Intel Corporation

Wooju Ryu

Tae-Hoon Kim

Minje Park

Yangzhou Du

Jinwook Lee

Xiaolu Shen

Myung-Ho Ju

Yeongjae Cheon

Boogeon Yoon

Olivier Duchenne

In the present disclosure, a plurality of frames of input images sequentially received for a predetermined time interval is obtained, and a face detecting operation is performed on a first frame if a full detecting mode is implemented. If a face is detected from a specific region of the first frame during the face detecting operation, a face tracking mode is implemented, a second frame is divided to produce the divided input image portions of the second frame, and the face tracking operation is performed on a surrounding region of the specific region of the divided input image portions of the second frame that corresponds to the specific region in the first frame. If the face is not detected in the face tracking mode, a partial detecting mode is implemented, and the face detecting operation is performed on image portions resized on divided input image portions of a third frame to which a specific region of the third frame corresponding to the specific region of the first frame belongs.

Method and device for detecting face, and non-transitory computer-readable recording medium for executing the method

A system, article, and method of curved object recognition using image matching for image processing.

Method and system of curved object recognition using image matching for image processing

Apparatuses, methods and storage medium associated with 3D face model reconstruction are disclosed herein. In embodiments, an apparatus may include a facial landmark detector, a model fitter and a model tracker. The facial landmark detector may be configured to detect a plurality of landmarks of a face and their locations within each of a plurality of image frames. The model fitter may be configured to generate a 3D model of the face from a 3D model of a neutral face, in view of detected landmarks of the face and their locations within a first one of the plurality of image frames. The model tracker may be configured to maintain the 3D model to track the face in subsequent image frames, successively updating the 3D model in view of detected landmarks of the face and their locations within each of successive ones of the plurality of image frames. In embodiments, the facial landmark detector may include a face detector, an initial facial landmark detector, and one or more facial landmark detection linear regressors. Other embodiments may be described and/or claimed.

3D face model reconstruction apparatus and method

Growing community of inventors

Seoul, South Korea

Wooju Ryu