Embedded Online Marketing
Marketing and advertsing using facial recognition of participants via mobile apps


em


Effective ways to directly communicate with consumers in mobile environments are explored in this application. In online envir-onments, the ability to tag banner ads to the person, without the need to access personal profiles, allows for targeted marketing to the individual, keeping the message within the target market demographics. In a multi-layered advertising strategy, a retailer can push from a number of advertising messages for the same product, each targeting the specific tribe, gender, or age group.



The technology allows for a single or multiple advertising and marketing service to pull ads for different companies, services and products, based on sensing of personal attributes and allowing products that are distinctly desirable by the tribe, gender and age groups. In a multilayered advertising strategy, a retailer can push from a number of advertising messages for the same product, each targeting the specific tribe, gender, or age group.

The technology allows for a single or multi-ple advertising and marketing service to pull ads for different companies, services and products, based on sensing of personal attributes and allowing products that are distinctly desirable by the tribe, gender and age groups.

The video below, left demonstrates the abilty to detect gender and smile. This technique currently uses an image processing approach by identifying shapes within a image field using Viola and Jones Open CV Haar-like features application [1], [2],[3] and a “feret” database [4] of facial image and support vector machine (LibSVM) [3] to classify the faces to glean attributes such as gender, or other individual characteristics.

Such a system must have an inherent intelligence that is ambient, and ubiquitous – allowing for interpretation of a wide variety of stimuli and that can be easily collected. The systems intelligences must have offer a range of options that can be autonomously responsive and give meaningful responses to the visual and sensor cues.

Building on previous work that explores the feasibility of a user centric delivery of point-of-purchase marketing content using biometric data capture. This system uses facial recogntion to transmit facial images of persons using internet in mobile environment. Through the intelligent analysis of facial data, physical cues, age, gender and other forms of data that can be directly captured in a non-invasive manner. Following analysis, the embedded maketing message can be focused to the individual based on the cues collected.


Further work will use extended image libraries that have focused slections of image that define demographic subsets of indivisual. The goal is to be bale to identify how to determine a viewer gender, age, hairstyle, clothings and style choices.
The ability to detect these persoal attributes, Once identified,marketing content can be target to gender groups, age groups, and tribe.



1. Viola, P., & Jones, M. (2001). Robust real-time object detection. Paper presented at the Second International Workshop on Theories of Visual Modelling Learning, Computing, and Sampling

2. Bradski, G. and Kaehler, A., (2008). Learning OpenCV. OReilly.

3. Burges, C. J.C., (1998) A Tutorial on Support Vector Machines for Pattern Recognition. Data Mining and Knowledge Discovery 2, 121-167

4. http://www.nist.gov/huma nid/colorferet

5. Wiskott, L.; Fellous, J.-M.; Kuiger, N.; von der Malsburg, C. (1997) Face recognition by elastic bunch graph matching, Pattern Analysis and Machine Intelligence, IEEE Transactions on Machine Intelligence, Volume: 19 Issue:7 Pages 775 - 779

6. Bronstein, A. M.; Bronstein, M. M., and Kimmel, R. (2005). "Three-dimensional face recognition". International Journal of Computer Vision (IJCV) 64 (1): 5–30

7. Ekman, P., (1999), "Basic Emotions", in Dalgleish, T; Power, M, Handbook of Cognition and Emotion, Sussex, UK: John Wiley & Sons, http://www.paulekman.com/wp-content/uploads/2009/02/Basic-Emotions.pdf