citation

Abstract

Our world is going through a constant phase of growth and advancement where the manufacture of vehicles has increased exponentially. Vehicles of different brands with different features and models are vastly available in all over the world. Along with the fact that vehicles are now a basic need, every individual is now able to afford a vehicle of their choice and status. Consequently, misdemeanors such as theft, accidents, damage done, relating to automobiles has also increased over the years. Identifying a specific model vehicle among these several brands of vehicles can be considered difficult. Our main goal is to find the details of a specific model of a transport from several unknown automobile’s datasets. Our system will help to identify a vehicle and its model using still pictures of any brand of car. We hope that in future we can extend it to a more advanced identifying system which can be used by the government to reduce all forms of transgressions towards vehicles.

Description

Cataloged from PDF version of thesis report.
Includes bibliographical references (page 42-43).
This thesis report is submitted in partial fulfillment of the requirements for the degree of Bachelor of Science in Computer Science and Engineering, 2016.

Publisher Link

Type

Thesis