公开(公告)号：US11074674B2

公开(公告)日：2021-07-27

申请号：US16480258

申请日：2018-01-29

申请人： Purdue Research Foundation

发明人： Fang Huang ,  Sheng Liu

IPC分类号： G06T5/00 ,  G06T5/10 ,  G06T5/20

摘要： A system for reducing noise in a camera image is disclosed. The system includes one or more processors, and a camera operatively coupled to the processor, the processors are configured to reduce noise of camera images, the processors are configured to receive input image data from the camera representing pixel data from a plurality of pixels, segment the input image data to a plurality of segments and for each segment establish an initial segment image, pre-correct pixel data by modifying the pixel data to account for voltage offset and gain of each pixel based on a predetermined map of gain and offset, and obtain an estimate of an output image by minimizing a cost function and output and stitch the estimated image to other estimated and outputted image segments, and output a noise reduced image including the stitched estimated images.

公开(公告)号：US12002185B2

公开(公告)日：2024-06-04

申请号：US17309027

申请日：2019-06-10

申请人： Purdue Research Foundation

发明人： Peiyi Zhang ,  Fang Huang ,  Sheng Liu

IPC分类号： G06T3/40 ,  G01J3/28 ,  G01J3/443 ,  G01N21/64 ,  G06N3/08 ,  G06T3/4046

CPC分类号： G06T3/4046 ,  G01J3/2823 ,  G01J3/443 ,  G01N21/6428 ,  G01N21/6458 ,  G06N3/08

摘要： A fluorescent single molecule emitter simultaneously transmits its identity, location, and cellular context through its emission patterns. A deep neural network (DNN) performs multiplexed single-molecule analysis to enable retrieving such information with high accuracy. The DNN can extract three-dimensional molecule location, orientation, and wavefront distortion with precision approaching the theoretical limit of information content of the image which will allow multiplexed measurements through the emission patterns of a single molecule.

公开(公告)号：US20240062334A1

公开(公告)日：2024-02-22

申请号：US18493899

申请日：2023-10-25

申请人： Purdue Research Foundation

发明人： Peiyi Zhang ,  Fang Huang ,  Sheng Liu

IPC分类号： G06T3/40 ,  G01J3/28 ,  G01J3/443 ,  G01N21/64 ,  G06N3/08

CPC分类号： G06T3/4046 ,  G01J3/2823 ,  G01J3/443 ,  G01N21/6428 ,  G01N21/6458 ,  G06N3/08

摘要： A fluorescent single molecule emitter simultaneously transmits its identity, location, and cellular context through its emission patterns. A deep neural network (DNN) performs multiplexed single-molecule analysis to enable retrieving such information with high accuracy. The DNN can extract three-dimensional molecule location, orientation, and wavefront distortion with precision approaching the theoretical limit of information content of the image which will allow multiplexed measurements through the emission patterns of a single molecule.

公开(公告)号：US20190385280A1

公开(公告)日：2019-12-19

申请号：US16480258

申请日：2018-01-29

申请人： Purdue Research Foundation

发明人： Fang Huang ,  Sheng Liu

IPC分类号： G06T5/00 ,  G06T5/10 ,  G06T5/20

摘要： A system for reducing noise in a camera image is disclosed. The system includes one or more processors, and a camera operatively coupled to the processor, the processors are configured to reduce noise of camera images, the processors are configured to receive input image data from the camera representing pixel data from a plurality of pixels, segment the input image data to a plurality of segments and for each segment establish an initial segment image, pre-correct pixel data by modifying the pixel data to account for voltage offset and gain of each pixel based on a predetermined map of gain and offset, and obtain an estimate of an output image by minimizing a cost function and output and stitch the estimated image to other estimated and outputted image segments, and output a noise reduced image including the stitched estimated images.