-
公开(公告)号：US11443542B2
公开(公告)日：2022-09-13
申请号：US17143170
申请日：2021-01-07
Applicant: Industrial Technology Research Institute
Inventor： Jian-Lung Chen , Chih-Chia Chang , Yu-Hsin Lin , Yu-Ju Chao , Ting-Hsun Cheng
Abstract: A fingerprint recognition method is provided. The method includes obtaining a plurality of fingerprint images by sensing a finger of a user, respectively calculating geometric center points corresponding to the fingerprint images, and calculating positions and offsets of the fingerprint images according to the geometric center points. The method also includes filling signals in the fingerprint images into a part of pixels in a pixel array according to the positions and the offsets of the fingerprint images, and obtaining signals of other pixels in the pixel array by inputting the signals filled in the part of pixels in the pixel array into an artificial intelligence engine. The method further includes generating a candidate fingerprint image and recognizing a user based on the candidate fingerprint image.
-
公开(公告)号：US20210365662A1
公开(公告)日：2021-11-25
申请号：US17143170
申请日：2021-01-07
Applicant: Industrial Technology Research Institute
Inventor： Jian-Lung Chen , Chih-Chia Chang , Yu-Hsin Lin , Yu-Ju Chao , Ting-Hsun Cheng
Abstract: A fingerprint recognition method is provided. The method includes obtaining a plurality of fingerprint images by sensing a finger of a user, respectively calculating geometric center points corresponding to the fingerprint images, and calculating positions and offsets of the fingerprint images according to the geometric center points. The method also includes filling signals in the fingerprint images into a part of pixels in a pixel array according to the positions and the offsets of the fingerprint images, and obtaining signals of other pixels in the pixel array by inputting the signals filled in the part of pixels in the pixel array into an artificial intelligence engine. The method further includes generating a candidate fingerprint image and recognizing a user based on the candidate fingerprint image.
-
公开(公告)号：US10928930B2
公开(公告)日：2021-02-23
申请号：US15997712
申请日：2018-06-05
Inventor： Te-Chih Liu , Chih-Chia Chang , Yu-Hsin Lin , Yi-Chuan Lu
Abstract: A transparent display device and a control method using the same are provided. The transparent display device includes a transparent display, a plurality of identification sensors, a scene sensor, and a controller. The identification sensors are configured to sense a user located at a first side of the transparent display to generate a plurality of identification data. The scene sensor is configured to sense scene information located at a second side. The controller obtains a user distance between the user and the transparent display, selects corresponding identification data generated by at least one of or multiple of the identification sensors according to the user distance, determines a location and a gaze direction of the user and a target object in the scene information according to the selected corresponding identification data, and presents target object information corresponding to the target object in the transparent display.
-
公开(公告)号：US20190050071A1
公开(公告)日：2019-02-14
申请号：US15997712
申请日：2018-06-05
Inventor： Te-Chih Liu , Chih-Chia Chang , Yu-Hsin Lin , Yi-Chuan Lu
Abstract: A transparent display device and a control method using the same are provided. The transparent display device includes a transparent display, a plurality of identification sensors, a scene sensor, and a controller. The identification sensors are configured to sense a user located at a first side of the transparent display to generate a plurality of identification data. The scene sensor is configured to sense scene information located at a second side. The controller obtains a user distance between the user and the transparent display, selects corresponding identification data generated by at least one of or multiple of the identification sensors according to the user distance, determines a location and a gaze direction of the user and a target object in the scene information according to the selected corresponding identification data, and presents target object information corresponding to the target object in the transparent display.
-
25.发明授权公开(公告)号：US12182905B2
公开(公告)日：2024-12-31
申请号：US17939900
申请日：2022-09-07
Applicant: Industrial Technology Research Institute
Inventor： Yi-Wei Luo , Jian-Lung Chen , Ting-Hsun Cheng , Yu-Ju Chao , Yu-Hsin Lin
Abstract: A method, a processing device, and a system for information display are provided, and the system includes a light transmissive display. A first information extraction device extracts spatial position information of a user, and a second information extraction device extracts spatial position information of a target object. The processing device performs the following steps. Display position information of virtual information of the target object on the display is determined according to the spatial position information of the user and the spatial position information of the target object. The display position information includes a first display reference position corresponding to a previous time and a second display reference position corresponding to a current time. An actual display position of the virtual information on the display corresponding to the current time is determined according to a distance between the first display reference position and the second display reference position. The virtual information is displayed on the display according to the actual display position.
-
Patent Agency Ranking
公开(公告)号：US11823438B2
公开(公告)日：2023-11-21
申请号：US17184319
申请日：2021-02-24
Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE
Inventor： Ting-Hsun Cheng , Yu-Ju Chao , Hsin-Cheng Lin , Chih-Chia Chang , Yu-Hsin Lin , Sen-Yih Chou
IPC: G06V10/774 , G06T5/00 , G06T7/11 , G06V20/00
CPC classification number: G06V10/774 , G06T5/002 , G06T7/11 , G06V20/00 , G06T2207/20081
Abstract: A recognition system and an image augmentation and training method thereof are provided. The image augmentation and training method of a recognition system includes the following steps. A plurality of image frames are obtained, wherein each of the image frames includes an object pattern. A plurality of environmental patterns are obtained. The object pattern is separated from each of the image frames. A plurality of image parameters are set. The image frames, based on the object patterns and the environmental patterns, are augmented according to the image parameters to increase the number of the image frames. A recognition model is trained using the image frames.
-
公开(公告)号：US20230169790A1
公开(公告)日：2023-06-01
申请号：US17547221
申请日：2021-12-10
Applicant: Industrial Technology Research Institute
Inventor： Jian-Lung Chen , Yu-Ju Chao , Ting-Hsun Cheng , Yu-Hsin Lin
CPC classification number: G06V40/161 , G06V40/171 , G06T7/75 , G06T5/001
Abstract: An eyeball locating method, an image processing device, and an image processing system are proposed. The method includes the following steps. A human facial image of a user is obtained, wherein the human facial image includes an unobscured human facial region and an obscured human facial region, and the unobscured human facial region includes an eye region. At least one unobscured human facial feature is detected from the unobscured human facial region, and at least one obscured human facial feature is estimated from the obscured human facial region. Next, an eyeball position is located according to the unobscured human facial feature and the obscured human facial feature.
-
公开(公告)号：US20220122274A1
公开(公告)日：2022-04-21
申请号：US17105666
申请日：2020-11-27
Applicant: Industrial Technology Research Institute
Inventor： Te-Chih Liu , Jian-Lung Chen , Yu-Hsin Lin
Abstract: A method, a processing device, and a system for object tracking are proposed. The method includes the following steps. Imaging capturing is performed on an actual scene by using a primary camera and at least one secondary camera to respectively generate a primary image and at least one secondary image. Image stacking is performed on the primary image and the at least one secondary image to generate a stacked image. Position information and depth information of each object in the stacked image are computed. Whether there exist same objects among the objects in the stacked images is determined based on the position information and the depth information of each of the objects.
-
公开(公告)号：US10997732B2
公开(公告)日：2021-05-04
申请号：US16351512
申请日：2019-03-13
Inventor： Jian-Lung Chen , Chih-Chia Chang , Yu-Hsin Lin , Shin-Hong Kuo
Abstract: An information display system and an information display method are provided. The information display system includes a display screen, an image-capture device, and a processing device. The image-capture device captures a picture sequence. The processing device is coupled to the display screen and the image-capture device. The processing device recognizes at least one dynamic object in the picture sequence and generates a recognition frame and a recognition information corresponding to the dynamic object. The processing device tracks a recognition frame of a plurality of first pictures in the picture sequence to obtain a tracking result. The processing device compensates a display coordinate of a recognition information of a second picture in the picture sequence according to the tracking result to obtain a compensated coordinate, and displays the recognition information on the display screen according to the compensated coordinate to reduce a jitter of the recognition information displayed on the display screen. The first pictures are prior to the second picture in terms of time sequence.
-
公开(公告)号：US10977492B2
公开(公告)日：2021-04-13
申请号：US16231943
申请日：2018-12-25
Inventor： Chih-Chia Chang , Yu-Hsin Lin , Jian-Lung Chen , Pi-Hsien Wang
Abstract: A method and an apparatus for preload display of object information are provided. The method includes following steps: capturing an external object information on a side of the transparent display opposite to a user by using the first information capturing device; pre-identifying at least one object in the external object information and tracing the at least one object according to an identification result; capturing information of the user by using the second information capturing device for pre-identifying and tracing a pointing range of the user, and determining whether the traced objects appear within the pointing range; and preload displaying object information of the objects appearing within the pointing range on the transparent display.
-
-
-
-
-
-
-
-
-
Search Results
32
records
(took 0.019 seconds)
