公开(公告)号：US20160104309A1

公开(公告)日：2016-04-14

申请号：US14863772

申请日：2015-09-24

Applicant: KOREA INSTITUTE OF SCIENCE AND TECHNOLOGY

Inventor： Ig Jae KIM ,  Young-ju CHOI ,  Yu-Jin HONG

IPC: G06T11/60 ,  G06T3/40 ,  G06F17/30 ,  G06K9/00 ,  G06T17/20 ,  G06K9/48 ,  G06K9/66

CPC classification number: G06T11/60 ,  G06F17/3028 ,  G06K9/00281 ,  G06K9/481 ,  G06K9/66 ,  G06K2009/00322 ,  G06T17/20

Abstract: Disclosed is an apparatus for generating a facial composite image, which includes: a database in which face image and partial feature image information is stored; a wireframe unit configured to apply a face wireframe to a basic face sketch image, the face wireframe applying an active weight to each intersecting point; a face composing unit configured to form a two-dimensional face model to which the wireframe is applied, by composing images selected from the database; and a model transforming unit configured to transform the two-dimensional face model according to a user input on the basis of the two-dimensional face model to which the wireframe is applied. Accordingly, a facial composite image with improved accuracy may be generated efficiently.

Abstract translation: 公开了一种用于生成面部合成图像的装置，其包括：存储有面部图像和部分特征图像信息的数据库; 线框架单元，其构造成将面线框架应用于基本面部草图图像，所述面线框架对每个交叉点施加有效重量; 通过构成从数据库中选择的图像，构成为形成应用了线框的二维面部模型的面部构成单元; 以及模型变换单元，被配置为基于应用了线框的二维面部模型，根据用户输入来变换二维面部模型。 因此，可以有效地生成精度提高的面部复合图像。

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。