In the paper A Method for Mobile Download Conversion Rate Measurement based on Device Fingerprinting, we present a method which allows to determine if a mobile application install originates from a specific campaign. This requires that mobile devices are uniquely identified before referral to the mobile application store and after a successful install of the application. However, the mobile sandbox environment makes it impossible to exchange device identifiers between a mobile web browser and other mobile applications on the same device. Therefore, we present a method that is based on device fingerprinting to uniquely identify smartphones across a native mobile browser and a native mobile application in order to measure the number of application installs from a specific marketing campaign. A more detailed description of this work, which has been conducted in the project AUToMAte, can be found in the research section of this website.
In the paper Range Face Segmentation: Face Detection and Segmentation for Authentication in Mobile Device Range Images, we propose a novel approach to robust single upright face detection and segmentation from different perspectives based on range information (pixel values corresponding to the camera-object distance). We use range template matching for finding the face’s coarse position and gradient vector flow (GVF) snakes for precisely segmenting faces. Results indicate that range template matching might be a good approach to finding a single face; in our tests we achieved an error free detection rate and average recognition rates above 98%/96% for color/range images. This paper has been written in cooperation with the Josef Ressel Center for User-friendly Secure Mobile Environments (u’Smile) at the Campus Hagenberg of the University of Applied Sciences Upper Austria.
MoMM is a leading international conference for researchers and industry practitioners to share their new ideas, original research results and practical development experiences from all mobile computing and multimedia related areas. The conference proceedings will be published by ACM with the ISBN 978-1-4503-2106-8 and will be available during the conference.