公开(公告)号：US20220207920A1

公开(公告)日：2022-06-30

申请号：US17565453

申请日：2021-12-30

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Junghyun CHO ,  Ig Jae KIM ,  Hochul HWANG

IPC: G06V40/20 ,  G06V10/82 ,  G06V10/84

Abstract: Embodiments relate to a human behavior recognition system using hierarchical class learning considering safety, the human behavior recognition system including a behavior class definer configured to form a plurality of behavior classes by sub-setting a plurality of images each including a subject according to pre-designated behaviors and assign a behavior label to the plurality of images, a safety class definer configured to calculate a safety index for the plurality of images, form a plurality of safety classes by sub-setting the plurality of images based on the safety index, and additionally assign a safety label to the plurality of images, and a trainer configured to train a human recognition model by using the plurality of images defined as hierarchical classes by assigning the behavior label and the safety label as training images.

公开(公告)号：US20210241463A1

公开(公告)日：2021-08-05

申请号：US17102537

申请日：2020-11-24

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Junghyun CHO ,  Ig Jae KIM ,  Hyunwoo CHO ,  Haesol PARK

IPC: G06T7/168 ,  G06T7/32

Abstract: Embodiments relate to a method for supporting X-ray image reading including receiving information associated with a reading target positioned in a reading space where X-rays pass through or are reflected off, acquiring a non X-RAY image of an item object based on the information associated with the reading target, and generating a fake X-RAY image of the item object by applying the non X-RAY image of the item object to the image transform model, and a system for performing the same.

公开(公告)号：US20200328897A1

公开(公告)日：2020-10-15

申请号：US16845362

申请日：2020-04-10

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Ig Jae KIM ,  Gi Pyo NAM ,  Junghyun CHO ,  Heeseung CHOI

IPC: H04L9/32 ,  G06F21/32 ,  G06K9/00 ,  H04M1/725 ,  G06F3/0488 ,  G06T7/73

Abstract: Exemplary embodiments relate to a method for unlocking a mobile device using authentication based on ear recognition including obtaining an image of a target showing at least part of the target's body in a lock state, extracting a set of ear features of the target from the image of the target, when the image of the target includes at least part of the target's ear, and determining if the extracted set of ear features of the target satisfies a preset condition, and a mobile device performing the same.

公开(公告)号：US20160148041A1

公开(公告)日：2016-05-26

申请号：US14941812

申请日：2015-11-16

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Ig Jae KIM ,  Hee Seung CHOI ,  Junghyun CHO

IPC: G06K9/00

CPC classification number: G06K9/00228 ,  G06K9/00208 ,  G06K9/00268 ,  G06K9/00302

Abstract: A method for face recognition through facial expression normalization includes: fitting an input two-dimensional face image into a three-dimensional face model by using a three-dimensional face database; normalizing the three-dimensional face model into a neutral-expression three-dimensional face model by using a neutral-expression parameter learned from the three-dimensional face database; converting the neutral-expression three-dimensional face model into a neutral-expression two-dimensional face image; and recognizing the neutral-expression two-dimensional face image from a two-dimensional face database. Accordingly, face recognition may be performed with high reliability without a loss of information.

Abstract translation: 通过面部表情归一化进行面部识别的方法包括：通过使用三维面部数据库将输入的二维面部图像拟合成三维面部模型; 通过使用从三维面部数据库学习的中性表达参数将三维面部模型归一化为中性表达三维面部模型; 将中性表达三维面部模型转换为中性表达二维脸部图像; 并从二维面部数据库识别中性表达二维脸部图像。 因此，可以以高可靠性执行面部识别，而不会丢失信息。

公开(公告)号：US20150286857A1

公开(公告)日：2015-10-08

申请号：US14310036

申请日：2014-06-20

Applicant: Korea Institute of Science and Technology

Inventor： Ig Jae KIM ,  Hee Seung CHOI ,  Jaewon KIM ,  Junghyun CHO ,  Young-ju CHOI

IPC: G06K9/00 ,  G06F17/30 ,  G06K9/62

CPC classification number: G06F17/30247 ,  G06K9/00288 ,  G06K9/6255

Abstract: Provided is an image recognition apparatus that identifies a person through a face of the person recognized from a photographed image, an image recognition method thereof and a face image generation method thereof.The method for recognizing a face image includes generating candidate images including at least one morphable image which is generated using an object image, extracting first features from the generated candidate images, extracting second feature from a reference image, and generating at least one score corresponding to each of the at least one morphable image by comparing the first features with the second feature, and performing matching to calculate a final score from the generated at least one score.

Abstract translation: 提供一种图像识别装置，其通过从拍摄图像识别的人的脸部识别人，其图像识别方法和面部图像生成方法。 用于识别面部图像的方法包括生成包括使用对象图像生成的至少一个变形图像的候选图像，从所生成的候选图像中提取第一特征，从参考图像中提取第二特征，以及生成至少一个与 通过将所述第一特征与所述第二特征进行比较，并且执行匹配以从所生成的至少一个得分计算最终得分，所述至少一个变形图像中的每一个。