-
公开(公告)号：US12086712B2
公开(公告)日：2024-09-10
申请号：US17512463
申请日：2021-10-27
Applicant: Korea Electronics Technology Institute
Inventor： Choong Sang Cho , Young Han Lee
CPC classification number: G06N3/08 , G06F18/2163 , G06F18/217 , G06N3/045 , G06T7/11 , G06V10/751 , G06T2207/20081 , G06T2207/20084
Abstract: There are provided a method and a system for image segmentation utilizing a GAN architecture. A method for training an image segmentation network according to an embodiment includes: inputting an image to a first network which is trained to output a region segmentation result regarding an input image, and generating a region segmentation result; and inputting the region segmentation result generated at the generation step and a ground truth (GT) to a second network, and acquiring a discrimination result, the second network being trained to discriminate inputted region segmentation results as a result generated by the first network and a GT, respectively; and training the first network and the second network by using the discrimination result. Accordingly, region segmentation performance of a semantic segmentation network regarding various images can be enhanced, and a very small image region can be exactly segmented.
-
公开(公告)号：US10978049B2
公开(公告)日：2021-04-13
申请号：US16256563
申请日：2019-01-24
Applicant: Korea Electronics Technology Institute
Inventor： Young Han Lee , Jong Yeol Yang , Choong Sang Cho , Hye Dong Jung
Abstract: An audio segmentation method based on an attention mechanism is provided. The audio segmentation method according to an embodiment obtains a mapping relationship between an “inputted text” and an “audio spectrum feature vector for generating an audio signal”, the audio spectrum feature vector being automatically synthesized by using the inputted text, and segments an inputted audio signal by using the mapping relationship. Accordingly, high quality can be guaranteed and the effort, time, and cost can be noticeably reduced through audio segmentation utilizing the attention mechanism.
-
公开(公告)号：US10923106B2
公开(公告)日：2021-02-16
申请号：US16256835
申请日：2019-01-24
Applicant: Korea Electronics Technology Institute
Inventor： Jong Yeol Yang , Young Han Lee , Choong Sang Cho , Hye Dong Jung
IPC: G10L13/00 , G10L13/10 , H04N21/233 , G06K9/00
Abstract: An audio synthesis method adapted to video characteristics is provided. The audio synthesis method according to an embodiment includes: extracting characteristics x from a video in a time-series way; extracting characteristics p of phonemes from a text; and generating an audio spectrum characteristic St used to generate an audio to be synthesized with a video at a time t, based on correlations between an audio spectrum characteristic St-1, which is used to generate an audio to be synthesized with a video at a time t−1, and the characteristics x. Accordingly, an audio can be synthesized according to video characteristics, and speech according to a video can be easily added.
-
4.发明申请公开(公告)号：US20170124720A1
公开(公告)日：2017-05-04
申请号：US15342890
申请日：2016-11-03
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor： Choong Sang Cho , Hwa Seon Shin , Young Han Lee , Joo Hyung Kang
CPC classification number: G06T7/11 , G06T2207/10024 , G06T2207/10028 , G06T2207/10088 , G06T2207/30016
Abstract: Provided herein is a topological derivatives (TDs)-based image segmentation method and system using heterogeneous image features data. The image segmentation method according to an embodiment of the present disclosure involves calculating TDs having each of the heterogeneous image features data as an input value, and segmenting an image into a plurality of regions using the calculated TDs. Accordingly, performance may be improved, and robustness against noise may be further improved.
-
Patent Agency Ranking
公开(公告)号：US11605167B2
公开(公告)日：2023-03-14
申请号：US17126299
申请日：2020-12-18
Applicant: Korea Electronics Technology Institute
Inventor： Choong Sang Cho , Charles Hyok Song , Young Han Lee
IPC: G06T7/11 , H04N19/167 , H04N19/176
Abstract: An image region segmentation method and system suing self-spatial adaptive normalization is provided. The image region segmentation system includes: an encoder configured to encode an image for segmenting a region by using a plurality of encoding blocks; and a decoder configured to decode the image encoded by the encoder and to generate a region-segmented image by using a plurality of decoding blocks, wherein each of the encoding blocks processes an inputted image into a convolution layer, performs spatial adaptive normalization, and then reduces the image and delivers the image to the next encoding block. Accordingly, spatial characteristics of the image are considered in an encoding process and a decoding process, so that region segmentation can be exactly performed with respect to various images.
-
公开(公告)号：US10819301B2
公开(公告)日：2020-10-27
申请号：US16163860
申请日：2018-10-18
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor： Choong Sang Cho , Young Han Lee
Abstract: The present disclosure relates to a method and system for controlling loudness of an audio based on signal analysis and deep learning. The method includes analyzing an audio characteristic in a frame level based on signal analysis, analyzing the audio characteristic in the frame level based on learning, and controlling loudness of the audio in the frame level, by combining the analysis results. Accordingly, reliability of audio characteristic analysis can be enhanced and audio loudness can be optimally controlled.
-
公开(公告)号：US10726289B2
公开(公告)日：2020-07-28
申请号：US16043338
申请日：2018-07-24
Applicant: Korea Electronics Technology Institute
Inventor： Bo Eun Kim , Choong Sang Cho , Hye Dong Jung , Young Han Lee
Abstract: A method and a system for automatic image caption generation are provided. The automatic image caption generation method according to an embodiment of the present disclosure includes: extracting a distinctive attribute from example captions of a learning image; training a first neural network for predicting a distinctive attribute from an image, by using a pair of the extracted distinctive attribute and the learning image; inferring a distinctive attribute by inputting the learning image to the trained first neural network; and training a second neural network for generating a caption of an image by using a pair of the inferred distinctive attribute and the learning image. Accordingly, a caption well indicating a feature of a given image is automatically generated, such that an image can be more exactly explained and a difference from other images can be clearly distinguished.
-
8.发明授权公开(公告)号：US10176583B2
公开(公告)日：2019-01-08
申请号：US15342890
申请日：2016-11-03
Applicant: KOREA ELECTRONICS TECHNOLOGY INSTITUTE
Inventor： Choong Sang Cho , Hwa Seon Shin , Young Han Lee , Joo Hyung Kang
Abstract: Provided herein is a topological derivatives (TDs)-based image segmentation method and system using heterogeneous image features data. The image segmentation method according to an embodiment of the present disclosure involves calculating TDs having each of the heterogeneous image features data as an input value, and segmenting an image into a plurality of regions using the calculated TDs. Accordingly, performance may be improved, and robustness against noise may be further improved.
-
公开(公告)号：US20170076462A1
公开(公告)日：2017-03-16
申请号：US15259935
申请日：2016-09-08
Applicant: Korea Electronics Technology Institute
Inventor： Choong Sang Cho , Hwa Seon Shin , Young Han Lee , Joo Hyung Kang
CPC classification number: G06K9/52 , G06K9/342 , G06K9/46 , G06K9/6215 , G06T7/11 , G06T7/12 , G06T7/149 , G06T2207/20021 , G06T2207/20116 , G06T2207/30048
Abstract: Provided herein is a robust region segmentation method and a system using the same, the method including receiving setting of an image in an input image; calculating representative values for each of an internal portion and an external portion of the region; calculating a cost by substituting the representative values and a pixel value of the image in a cost function, and updating the region based on the calculated cost, wherein the cost function includes a term in which a difference between the updated pixel value and an original pixel value is reflected, thereby enabling an accurate region segmentation even in ambiguous images that are complicated and where division of regions is unclear.
Abstract translation: 本文提供了鲁棒区域分割方法和使用该方法的系统，该方法包括接收输入图像中的图像的设置; 计算该区域的内部部分和外部部分中的每一个的代表值; 通过在成本函数中代替图像的代表值和像素值来计算成本，并且基于计算出的成本来更新该区域，其中，成本函数包括其中更新的像素值和原始像素之间的差值 反映了这一点，从而即使在复杂的模糊图像中也能进行精确的区域分割，并且区域划分不清楚。
-
-
-
-
-
-
-
-
Search Results
9
records
(took 0.014 seconds)
