Machine-learning approach to holographic particle characterization
US-2017241891-A1 · Aug 24, 2017 · US
US10295451B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-10295451-B2 |
| Application number | US-201615738227-A |
| Country | US |
| Kind code | B2 |
| Filing date | Jun 28, 2016 |
| Priority date | Jun 30, 2015 |
| Publication date | May 21, 2019 |
| Grant date | May 21, 2019 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
A device for extracting at least one object characteristic of an object ( 106 ) is presented, the device comprising: a light sensor ( 101 ) for recording a hologram of an object and a processing unit ( 102 ) coupled to the light sensor and configured for extracting at least one object characteristic from the hologram; wherein the processing unit is configured for extracting the at least one object characteristic from a section of the hologram without reconstructing an image representation of the object. Further, a device ( 200 ) for sorting an object ( 106 ), a method for identifying an object and a method for sorting objects is presented.
Opening claim text (preview).
The invention claimed is: 1. A device for extracting at least one characteristic of an object, comprising: a light sensor configured for recording at least a section of a hologram of an object, the light sensor consisting of a single row of light recording elements; and a processing unit coupled to the light sensor and configured for extracting at least one object characteristic from the hologram, wherein the processing unit is configured for extracting the at least one object characteristic from only a section of the hologram without reconstructing an image representation of the object. 2. A device for extracting at least one characteristic of an object, comprising: a light sensor configured for recording at least a section of a hologram of an object, the light sensor consisting of two rows of light recording elements intersecting each other thereby forming a cross-shape; and a processing unit coupled to the light sensor and configured for extracting at least one object characteristic from the hologram, wherein the processing unit is configured for extracting the at least one object characteristic from only a section of the hologram without reconstructing an image representation of the object. 3. A device for extracting at least one characteristic of an object, comprising: a light sensor configured for recording at least a section of a hologram of an object, the light sensor comprising optical in-coupling elements for recording the hologram; and a processing unit coupled to the light sensor and configured for extracting at least one object characteristic from the hologram, wherein the processing unit is configured for extracting the at least one object characteristic from only a section of the hologram without reconstructing an image representation of the object. 4. The device according to claim 1 , 2 or 3 , wherein the at least one object characteristic comprises at least one of an object size, an object type, an object internal structure, or an object homogeneity. 5. The device according to claim 1 , 2 or 3 , wherein the object is a biological cell and the at least one object characteristic comprises at least one of a size of the cell, a size of a nucleus of the cell, a cell type, a cell internal structure, or a cell homogeneity. 6. The device according to claim 1 , 2 or 3 , wherein the object is a red blood cell, a white blood cell, or a circulating tumor cell and the at least one object characteristic comprises at least one of a size of the cell, a size of a nucleus of the cell, a cell type, a cell internal structure, or a cell homogeneity. 7. The device according to claim 1 , 2 or 3 , wherein the processing unit is a photonic integrated circuit. 8. An in-flow object sorting system, comprising: at least one fluidic channel for propagating a fluid sample comprising at least one object; a coherent light source associated with each fluidic channel, positioned to illuminate the object propagating in that fluidic channel; a device, according to claim 1 , 2 or 3 , associated with each fluidic channel, positioned to record a section of a hologram of an illuminated object in that fluidic channel; and a sorter associated with each fluidic channel, coupled to the device and positioned downstream of the device, configured for sorting the illuminated object in the associated fluidic channel. 9. A method for extracting at least one characteristic of an object, the method comprising: providing a fluid sample comprising an object; illuminating the object; recording a hologram of the illuminated object; extracting at least one characteristic of the object from the recorded hologram; and sorting the object based on the extracted at least one characteristic of the object, wherein the extraction of the at least one characteristic of the object is performed using only a section of the recorded hologram, without reconstructing an image representation of the object. 10. The method according to claim 9 , wherein the recording of the hologram comprises recording intensity and phase of light representing the hologram, and wherein the extraction of the at least one characteristic of the object uses the recorded intensity and the recorded phase of light. 11. The method according to claim 9 , wherein the object is a biological cell and the at least one object characteristic comprises at least one of a size of the cell, a size of a nucleus of the cell, a cell type, a cell internal structure, or a cell homogeneity. 12. The device according to claim 1 , 2 or 3 , wherein the processing unit comprises a machine learning component calibrated for extracting the at least one object characteristic. 13. The device according to claim 12 , wherein the machine learning component comprises an artificial neural network or a support vector machine. 14. The device according to claim 1 , 2 or 3 , wherein recording the hologram and extracting the at least one object characteristic comprises: receiving light of the hologram and determining the at least one object characteristic using the received light without converting the light into electrical signals.
Digital holography, i.e. recording holograms with digital recording means (holobject computation G03H1/0866) · CPC title
Optical arrangements · CPC title
using phase shift or interference, e.g. for improving contrast · CPC title
Electro-optic recording means, e.g. CCD, pyroelectric sensors · CPC title
Details {of features involved during the holographic process; Replication of holograms without interference recording} · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.