Mobile apps development for image processing using openCV4Android

Computer vision has been extensively studied as one of the cutting-edge fields of research. As mobile phones have become essentials for almost everyone, computer vision techniques are no longer obscure terminologies on books and journals. Individuals nowadays are able to enjoy the advances in comput...

Full description

Saved in:
Bibliographic Details
Main Author: Wang, Qijia
Other Authors: Chong Yong Kim
Format: Final Year Project
Language:English
Published: 2016
Subjects:
Online Access:http://hdl.handle.net/10356/67477
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
Description
Summary:Computer vision has been extensively studied as one of the cutting-edge fields of research. As mobile phones have become essentials for almost everyone, computer vision techniques are no longer obscure terminologies on books and journals. Individuals nowadays are able to enjoy the advances in computer visions through abundant mobile applications. There are a number of examples including photo editors and real-time translation apps with Augmented Reality (AR). Among them, recognition applications help people better perceive the world by turning mobile phones into artificial eyes. This project aims to develop an Android application for recognizing logos as well as signs by leveraging on OpenCV4Android library. The application emphasizes on the portability with offline processing capability. It fully utilizes the local processors of mobile phones. Users simply need to take a photo of the logo which is new to them, and the application will search through a built-in database for a match. Details including nearby places related to the logo will be provided to the users. The application has been implemented in a Java-C++ hybrid manner to achieve best performance. An effective algorithm has been developed as a by-product. It is the heart of this application and it makes high-accuracy matching possible. With the algorithm, many other mobile or embedded applications can be engineered in the future to meet various needs.