公开(公告)号：US20150366328A1

公开(公告)日：2015-12-24

申请号：US14764698

申请日：2013-11-28

Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.

Inventor： Hajime TAMURA ,  Hiroaki YOSHIO ,  Katsuji AOKI ,  Kaori MORI ,  Sonoko HIRASAWA ,  Shin YAMADA ,  Takayuki MATSUKAWA

IPC: A45D44/00

CPC classification number: A45D44/005 ,  A45D44/00 ,  A45D2044/007 ,  A61B5/0077 ,  A61B5/441 ,  G06T11/00

Abstract: Provided is a cosmetic assist device that can extract a cosmetic technique for making a user's face look like a target face image. The device includes an image capturing unit for capturing a face image of a user, an input unit for inputting a target face image, a synthesized face image generating unit for generating a plurality of synthesized face images obtained by applying mutually different cosmetic techniques on the face image of the user, a similarity determination unit for determining a degree of similarity between each synthesized face image and the target face image, and a cosmetic technique extraction unit for extracting one of the cosmetic techniques that was used to obtain the synthesized face image determined to have a highest degree of similarity by the similarity determination unit.

Abstract translation: 提供了一种美容辅助装置，其可以提取用于使用户的脸部看起来像目标脸部图像的美容技术。 该装置包括用于捕获用户的脸部图像的图像捕获单元，用于输入目标脸部图像的输入单元，合成面部图像生成单元，用于生成通过在脸部上应用相互不同的美容技术而获得的多个合成面部图像 用户的图像，用于确定每个合成面部图像与目标面部图像之间的相似度的相似度确定单元，以及用于提取用于获得被确定为合成面部图像的合成面部图像的化妆技术之一的美容技术提取单元 具有相似度确定单元的最高相似度。

公开(公告)号：US20240203221A1

公开(公告)日：2024-06-20

申请号：US18286393

申请日：2022-03-25

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Shin YAMADA ,  Kazuhiko IWAI ,  Takeshi WATANABE

IPC: G08B13/196 ,  G06V20/52

CPC classification number: G08B13/19652 ,  G06V20/52 ,  G08B13/19613

Abstract: Provided is a monitoring system configured such that, even when there is a deviation of a shooting region of a camera, if the deviation is within an acceptable level, an accurate vehicle detection using a recognition model can be performed without readjusting parameters or re-training the model. Based on an image of a no-entry zone and a platform zone, a processor performs a first operation for detecting a person in the no-entry zone and a second operation for detecting a vehicle in the no-entry zone; and based on detection results, determines whether an alert needs to be issued. When there is a deviation of the shooting region of a camera, the processor performs a conversion operation for converting an image of a current shooting region to an image that would be captured by the camera with an original shooting region and uses the converted image for the two detection operations.

公开(公告)号：US20160148381A1

公开(公告)日：2016-05-26

申请号：US14898847

申请日：2014-06-30

Applicant: PANASONIC INTELLECTUAL PROPERTY MANAGEMENT CO., LTD.

Inventor： Katsuji AOKI ,  Hajime TAMURA ,  Takayuki MATSUKAWA ,  Shin YAMADA ,  Hiroaki YOSHIO

IPC: G06T7/00 ,  G06K9/00 ,  G06K9/62

CPC classification number: G06K9/00255 ,  G06K9/00208 ,  G06K9/00248 ,  G06K9/00268 ,  G06K9/00288 ,  G06K9/00785 ,  G06K9/6202 ,  G06K9/6267 ,  G06T7/33 ,  G06T2207/10016 ,  G06T2207/30201

Abstract: A category selection portion selects a face orientation based on an error between the positions of feature points (the eyes and the mouth) on the faces of each face orientation and the positions of feature points, corresponding to the feature points on the faces of each category, on the face of a collation face image. A collation portion collates the registered face images of the face orientation selected by the category selection portion and the collation face image with each other, and the face orientations are determined so that face orientation ranges where the error with respect to each individual face orientation is within a predetermined value are in contact with each other or overlap each other. The collation face image and the registered face images can be more accurately collated with each other.

Abstract translation: 类别选择部分基于每个面部朝向的面部上的特征点（眼睛和嘴部）的位置与特征点的位置之间的误差来选择面部取向，其与每个类别的面部上的特征点相对应 ，在面对对照的脸部图像。 对照部分将由类别选择部分选择的面部方向和对照面部图像的登记面部图像相互对照，并且确定面部取向，使得相对于每个单独面部方向的误差在其内的面部取向范围 预定值彼此接触或彼此重叠。 对照面部图像和登记的脸部图像可以更准确地对照。

公开(公告)号：US20230064953A1

公开(公告)日：2023-03-02

申请号：US17894813

申请日：2022-08-24

Applicant: Panasonic Intellectual Property Management Co., Ltd.

Inventor： Kazuhiko IWAI ,  Shin YAMADA

IPC: H04N7/18 ,  H04N5/232 ,  G06V20/52 ,  G08B13/196

Abstract: A surveillance device of the present disclosure includes an image analysis server that generates an alarm when detecting an alarm generation target that has entered an intrusion detection area, based on a camera image captured by a camera. The image analysis server acquires the camera image (basic image) to set a fixed object area (basic area) corresponding to a fixed object included in the basic image, acquires a camera image (live image) to extract a fixed object area (reference area) corresponding to a fixed object included in the live image, calculates a deviation amount of an angle of view based on a result of a comparison in standard position between the basic area and the reference area, and generates a surveillance screen including an adjustment screen for guidance on an operation for cancelling the deviation amount of the angle of view to display the surveillance screen.