Device for hyperspectral holographic microscopy by sensor fusion
AssigneeCarbon Bee
InventorGérald Germain
Life of this patent
Estimating the term…
Abstract
The invention concerns a device for the holographic and hyperspectral measurement and analysis (2) of a sample (3), comprising; —an acquisition means (2) for acquiring a diffracted image (11) of an image of the sample (3); and interference patterns (12) of a reference light signal (R) and the light signal (O) having passed through the sample (3) to be measured and analysed; and —a means for illuminating the sample (3) focused on the sample (3); and —a means for reconstructing and analysing (1) the hyperspectral holographic image comprising a deep convolutional neural network generating an image for analysis and detection of particularities in the sample.
Claims19
Device for holographic and hyperspectral measuring and analyzing of a sample, wherein said device comprises:
- an acquisition device of an image containing spectral and amplitude information of the light signal illuminating said sample;
- and holographic interference figures of a reference light beam and of a light beam having illuminated said sample containing the amplitude and phase information of the light signal illuminating said sample;
- and
- an illumination device of said sample;
- and
- a device for reconstructing the hyperspectral holographic image and analyzing the amplitude, phase and spectrum properties of the light illuminating said sample integrating a deep and convolutional neural network architectured for calculating a probability of presence of the particularity sought in said sample from the hyperspectral holographic image, and generating an image for each sought particularity whose value of each pixel at the x and y coordinates corresponds to the probability presence of said particularity at the same x and y coordinates of said sample.
Method for holographic and hyperspectral measuring and analyzing of a sample, said method comprising:
- an illumination device illuminates said sample;
- and
- an acquisition device acquires an image containing the spectral and amplitude information of the light signal illuminating said sample;
- and holographic interference figures of a reference light beam and of a light beam having illuminated said sample containing the amplitude and phase information of the light signal illuminating said sample;
- and
- a device for reconstructing the hyperspectral holographic image and analyzing the amplitude, phase and spectrum properties of the light illuminating said sample integrates a deep and convolutional neural network architectured to calculate a probability of presence of the particularity sought in said sample from the hyperspectral holographic image, and generate an image for each sought particularity whose value of each pixel at the x and y coordinates corresponds to the probability of presence of said particularity at the same x and y coordinates of said sample.
A device for measuring a sample, said device comprising:
- a capture device for acquiring a compressed image of the sample containing spectral and amplitude information of the light signal illuminating said sample and holographic interference figures of a reference light beam and of a light beam having illuminated said sample containing the amplitude and phase information of the light signal illuminating said sample;
- and
- an illumination device of said sample;
- and
- a device for reconstructing a microscopy image of the sample integrating a deep and convolutional neural network architectured to calculate a light intensity in said sample from the compressed image and the holographic interference figure of the beam of reference with the beam illuminating the sample, and generating an image whose value of each pixel at the coordinates u and v corresponds to the light intensity at the x and y coordinates of the plane of said sample;
- said deep and convolutional neural network being architectured so as to merge the information of the sensors of the diffracted image and of the image of the holographic interference figure.
Dependencies are inferred from the claim text.