BROWSE
Detail
Conference Paper
Smart Eye: Automated Intelligent Advertisement Selection for Digital Signage
Cited - time in 
Share 
Share
- Authors
- Naveed Ejaz, Jong Weon Lee, Wonil Kim, Cheolsu Lim, Sanghyun Joo, Sung Wook Baik
- Issue Date
- 2011-10
- Citation
- International Conference on Computer Convergence Technology (ICCCT) 2011, pp.1-11
- Language
- English
- Type
- Conference Paper
- Abstract
- Digital signage is a relatively newer form of advertising which provides flexibility of changing advertising contents dynamically. The core challenge of an effective advertisement campaign is to advertise appropriate items to appropriate people at appropriate time. This paper presents a framework for automated selection of appropriate advertisement for digital signage systems using image processing techniques. The appropriate advertisement is selected based on the count, genders and stereotypic knowledge of the people nearby the signage. We exploit combined histogram of gradient (HOG) based approach for both people and gender detection thus saving the computational time of separate feature set computations. We also propose a novel rule based mechanism to collects crowd profile information based on individuals' dressing and shape of the shoulders. The individual modules and the integrated system have been thoroughly tested. The experimental results show the applicability of our framework in real world scenarios.
- KSP Keywords
- Based Approach, Computational time, Image processing(IP), Image processing techniques, Profile information, Real-world, Rule-based, digital signage, feature set, gender detection, histogram of gradient(HOG)