-
公开(公告)号：US20180189553A1
公开(公告)日：2018-07-05
申请号：US15837877
申请日：2017-12-11
发明人： Tianchu GUO , Youngsung KIM , Hui ZHANG , Byungin YOO , Chang Kyu CHOI , Jae-Joon HAN , Jingtao XU , Deheng QIAN
CPC分类号： G06K9/00302 , G06F17/10 , G06K9/00255 , G06K9/00268 , G06K9/00281 , G06K9/6211 , G06T7/248 , G06T11/00 , G06T2207/30201
摘要： A processor implemented method of processing a facial expression image, the method includes acquiring an expression feature of each of at least two reference facial expression images; generating a new expression feature based on an interpolation value of the expression feature; and adjusting a target facial expression image based on the new expression feature and creating a new facial expression image.
-
公开(公告)号：US20180114057A1
公开(公告)日：2018-04-26
申请号：US15467396
申请日：2017-03-23
发明人： Youngsung KIM , Byungin YOO , Youngjun KWAK , Chang Kyu CHOI
IPC分类号： G06K9/00
CPC分类号： G06K9/00302 , G06K9/00 , G06K9/00228 , G06K9/00268 , G06K9/00308 , G06K9/624
摘要： A method and apparatus for recognizing a facial expression is provided. The method of recognizing the facial expression includes extracting a feature from an input image, extracting a feature from a reference image, and recognizing a user facial expression based on a difference between the feature of the input image and the feature of the reference image.
-
43.发明申请公开(公告)号：US20170140247A1
公开(公告)日：2017-05-18
申请号：US15347143
申请日：2016-11-09
发明人： Byungin YOO , Youngjun KWAK , Jungbae KIM , Seon Min RHEE , Seungju HAN , Jaejoon HAN , Wonjun HWANG
CPC分类号： G06K9/6256 , G06K9/00067 , G06K9/00087 , G06K9/00221 , G06K9/00268 , G06K9/00288 , G06K9/4623 , G06N3/08 , H04L63/0861
摘要： A method and an apparatus for recognizing an object are disclosed. The apparatus may extract a plurality of features from an input image using a single recognition model and recognize an object in the input image based on the extracted features. The single recognition model may include at least one compression layer configured to compress input information and at least one decompression layer configured to decompress the compressed information to determine the features.
-
公开(公告)号：US20160203354A1
公开(公告)日：2016-07-14
申请号：US14933614
申请日：2015-11-05
发明人： Chang Kyu CHOI , Wonjun KIM , Sungjoo SUH , Byungin YOO , Jaejoon HAN
CPC分类号： G06K9/00026 , G06K9/001 , G06K9/4642 , G06T3/60 , G06T2200/32 , G06T2207/20021 , G06T2207/20221
摘要： A fingerprint recognition method includes determining a code corresponding to a query image based on features of blocks in the query image, obtaining information corresponding to the determined code from a lookup table, and verifying the query image based on the obtained information.
摘要翻译： 指纹识别方法包括基于查询图像中的块的特征来确定与查询图像相对应的代码，从查找表获得与确定的代码相对应的信息，以及基于所获得的信息来验证查询图像。
-
45.发明申请METHOD AND APPARATUS FOR RECOGNIZING OBJECT, AND METHOD AND APPARATUS FOR TRAINING RECOGNIZER 有权用于识别对象的方法和装置，以及用于训练识别器的方法和装置公开(公告)号：US20160148080A1
公开(公告)日：2016-05-26
申请号：US14938365
申请日：2015-11-11
发明人： Byungin YOO , Namjoon KIM , Changkyo LEE , Chang Kyu CHOI , Jaejoon HAN
CPC分类号： G06K9/00302 , G06K9/00281 , G06K9/4628 , G06N3/0454 , G06N3/082 , G06N7/005
摘要： A recognition method includes receiving an input image; and recognizing a plurality of elements associated with the input image using a single recognizer pre-trained to recognize a plurality of elements simultaneously.
摘要翻译： 识别方法包括接收输入图像; 以及使用预先训练以同时识别多个元素的单个识别器来识别与所述输入图像相关联的多个元素。
-
公开(公告)号：US20160125572A1
公开(公告)日：2016-05-05
申请号：US14931170
申请日：2015-11-03
发明人： Byungin YOO , Jun Ho YIM , Jun Mo KIM , Hee Chul JUNG , Chang Kyu CHOI , Jaejoon HAN
CPC分类号： G06K9/2081 , G06K9/00228 , G06K9/6255 , G06K2209/29 , G06N3/0445 , G06N3/0454 , G06N3/084 , G06T5/002 , G06T5/006 , G06T15/205 , G06T2207/20081 , G06T2207/20084
摘要： At least some example embodiments disclose a device and a method for generating a synthetic image and a different-angled image and eliminating noise. The method may include receiving input images, extracting feature values corresponding to the input images using an image learning model, the image learning model permitting an input and an output to be identical and generating a synthetic image based on the feature values corresponding to the input images using the image learning model.
摘要翻译： 至少一些示例性实施例公开了用于产生合成图像和不同角度图像并消除噪声的装置和方法。 该方法可以包括接收输入图像，使用图像学习模型提取与输入图像相对应的特征值，允许输入和输出相同的图像学习模型，并且基于与输入图像相对应的特征值来生成合成图像 使用图像学习模型。
-
-
-
-
-
搜索结果
46 条记录 (耗时 0.021 秒)
