Face recognition system for set-top box-based intelligent TV

Despite the prevalence of smart TVs, many consumers continue to useconventional TVs with supplementary set-top boxes (STBs) because of the high cost ofsmart TVs. However, because the processing power of a STB is quite low, the smart TVfunctionalities that can be implemented in a STB are very limited. Because of this,negligible research has been conducted regarding face recognition for conventional TVswith supplementary STBs, even though many such studies have been conducted with smartTVs. In terms of camera sensors, previous face recognition systems have usedhigh-resolution cameras, cameras with high magnification zoom lenses, or camera systemswith panning and tilting devices that can be used for face recognition from variouspositions. However, these cameras and devices cannot be used in intelligent TV environments because of limitations related to size and cost, and only small, low cost web-cameras can be used. The resulting face recognition performance is degraded becauseof the limited resolution and quality levels of the images. Therefore, we propose a new facerecognition system for intelligent TVs in order to overcome the limitations associated withlow resource set-top box and low cost web-cameras. We implement the face recognitionsystem using a software algorithm that does not require special devices or cameras. Ourresearch has the following four novelties: first, the candidate regions in a viewer’s face aredetected in an image captured by a camera connected to the STB via low processingbackground subtraction and face color filtering; second, the detected candidate regions offace are transmitted to a server that has high processing power in order to detect face regions accurately; third, in-plane rotations of the face regions are compensated based onsimilarities between the left and right half sub-regions of the face regions; fourth, variousposes of the viewer’s face region are identified using five templates obtained during theinitial user registration stage and multi-level local binary pattern matching. Experimentalresults indicate that the recall; precision; and genuine acceptance rate were about 95.7%;96.2%; and 90.2%, respectively.