公开(公告)号：US11238624B2

公开(公告)日：2022-02-01

申请号：US16808345

申请日：2020-03-03

Applicant: Industrial Technology Research Institute

Inventor： Duan-Li Liao ,  Chia-Chang Li ,  Wen-Hung Ting ,  Po-Lung Chen

IPC: G06T11/00 ,  G06T11/60

Abstract: Provided are an image transform method and an image transform network. The method is for the image transform network including an image generator, a transform discriminator and a focus discriminator, and includes: generating a transformed image according to an un-transformed image and focus information by the image generator; computing a transform discrimination value according to the transformed image by the transform discriminator; computing a value of a first generator loss function and updating the image generator by the image generator; generating a focus discrimination value according to the un-transformed image, the transformed image, and the focus information by the focus discriminator; and computing a value of a second generator loss function according to the focus discrimination value and updating the image generator according to the value of the second generator loss function by the image generator.

公开(公告)号：US20210118195A1

公开(公告)日：2021-04-22

申请号：US16808345

申请日：2020-03-03

Applicant: Industrial Technology Research Institute

Inventor： Duan-Li Liao ,  Chia-Chang Li ,  Wen-Hung Ting ,  Po-Lung Chen

IPC: G06T11/00 ,  G06T11/60

Abstract: Provided are an image transform method and an image transform network. The method is for the image transform network including an image generator, a transform discriminator and a focus discriminator, and includes: generating a transformed image according to an un-transformed image and focus information by the image generator; computing a transform discrimination value according to the transformed image by the transform discriminator; computing a value of a first generator loss function and updating the image generator by the image generator; generating a focus discrimination value according to the un-transformed image, the transformed image, and the focus information by the focus discriminator; and computing a value of a second generator loss function according to the focus discrimination value and updating the image generator according to the value of the second generator loss function by the image generator.

公开(公告)号：US20190303645A1

公开(公告)日：2019-10-03

申请号：US15960559

申请日：2018-04-24

Applicant: Industrial Technology Research Institute

Inventor： Wen-Hung Ting ,  Hian-Kun Tenn ,  Duan-Li Liao ,  Chia-Chang Li ,  Po-Lung Chen

IPC: G06K9/00

Abstract: An electronic device, an iris recognition method and a non-volatile computer-readable medium are provided. A processor in the electronic device obtains a first and second iris images, and calculates a plurality of first and second feature mark boxes that are non-uniformly arranged according to the first and second iris images. The processor uses the first feature mark boxes to obtain a first and second image features from the first and second iris images respectively, and compares the first and second image features to obtain a first recognition result. The processor uses the second feature mark boxes to obtain a third and fourth image features from the second and first iris images respectively, and compares the third and fourth image features to obtain a second recognition result. The processor determines a similarity degree of the first and second iris images according to the first and second recognition results.

公开(公告)号：US11549805B2

公开(公告)日：2023-01-10

申请号：US16828902

申请日：2020-03-24

Applicant: Industrial Technology Research Institute

Inventor： Kai-Shiang Gan ,  Po-Lung Chen ,  Chun-Yuan Chen ,  Chien-Chun Kuo

IPC: G01B11/25 ,  G06T17/20

Abstract: A projecting apparatus includes a projecting device, an image-capturing device and a processing device. The projecting device projects a reversible structured light code onto a surface. The image-capturing device captures the reversible structured light code projected onto the surface and obtains image data. The processing device is coupled to the projecting device and the image-capturing device. The processing device receives the image data, generates three-dimensional point cloud information by performing decoding on the image data, and obtains scanning shift information corresponding to the projecting device according to the three-dimensional point cloud information and three-dimensional information corresponding to the surface.

公开(公告)号：US10474893B2

公开(公告)日：2019-11-12

申请号：US15960559

申请日：2018-04-24

Applicant: Industrial Technology Research Institute

Inventor： Wen-Hung Ting ,  Hian-Kun Tenn ,  Duan-Li Liao ,  Chia-Chang Li ,  Po-Lung Chen

IPC: G06K9/00

Abstract: An electronic device, an iris recognition method and a non-volatile computer-readable medium are provided. A processor in the electronic device obtains a first and second iris images, and calculates a plurality of first and second feature mark boxes that are non-uniformly arranged according to the first and second iris images. The processor uses the first feature mark boxes to obtain a first and second image features from the first and second iris images respectively, and compares the first and second image features to obtain a first recognition result. The processor uses the second feature mark boxes to obtain a third and fourth image features from the second and first iris images respectively, and compares the third and fourth image features to obtain a second recognition result. The processor determines a similarity degree of the first and second iris images according to the first and second recognition results.