# US 10,504,225 B2 · Image processing device, image processing method, and non-transitory computer-readable recording medium having stored therein image processing program

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

- Number: US 10,504,225 B2
- Document ID: US10504225B2
- Status: Granted
- Kind: B2
- Application number: 15/720,125
- Filed: 2017-09-29
- Published: 2018-01-25
- Granted: 2019-12-10
- Earliest claimed: 2015-03-31
- Assignees: Tohoku University; Hirosaki University
- Applicants: Tohoku University; Hirosaki University
- Inventors: Noriyasu Homma; Masao Sakai; Kei Ichiji; Naoki Shibusawa; Xiaoyong Zhang; Makoto Abe; Norihiro Sugita; Makoto Yoshizawa; Yoshihiro Takai
- Web page: https://patentgrep.com/patent/US10504225B2

## CPC

- G06T 7/0012: {Biomedical image inspection}
- A61B 6/00: Apparatus or devices for radiation diagnosis; Apparatus or devices for radiation diagnosis combined with radiation therapy equipment (instruments measuring radiation intensity for application in the field of nuclear medicine, e.g. in vivo counting, G01T1/161)
- A61B 6/5264: {due to motion}
- G06T 5/40: using histogram techniques
- G06T 5/94: based on local image properties, e.g. for local contrast enhancement
- G06T 7/11: Region-based segmentation
- G06T 7/143: involving probabilistic approaches, e.g. Markov random field [MRF] modelling
- G06T 7/194: involving foreground-background segmentation
- G06T 2207/10116: X-ray image
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D)

## Abstract

An image processing device includes: an acquisition unit that acquires a probability distribution of luminance of a pixel in a plurality of perspective images including the luminance of the pixel which is superposition of luminance components resulting from respective objects, based on an occurrence frequency of a perspective image in which the luminance of the pixel has respective values of a plurality of values; a distribution estimation unit that estimates a mixture distribution indicating the acquired probability distribution; a component estimation unit that estimates a component corresponding to a smallest expectation value distribution of which an expectation value is the smallest among a plurality of partial distributions that form the estimated mixture distribution, and forming at least a portion of the luminance of the pixel; a removal unit that removes the estimated component from the luminance of the pixel included in the perspective image.

## Claims

### Claim 1

An image processing device comprising processor circuitry, the processor circuitry being configured to:
acquire a probability distribution of luminance of a pixel in a plurality of perspective images including the luminance of the pixel which is superposition of luminance components resulting from respective objects, based on an occurrence frequency of a perspective image in which the luminance of the pixel has respective values of a plurality of values;
estimate a mixture distribution indicating the acquired probability distribution;
estimate a component corresponding to a smallest expectation value distribution of which an expectation value is the smallest among a plurality of partial distributions that form the estimated mixture distribution, and forming at least a portion of the luminance of the pixel;
remove the estimated component from the luminance of the pixel included in the perspective image.

### Claim 2 (depends on 1)

The image processing device according to claim 1, wherein
processor circuitry estimates the luminance of the pixel as the component when a probability that the luminance of the pixel results from the smallest expectation value distribution is higher than a probability that the luminance of the pixel results from a partial distribution different from the smallest expectation value distribution among the plurality of partial distributions that form the estimated mixture distribution.

### Claim 3 (depends on 1)

The image processing device according to claim 1, wherein
the processor circuitry estimates a value based on the smallest expectation value distribution as the component when a probability that the luminance of the pixel results from the smallest expectation value distribution is lower than a probability that the luminance of the pixel results from a partial distribution different from the smallest expectation value distribution among the plurality of partial distributions that form the estimated mixture distribution.

### Claim 4 (depends on 1)

The image processing device according to claim 1, wherein
the processor circuitry executes removal of the component in each of the plurality of perspective images, and
the processor circuitry repeatedly executes acquisition of the probability distribution, estimation of the mixture distribution, estimation of the component, and removal of the component with respect to the plurality of perspective images in which the component is removed.

### Claim 5 (depends on 1)

The image processing device according to claim 1, wherein
the processor circuitry estimates a moving distance and a moving direction of a subject in each of the plurality of perspective images in relation to a reference perspective image selected among the plurality of perspective images and corrects the perspective image so that the subject is moved by the estimated moving distance in a direction opposite to the estimated moving direction with respect to each of the plurality of perspective images.

### Claim 6

An image processing method comprising:
acquiring a probability distribution of luminance of a pixel in a plurality of perspective images including the luminance of the pixel which is superposition of luminance components resulting from respective objects, based on an occurrence frequency of a perspective image in which the luminance of the pixel has respective values of a plurality of values;
estimating a mixture distribution indicating the acquired probability distribution;
estimating a component corresponding to a smallest expectation value distribution of which an expectation value is the smallest among a plurality of partial distributions that form the estimated mixture distribution, and forming at least a portion of the luminance of the pixel;
removing the estimated component from the luminance of the pixel included in the perspective image.

### Claim 7

A non-transitory computer-readable recording medium having stored therein an image processing program for causing a computer to execute a process comprising:
acquiring a probability distribution of luminance of a pixel in a plurality of perspective images including the luminance of the pixel which is superposition of luminance components resulting from respective objects, based on an occurrence frequency of a perspective image in which the luminance of the pixel has respective values of a plurality of values;
estimating a mixture distribution indicating the acquired probability distribution;
estimating a component corresponding to a smallest expectation value distribution of which an expectation value is the smallest among a plurality of partial distributions that form the estimated mixture distribution, and forming at least a portion of the luminance of the pixel;
removing the estimated component from the luminance of the pixel included in the perspective image.