Unlock instant, AI-driven research and patent intelligence for your innovation.

Image processing device and image processing method

An image processing device and pixel technology, which can be used in image data processing, image enhancement, image analysis, etc., and can solve problems such as loss of image spatial position information and inability to detect

Active Publication Date: 2016-10-05
OLYMPUS CORP
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the technology of Patent Document 1, the position information in the image space is lost when the feature space is expressed, so there is a problem that even for an abnormal part whose pixel value is different from that of the surrounding pixels in the image space, it cannot be determined due to the imaging state. Detect abnormal parts that have an extended pixel value distribution that does not deviate from the normal mucosa in the feature space due to individual differences

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Image processing device and image processing method
  • Image processing device and image processing method
  • Image processing device and image processing method

Examples

Experimental program
Comparison scheme
Effect test

no. 1 Embodiment approach

[0034] First, the configuration of the image processing device 10 according to the first embodiment will be described. figure 2 It is a schematic block diagram illustrating the main configuration of the image processing device 10 according to the first embodiment. Such as figure 2 As shown, the image processing device 10 of the first embodiment includes a computing unit 20 and a recording unit 30 . The image processing device 10 is incorporated into, for example, the above-mentioned endoscope, receives an intraluminal image captured by the endoscope, processes the intraluminal image, and outputs a detected abnormality detection result.

[0035] The calculation unit 20 can be realized by hardware such as a CPU, and performs various calculation processes for detecting an abnormal part from an intraluminal image. The calculation unit 20 includes an approximate value calculation unit 21 , a validity evaluation unit 22 , a region division unit 23 , a target region resetting uni...

no. 2 Embodiment approach

[0083] First, the configuration of the image processing device according to the second embodiment will be described. In the second embodiment, as an intraluminal image to be processed, a color image including pixel values ​​for each of the R, G, and B wavelength components in each pixel is assumed. Among them, the R component is a wavelength component far from the absorption band of blood, and is a long-wavelength component, so it is not easily affected by the light absorption and light scattering of the illumination light by the living body, and it is the most suitable for the structure of the living tissue as the imaging target. corresponding pixel value. On the other hand, the G component and the B component are easily affected by the light absorption of the illumination light by the blood in abnormal parts such as bleeding parts. Therefore, in the second embodiment, a specific wavelength component determined according to the degree of absorption or scattering in a living ...

no. 3 Embodiment approach

[0116] First, the configuration of the image processing device of the third embodiment will be described. Figure 15 It is a schematic block diagram illustrating the main configuration of the image processing device 10b of the third embodiment. In addition, the same reference numerals are assigned to the same configurations as those described in the first embodiment. Such as Figure 15 As shown, the image processing device 10b of the third embodiment includes a computing unit 20b and a recording unit 30b. The image processing device 10b is incorporated into an endoscope, for example, in the same manner as the first embodiment, receives an intraluminal image captured by the endoscope, processes the intraluminal image, and outputs a detected abnormal portion detection result. .

[0117] The calculation unit 20b includes an approximate value calculation unit 21 , a validity evaluation unit 22b , a region division unit 23 , a region integration unit 27b , a target region resett...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The present invention provides an image processing device and an image processing method. The image processing device has: according to the pixel values ​​of the pixels in the inspection object area in the image, the pixel values ​​of the pixels in the inspection object area are calculated consecutively in the inspection object area. an approximate value calculation unit for an approximate value; a validity evaluation unit for evaluating whether the approximation value is appropriate for the pixel value of the inspection target area; an area division unit for dividing the inspection target area evaluated by the validity evaluation unit as the above-mentioned approximation value being unsuitable; dividing the area Each area divided by the division unit is set as a new inspection target area, and the target area resetting unit that controls the repetition of the process; Abnormal part detection part for detecting abnormal part.

Description

technical field [0001] The present invention relates to an image processing device and an image processing method for detecting an abnormal part from an image. Background technique [0002] Conventionally, as one of technologies for reducing the burden imposed on doctors and the like by observing images of internal lumens captured by endoscopes, capsule endoscopes, etc., detection of bleeding sites, etc. from images is known. Technology of the Abnormal Department. For example, in the technology of Japanese Patent Application Laid-Open No. 2005-192880, first, each pixel in an image or each region obtained by rectangularly dividing the image is expressed as a color based on its color information (chromaticity=R / (R+G+ B), feature space of G / (R+G+B), color ratio=R / G, etc.). Furthermore, after clustering in the feature space, normal mucous membranes and abnormal types are specified based on information such as the size of each type and the coordinates of the center of gravity, ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00
CPCG06T7/0012G06T2207/10024G06T2207/10068G06T2207/10152G06T2207/30028
Inventor 神田大和北村诚松田岳博河野隆志弘田昌士
Owner OLYMPUS CORP