Image processing device, image processing method, and image processing program

An image processing device and image technology, applied in image data processing, image data processing, image enhancement and other directions, can solve the problems of inability to calculate feature quantities, inability to discriminate between normal and abnormal with high precision, and achieve the effect of high-precision recognition

Active Publication Date: 2015-07-29
OLYMPUS CORP
View PDF9 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Therefore, when calculating feature quantities based on spatial frequency for the entire image as in the prior art, appropriate feature quantities cannot be calculated due to the influence of these contour edges, and there is a problem that it is impossible to distinguish between normal and abnormal with high accuracy.

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, image processing method, and image processing program
  • Image processing device, image processing method, and image processing program
  • Image processing device, image processing method, and image processing program

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0051] figure 1 It is a block diagram showing the image processing device according to Embodiment 1 of the present invention. like figure 1 As shown, the image processing device 1 has a control unit 10 that controls the overall operation of the image processing device 1, an image acquisition unit 20 that acquires image data corresponding to an image captured by an endoscope, and accepts input from the outside. An input unit 30 for input signals, a display unit 40 for performing various displays, a recording unit 50 for storing image data acquired by the image acquisition unit 20 and various programs, and a computing unit 100 for performing predetermined image processing on the image data.

[0052] The control unit 10 is realized by hardware such as a CPU, reads various programs recorded in the recording unit 50, and executes the configuration of the image processing device 1 based on the image data input from the image acquisition unit 20 and the operation signal input from t...

Deformed example 1-1

[0091] Next, Modification 1-1 of Embodiment 1 of the present invention will be described.

[0092] In Embodiment 1 above, an example of using the spatial frequency component as the texture information of the mucous membrane surface was shown, but instead of the spatial frequency component, a statistical feature value using a co-occurrence matrix or a Local Binary Pattern (local binary pattern) may be used. , high-order local autocorrelation, SIFT (Scale-Invariant Feature Transform: scale-invariant feature transformation), HOG (Histograms of Oriented Gradients: gradient direction histogram) and other well-known texture information.

Deformed example 1-2

[0094] Next, Modification 1-2 of Embodiment 1 of the present invention will be described.

[0095] Figure 9 It is a block diagram showing the configuration of the computing unit included in the image processing device of Modification 1-2. Figure 9 The illustrated calculation unit 100A includes a contour edge region extraction unit 110A, an inspection region setting unit 120A, and an abnormal structure recognition unit 130A. In addition, the configuration and operation of the image processing device other than the computing unit 100A are the same as those of Embodiment 1 (see figure 1 ).

[0096] Contour edge region extracting unit 110A is relative to figure 1 The shown contour edge region extraction section 110 also has a low-absorption wavelength selection section 114 . The low-absorption wavelength selection unit 114 selects a wavelength component (low-absorption wavelength component) in which the degree of absorption or scattering in the living body is the lowest amon...

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

Provided are an image processing device and the like which enable the abnormality of the microstructure of the surface of an inspection object such as a mucous membrane to be accurately identified even when the contour edge of the inspection object is present in an intraluminal image. An image processing device (1) is provided with: a contour edge region extraction unit (110) for extracting a contour edge region of an inspection object from an image obtained by capturing an image of the inside of a lumen of a living organism; an inspection region setting unit (120) for setting an inspection region in the image such that the contour edge region is not contained therein; and an abnormal structure identification unit (130) for identifying whether the microstructure of the surface of the inspection object is abnormal or not on the basis of texture information relating to the inspection region.

Description

technical field [0001] The present invention relates to an image processing device, an image processing method, and an image processing program for recognizing an abnormality in the fine structure of the surface of an inspection object reflected in an image obtained by imaging the inside of a lumen of a living body. Background technique [0002] As image processing for an image (hereinafter referred to as an intraluminal image or simply an image) obtained by imaging the lumen of a living body with a medical observation device such as an endoscope or a capsule endoscope, for example, Patent Document 1 discloses a technique for detecting an abnormal part from an image based on the fine structure of the mucosal surface or the progression of blood vessels. More specifically, after extracting an image composed of the G (green) component that contains a lot of information on the fine structure of the mucosa or blood vessel images from the intraluminal image, the pixel value patter...

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 Applications(China)
IPC IPC(8): A61B1/04G06T1/00G06V10/764G06V10/44
CPCG06T7/0012G06T7/401G06T2207/10068G06T2207/10024G06T7/41G06T2207/20021G06T2207/20041G06T2207/30028G06T2207/30092G06V10/431G06V10/44G06V2201/032G06V10/764G06F18/2415G06T7/00G06T2207/30101
Inventor 神田大和北村诚河野隆志弘田昌士上山都士也
Owner OLYMPUS CORP
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap