Panasonic Intellectual Property Management Co., Ltd.

Panasonic Intellectual Property Corporation of America

ZhiHeng Niu

Sugiri Pranata

Hirofumi Nishimura

Sotaro Tsukizawa

Hiroyuki Kubotani

Yunyun Cao

A measurement-target-selecting device that is capable of estimating a face shape with high precision and at low computational time. In this device, a face texture assessment value calculating part () calculates a face texture assessment value representing a degree of match between an input face image and the texture of a face shape candidate, a facial-expression-change-likelihood-calculating part () calculates a first likelihood between a face shape constituting a reference and a face shape candidate, a correlation assessment part (); calculates a first correlation assessment value representing the strength of a correlation between the face texture assessment value and the first likelihood, and a selection part () selects from among the plurality of face shape candidates as a measurement target a face shape candidate having a first correlation assessment value that is lower than a first threshold.

Measurement-target-selecting device, face-shape-estimating device, method for selecting measurement target, and method for estimating face shape

Device () comprises: a comparison object pixel acquisition unit () which acquires pixel values of a plurality of comparison object pixels which, when each pixel of an image is designated as a pixel of interest, and a ring-shaped region with the pixel of interest being designated as the center thereof being designated a vicinity region, said comparison object pixels are included in the vicinity region; a pixel difference calculation unit () which calculates the difference between the pixel value of the pixel of interest and the pixel values of each comparison object pixel; and a local binary pattern generation unit () which generates a local binary pattern for each pixel. A plurality of vicinity regions are present for each pixel of interest, and the distance of the vicinity regions are established on the basis of the spatial frequency characteristics of a lens with which the image is photographed.

Feature extraction device, feature extraction method, and feature extraction program

A detection device capable of reliably detecting an object to be detected. An intersection region pattern setting unit () sets a configuration pattern of a first intersection region pattern group in sequence for each unit image pair. Each intersection region pattern is defined by set image information which denotes locations and sizes of regions (where n is a natural number greater than 1) within respective unit images (e.g., unit image plane coordinates), as well as whether each region is set within either or both of a first unit image and a second unit image. A detection unit () detects the object to be detected, based on a total feature value relating to each configuration pattern of the first intersection region pattern group, computed by a feature value computation unit (), and a strong identification apparatus configured from a plurality of weak identification apparatuses and stored in an identification apparatus storage unit ().

Detection device and detection method

Provided is a feature extraction device whereby it is possible, while using local binary patterns, to extract image features with which object detection which is robust against disparities in a photographic environment is possible. A feature extraction unit () comprises: a binary pattern generation unit () which generates, for each of all pixels or partial pixels in an image, local binary patterns which denote, by bit values, whether the difference in pixel values between the pixel and the surrounding adjacent pixels is greater than or equal to a threshold value; a weighting generation unit () which determines, for each generated local binary pattern, a weighting according to the pixel value difference; and a histogram generation unit () which applies the determined weightings to the corresponding local binary patterns and generates a histogram which denotes the distribution of the local binary patterns which are generated from the image.

Growing community of inventors

Singapore, Singapore

ZhiHeng Niu