Please use this identifier to cite or link to this item:
Title: Mobile product recognition services
Authors: Hla Win San
Keywords: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
Issue Date: 2015
Abstract: Nowadays Smartphone has become a popular and essential electronic gadget for all ages. This is because it can not only be used as a communication device but also can be used as a mini computer for surfing net to obtain information via 3G/4G network/wireless broadband and can also be used as a camera. Hence, the software developers gain a great motivation to develop various web based applications (apps) in order for users to obtain information from the service provider via the internet easily and promptly. This project intends to build a mobile product recognition app which allows users to search the movie’s information by image (a movie poster) which captures from their smartphone’s camera. In this project, we will study and analyze the performance of the object recognition techniques and the two feature detectors - Scale Invariant Feature Transform (SIFT) and Speeded Up Robust Features (SURF). We will compare their feature extraction time and detection accuracy on the system. Moreover the movie posters are not always posted or displayed under control environment, therefore, the ‘noise’ is introduced to the captured images and this will reduce the matching accuracy. The Geometric Verification (GV) technique is applied to improve the matching accuracy under uncontrolled condition although it will take longer recognition time. We will further perform the experiments with GV and evaluate the performance between GV and without GV. Lastly, we will try to improve the recognition efficiency in terms of accuracy and robustness and recommend the technique for future work.
Schools: School of Electrical and Electronic Engineering 
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.96 MBAdobe PDFView/Open

Page view(s)

Updated on Jun 22, 2024


Updated on Jun 22, 2024

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.