Advertisement Image Recognition for a Location-Based Reminder System

In this paper, we propose a location-based reminder system on mobile phones using image recognition technology. With this system, mobile phone users can actively capture images from their favorite product or event promotional materials. Upon recognizing the image sent to a computer server, location-based reminders will be downloaded to the phone. The mobile phone will alert the user when he/she is close to the place where the product is being sold or the event is happening. Nearduplicate image recognition is employed to identify the advertisement. Using scale-invariant features followed by Kd-tree image matching and geometric validation, near-duplicates of trained images in the database are recognized. The image recognition provides accurate and efficient retrieval of the corresponding reminders. A mobile client application is developed to capture images, conduct GPS location tracking and to pop up reminders.