公开(公告)号：US20160238748A1

公开(公告)日：2016-08-18

申请号：US14846444

申请日：2015-09-04

Applicant: INDUSTRIAL TECHNOLOGY RESEARCH INSTITUTE

Inventor： Cheng-Chung LEE ,  Yu-Ju CHAO ,  Chia-Yu WU ,  Kuo-Chang LEE

IPC: G02B5/00 ,  H01L51/52 ,  H01L51/50 ,  G02B3/00

CPC classification number: G02B5/003 ,  G02B3/0056 ,  H01L51/5012 ,  H01L51/5056 ,  H01L51/5072 ,  H01L51/5088 ,  H01L51/5092 ,  H01L51/5206 ,  H01L51/5221 ,  H01L51/5253 ,  H01L51/5271 ,  H01L51/5275 ,  H01L51/5284

Abstract: An optical film structure includes a first substrate having a first surface and a second surface, an optical component includes a micro-lens array and disposed on the first surface of the first substrate, a micro-lens array including a plurality of micro-lens units each of which has a round concentrated area with a projected radius R formed on the first surface, a planarization layer disposed on the optical component, a light absorbing layer disposed on the planarization layer and including a plurality of light absorbing units each of which has a width W. Light incident from the second surface of the first substrate and passing through the micro-lens array is focused on the light absorbing units. The micro-lens array and the planarization layer have a difference in refractive index greater than or equal to 0.2; and W is less than or equal to R/2.

Abstract translation: 光学膜结构包括具有第一表面和第二表面的第一基底，光学部件包括微透镜阵列并且设置在第一基底的第一表面上，微透镜阵列包括多个微透镜单元 每个具有形成在第一表面上的具有投影半径R的圆形集中区域，设置在光学部件上的平坦化层，设置在平坦化层上的光吸收层，并且包括多个光吸收单元，每个光吸收单元具有 从第一基板的第二表面入射的并通过微透镜阵列的光聚焦在光吸收单元上。 微透镜阵列和平坦化层具有大于或等于0.2的折射率差; W小于或等于R / 2。

公开(公告)号：US20220147763A1

公开(公告)日：2022-05-12

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: G06K9/62 ,  G06T5/00 ,  G06K9/00 ,  G06T7/11 ,  G06N20/00

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.