Intel Corporation

Yeongjae Cheon

Minje Park

Tae-Hoon Kim

Hyungsoo Lee

YongChan Park

Hongmo Je

Yangzhou Du

Taesup Kim

Sumin Lee

Xiaolu Shen

Myung-Ho Ju

Wooju Ryu

Byungseok Roh

Kye-Hyeon Kim

Sanghoon Hong

Olivier Duchenne

Technologies for multi-scale object detection include a computing device including a multi-layer convolution network and a multi-scale region proposal network (RPN). The multi-layer convolution network generates a convolution map based on an input image. The multi-scale RPN includes multiple RPN layers, each with a different receptive field size. Each RPN layer generates region proposals based on the convolution map. The computing device may include a multi-scale object classifier that includes multiple region of interest (ROI) pooling layers and multiple associated fully connected (FC) layers. Each ROI pooling layer has a different output size, and each FC layer may be trained for an object scale based on the output size of the associated ROI pooling layer. Each ROI pooling layer may generate pooled ROIs based on the region proposals and each FC layer may generate object classification vectors based on the pooled ROIs. Other embodiments are described and claimed.

Technologies for improved object detection accuracy with multi-scale representation and training

Techniques are provided for facial recognition using decoy-based matching of facial image features. An example method may include comparing extracted facial features of an input image, provided for recognition, to facial features of each of one or more images in a gallery of known faces, to select a closest gallery image. The method may also include calculating a first distance between the input image and the selected gallery image. The method may further include comparing the facial features of the input image to facial features of each of one or more images in a set of decoy faces, to select a closest decoy image and calculating a second distance between the input image and the selected decoy image. The method may further include recognizing a match between the input image and the selected gallery image based on a comparison of the first distance and the second distance.

Decoy-based matching system for facial recognition

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

The present disclosure relates to detecting the location of a face feature point using an Adaboost learning algorithm. According to some embodiments, a method for detecting a location of a face feature point comprises: (a) a step of classifying a sub-window image into a first recommended feature point candidate image and a first non-recommended feature point candidate image using first feature patterns selected by an Adaboost learning algorithm, and generating first feature point candidate location information on the first recommended feature point candidate image; and (b) a step of re-classifying said sub-window image classified into said first non-recommended feature point candidate image, into a second recommended feature point candidate image and a second non-recommended feature point candidate image using second feature patterns selected by the Adaboost learning algorithm, and generating second feature point candidate location information on the second recommended feature point recommended candidate image.

Method, apparatus and computer readable recording medium for detecting a location of a face feature point using an Adaboost learning algorithm

Computer-readable storage media, computing devices and methods are discussed herein. In embodiments, a computing device may be configured to perform facial recognition based on gradient based feature extractions of images of faces. In embodiments, the computing device may be configured to determine directional matching patterns of the images from the gradient based feature extraction and may utilize these directional matching patterns in performing a facial recognition analysis of the images of faces. Other embodiments may be described and/or claimed.

Face recognition using gradient based feature analysis

Growing community of inventors

Seoul, South Korea

Yeongjae Cheon