Samsung Electronics Co., Ltd.

Seokcheol Kee

Jiali Zhao

Dejun Wang

Haibing Ren

Wonjun Hwang

Haitao Wang

Maolin Chen

Whoiyul Kim

An apparatus and method for detecting a head image of an input image. In the head image detection apparatus, a training DB stores therein a positive head image and a negative head image into which a plurality of images are classified. A sub-window processor extracts a feature population while sliding a sub-window of a predetermined size with respect to the input image. A head candidate region classifier classifies head candidate regions based on the extracted feature population from the sub-window processor by referring to samples stored in the training DB. A head candidate region determiner determines a head candidate region as a head region by checking continuity of contours of the classified head candidate regions.

Apparatus and method for detecting heads in input image

An apparatus for and method of performing a most informative feature extraction (MIFE) method in which a facial image is separated into sub-regions, and each sub-region makes individual contribution for performing facial recognition. Specifically, each sub-region is subjected to a sub-region based adaptive gamma (SadaGamma) correction or sub-region based histogram equalization (SHE) in order to account for different illuminations and expressions. A set of reference images is also divided into sub-regions and subjected to the SadaGamma correction or SHE. A comparison is made between the each corrected sub-region and each corresponding sub-region of the reference images. Based upon the comparisons made individually for the sub-regions of the facial image, one of the stored reference images having the greatest correspondence is chosen. While usable individually, using the MIFE and/or SadaGamma correction or SHE together achieves a lower error ratio in face recognition under different expressions, illuminations and occlusions.

Apparatus for and method of feature extraction for image recognition

An apparatus and method for generating a shape model of an object and an apparatus and method for automatically searching for feature points of an object employing the same. The apparatus for automatically searching for feature points of an object includes: a shape model generation unit which generates a shape model including a mean model of an object, and statistical feature data of each feature point forming a mean shape, by training a plurality of training sets in which a plurality of feature points are labeled for the object; an initial position resetting unit which resets an initial position of each feature point of the mean shape according to a pose of an input image; and a feature point extraction unit which adapts the mean shape whose initial position is reset, to the input image, by using the statistical feature data of each feature point of the mean shape, and extracts feature points of the input image.

Apparatus and method for generating shape model of object and apparatus and method for automatically searching for feature points of object employing the same

There is provided a method of estimating disparity for 3D object recognition. The method includes obtaining a plurality of images having different resolutions for the stereo image, estimating a disparity map for a lowest-resolution level image, estimating a coarse disparity map for an upper resolution level image by using the disparity, obtaining a fine disparity map for the upper resolution level image by using the coarse disparity, and outputting the fine disparity map as a final disparity map for the stereo image if the upper resolution level image has a resolution of a highest level.

Method of estimating disparity for 3D object recognition

A face detection method and apparatus using a level-set method. The method includes: laying a first initial shape model over a face image; evolving shape curves of the first initial shape model using the level-set method; detecting first through M-th neighboring boundary points that neighbor first through M-th initial boundary points of the first initial shape model, and that neighbor the evolved shape curves, M being a positive integer larger than 1; laying a modified shape model rendered using the detected first through M-th neighboring boundary points over the face image; detecting a rotation angle of the modified shape model; determining whether the detected rotation angle of the modified shape model is within a predetermined angle range; and selecting one of a second initial shape model, which is rotated to the left, or a third initial shape model, which is rotated to the right, according to the detected rotation angle, and laying the selected initial shape model over the face image, and returning to the detecting of the first through M-th neighboring boundary points, when the detected rotation angle of the modified shape model is outside the predetermined angle range.

Face detection method and apparatus using level-set method

A image verification method, medium, and apparatus using a local binary pattern (LBP) discriminant technique. The verification method includes generating a kernel fisher discriminant analysis (KFDA) basis vector by using the LBP feature of an input image, obtaining a Chi square inner product by using the LBP feature of an image registered in advance and a kernel LBP feature and projecting to a KFDA basis vector, obtaining a Chi square inner product by using the LBP feature of a query image and a kernel LBP feature and projecting to a KFDA basis vector, and obtaining the similarity degree of the target image and the query image that are obtained as Chi square inner product results, and projected to the KFDA basis vector. According to the method, medium, and apparatus, the KFDA based LBP shows superior performance over conventional LBP, KFDA, and biometric experimentation environment (BEE) baseline algorithms.

Image verification method, medium, and apparatus using a kernel based discriminant analysis with a local binary pattern (LBP)

A global localization apparatus, medium, and method, with the global localization method including selecting one from a plurality of samples and shifting the selected sample according to a movement of a robot, generating a new sample within a predetermined range of the shifted sample, determining either the shifted sample or the new sample as a next sample at a next time step according to a predetermined condition for the shifted sample and the next sample, repeating for all the samples, and estimating a next position of the robot according to positions of the next samples when the number of next samples is equal to or larger than the maximum number of samples.

Growing community of inventors

Seoul, South Korea

Seokcheol Kee