# US 2019/0318467 A1 · Automated analysis of petrographic thin section images using advanced machine learning techniques

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2019/0318467 A1
- Document ID: US20190318467A1
- Status: Published application
- Kind: A1
- Application number: 15/955,072
- Filed: 2018-04-17
- Published: 2019-10-17
- Earliest claimed: 2018-04-17
- Assignees: Saudi Arabian Oil Company
- Applicants: Saudi Arabian Oil Company
- Inventors: Fatai A. Anifowose; Mokhles Mustapha Mezghani
- Web page: https://patentgrep.com/patent/US20190318467A1

## CPC

- G02B 21/365: {Control or image processing arrangements for digital or video microscopes (G02B21/361, G02B21/362 take precedence)}
- G06F 18/23: Clustering techniques
- G06T 7/0002: {Inspection of images, e.g. flaw detection}
- G06T 7/0004: {Industrial image inspection}
- G06T 7/11: Region-based segmentation
- G06T 7/174: involving the use of two or more images
- G06T 7/62: of area, perimeter, diameter or volume
- G06T 7/90: Determination of colour characteristics
- G06V 10/145: Illumination specially adapted for pattern recognition, e.g. using gratings
- G06V 10/56: relating to colour
- G06V 10/762: using clustering, e.g. of similar faces in social networks
- G01N 33/241: {for hydrocarbon content}
- G02B 21/0092: {Polarisation microscopes}
- G06T 2207/10024: Color image
- G06T 2207/10056: Microscopic image
- G06T 2207/10152: Varying illumination
- G06T 2207/20081: Training; Learning
- G06T 2207/20152: Watershed segmentation
- G06T 2207/20221: Image fusion; Image merging
- G06T 2207/30181: Earth observation
- G06T 2207/30242: Counting objects in image
- G02B: OPTICAL ELEMENTS, SYSTEMS OR APPARATUS
- G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N)
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q)

## Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for automated analysis of petrographic thin section images. In one aspect, a method includes determining a first image of a petrographic thin section of a rock sample, and determining a feature vector for each pixel of the first image. Multiple different regions of the petrographic thin section are determined by clustering the pixels of the first image based on the feature vectors, wherein one of the regions corresponds to grains in the petrographic thin section. The method further includes determining a second image of the petrographic thin section, including combining images of the petrographic thin section acquired with plane-polarized light and cross-polarized light. Multiple grains are segmented from the second image of the petrographic thin section based on the multiple different regions from the first image, and characteristics of the segmented grains are determined.

## Claims

### Claim 1

A method for automated analysis of petrographic thin section images, the method comprising:
determining a first image of a petrographic thin section of a rock sample;
determining a feature vector for each pixel of the first image, wherein the feature vector of each respective pixel is determined based at least on color characteristics of the respective pixel;
determining multiple different regions of the petrographic thin section by clustering the pixels of the first image based on the feature vectors of the pixels of the first image, wherein one of the regions corresponds to grains in the petrographic thin section; and
determining a second image of the petrographic thin section, comprising:
combining images of the petrographic thin section acquired with plane-polarized light and cross-polarized light;
segmenting multiple grains from the second image of the petrographic thin section based on the multiple different regions from the first image; and
determining characteristics of the segmented grains.

### Claim 2 (depends on 1)

The method of claim 1, wherein the multiple different regions of the petrographic thin section correspond to at least one of grains, pores, clays, or iron oxides.

### Claim 3 (depends on 2)

The method of claim 2, further comprising determining relative proportions of the multiple different regions of the petrographic thin section.

### Claim 4 (depends on 1)

The method of claim 1, wherein the characteristics of the segmented grains include, for each of the multiple grains, at least one of area, perimeter, long axis diameter, short axis diameter, or roundness.

### Claim 5 (depends on 1)

The method of claim 1, wherein clustering the pixels of the first image comprises applying a k-means clustering algorithm to the pixels of the first image.

### Claim 6 (depends on 1)

The method of claim 1, wherein the multiple grains are segmented using a watershed segmentation algorithm.

### Claim 7 (depends on 1)

The method of claim 1, wherein the first image is an image of the petrographic thin section acquired with plane-polarized light.

### Claim 8 (depends on 1)

The method of claim 1, wherein each image acquired with cross-polarized light is acquired when the petrographic thin section is rotated to a different angle relative to a reference angle, and determining a second image of the petrographic thin section further comprises registering the multiple acquired images to a reference image.

### Claim 9 (depends on 1)

The method of claim 1, wherein the determined multiple different regions of the thin section and the characteristics of the segmented grains are used to evaluate a quality of a reservoir.

### Claim 10

A system, comprising:
a data processing apparatus; and
a non-transitory computer readable storage medium in data communication with the data processing apparatus storing instructions executable by the data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising:
determining a first image of a petrographic thin section of a rock sample;
determining a feature vector for each pixel of the first image, wherein the feature vector of each respective pixel is determined based at least on color characteristics of the respective pixel;
determining multiple different regions of the petrographic thin section by clustering the pixels of the first image based on the feature vectors of the pixels of the first image, wherein one of the regions corresponds to grains in the petrographic thin section; and
determining a second image of the petrographic thin section, comprising:
combining images of the petrographic thin section acquired with plane-polarized light and cross-polarized light;
segmenting multiple grains from the second image of the petrographic thin section based on the multiple different regions from the first image; and
determining characteristics of the segmented grains

### Claim 11 (depends on 10)

The system of claim 10, wherein the multiple different regions of the petrographic thin section correspond to at least one of grains, pores, clays, or iron oxides.

### Claim 12 (depends on 11)

The system of claim 11, further comprising determining relative proportions of the multiple different regions of the petrographic thin section.

### Claim 13 (depends on 10)

The system of claim 10, wherein the characteristics of the segmented grains include, for each of the multiple grains, at least one of area, perimeter, long axis diameter, short axis diameter, or roundness.

### Claim 14 (depends on 10)

The system of claim 10, wherein clustering the pixels of the first image comprises applying a k-means clustering algorithm to the pixels of the first image.

### Claim 15 (depends on 10)

The system of claim 10, wherein the multiple grains are segmented using a watershed segmentation algorithm.

### Claim 16 (depends on 10)

The system of claim 10, wherein the determined multiple different regions of the thin section and the characteristics of the segmented grains are used to evaluate a quality of a reservoir.

### Claim 17

A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and that upon such execution causes the data processing apparatus to perform operations comprising:
determining a first image of a petrographic thin section of a rock sample;
determining a feature vector for each pixel of the first image, wherein the feature vector of each respective pixel is determined based at least on color characteristics of the respective pixel;
determining multiple different regions of the petrographic thin section by clustering the pixels of the first image based on the feature vectors of the pixels of the first image, wherein one of the regions corresponds to grains in the petrographic thin section; and
determining a second image of the petrographic thin section, comprising:
combining images of the petrographic thin section acquired with plane-polarized light and cross-polarized light;
segmenting multiple grains from the second image of the petrographic thin section based on the multiple different regions from the first image; and
determining characteristics of the segmented grains.

### Claim 18 (depends on 17)

The medium of claim 17, wherein the multiple different regions of the petrographic thin section correspond to at least one of grains, pores, clays, or iron oxides.

### Claim 19 (depends on 18)

The medium of claim 18, further comprising determining relative proportions of the multiple different regions of the petrographic thin section.

### Claim 20 (depends on 17)

The medium of claim 17, wherein the determined multiple different regions of the thin section and the characteristics of the segmented grains are used to evaluate a quality of a reservoir.
