Development of a automatic mobile framework for landmark image captioning, annotation and augmentation
I was funded by the Tripod Project for three months to complete work on a mobile framework for image recognision, classification. The goal of which was to produce a research demonstrator system which would showcase the potential of image captioning and localization search services developed by Mark Hughes at Dublin City University and within the Tripod Project. The mobile framework is a research prototype designed to showcase the potential of the Landmark Image Recognition and Classification engine in performing in-situ classification and image management tasks.
The mobile framework I developed, was designed to support the user in the automatic annotation (captioning and tagging) of a digital photo of a landmark. It was designed with a tourist-style scenario in mind. Within our scenario, this manual process of captioning and uploading media becomes automatic and is performed in-situ as the user takes the photos at the landmark of interest. Once captioned we provide them the ability to automatically upload the captured media to an online social media application.
The mobile framework for landmark image recognition and classification has three major components in its architecture. The landmark image recognition and classification engine resides on the server along with a series of web services designed to expose their functionality to a mobile application running on a compatible mobile device (in this case an iPhone.)
The efficacy of the mobile framework in end-to-end image classification and annotation was evaluated and is the subject of a publication presented at SAMT 2010.