Image processing device and image processing method in image processing device for identifying features in an image

• US 8,300,955 B2
• Filed: 06/24/2011
• Issued: 10/30/2012
• Est. Priority Date: 12/28/2005
• Status: Active Grant

• Current Assignee: Olympus Corporation
• Original Assignee: Olympus Medical Systems Corporation (Olympus Corporation)
• Inventors: Nishimura, Hirokazu, Nonami, Tetsuo
• Primary Examiner(s): Lu, Tom Y
• Assistant Examiner(s): CONWAY, THOMAS A
• Application Number:
  US13/168,510
• Publication Number:
  US 20110255759A1
• Time in Patent Office: 494 Days
• Field of Search: None
• US Class Current: 382/224
• CPC Class Codes: A61B 1/00016 using wireless means
• CPC Class Codes: A61B 1/00036 Means for power saving, e.g. sleeping mode
• CPC Class Codes: A61B 1/00055 for alerting the user
• CPC Class Codes: A61B 1/041 Capsule endoscopes for imaging
• CPC Class Codes: A61B 5/073 Intestinal transmitters
• CPC Class Codes: A61B 5/7264 Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems neural networks per se G06N3/00; expert systems per se G06N5/00
• CPC Class Codes: A61B 5/7267 involving training the classification device
• CPC Class Codes: G06T 2207/10016 Video; Image sequence
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/10068 Endoscopic image
• CPC Class Codes: G06T 2207/30028 Colon; Small intestine
• CPC Class Codes: G06T 2207/30168 Image quality inspection
• CPC Class Codes: G06T 7/0002 Inspection of images, e.g. flaw detection
• CPC Class Codes: G06V 10/56 relating to colour
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A plurality of images inputted in an image signal input portion are divided into a plurality of regions by an image dividing portion, and a feature value in each of the plurality of regions is calculated by a feature value calculation portion and divided into a plurality of subsets by a subset generation portion. On the other hand, a cluster classifying portion classifies a plurality of clusters generated in a feature space into any one of a plurality of classes on the basis of the feature value and occurrence frequency of the feature value. And a classification criterion calculation portion calculates a criterion of classification for classifying images included in one subset on the basis of a distribution state of the feature value in the feature space of each of the images included in the one subset.

Claims

1. An image processing device comprising:

an image signal input portion for inputting an image signal of images obtained by medical equipment having an imaging function;

an image dividing portion for dividing each of a plurality of images into a plurality of regions, respectively, the plurality of images being representative of the image signal;

a feature vector calculation portion for calculating a plurality of feature vectors in each of the plurality of regions;

a first cluster classifying portion for generating a first plurality of clusters in a first feature space on the basis of a first feature vector of the plurality of feature vectors and the occurrence frequency of the first feature vector in the plurality of feature vectors and for classifying the first plurality of clusters into any of a plurality of classes, respectively, the first feature space indicating chromaticity of the image;

a second cluster classifying portion for generating a second plurality of clusters in a second feature space on the basis of a second feature vector of the plurality of feature vectors and the occurrence frequency of the second feature vector in the plurality of feature vectors and for classifying the second plurality of clusters into any of the plurality of classes, respectively, the second feature space indicating variation in the chromaticity of the image; and

a cluster division portion for carrying out division processing such that, when it is detected that the second feature vectors calculated in different regions included in the plurality of regions belong to different clusters respectively in the second plurality of clusters and that the first feature vectors calculated in the different regions included in the plurality of regions belong to one cluster in the first plurality of clusters, the division processing is carried out with respect to the one cluster.

2. An image processing method in an image processing device comprising:

an image dividing step for dividing an image into a plurality of regions, respectively;

a feature vector calculation step for calculating a plurality of feature vectors in each of the plurality of regions;

a first cluster classifying step for generating a first plurality of clusters in a first feature space on the basis of a first feature vector of the plurality of feature vectors and the occurrence frequency of the first feature vector in the plurality of feature vectors and for classifying the first plurality of clusters into any of a plurality of classes, respectively, the first feature space indicating chromaticity of the image;

a second cluster classifying step for generating a second plurality of clusters in a second feature space on the basis of a second feature vector of the plurality of feature vectors and the occurrence frequency of the second feature vector in the plurality of feature values and for classifying the second plurality of clusters into any of the plurality of classes, respectively, the second feature space indicating variation in the chromaticity of the image; and

a cluster division step for carrying out division processing such that, when it is detected that the second feature vectors calculated in different regions included in the plurality of regions belong to different clusters respectively in the second plurality of clusters and that the first feature vectors calculated in the different regions included in the plurality of regions belong to one cluster in the first plurality of clusters, the division processing is carried out with respect to the one cluster.

3. An image processing method in an image processing device comprising:

dividing an image obtained by medical equipment into a plurality of regions;

calculating a plurality of feature vectors in each of the plurality of regions;

generating a first plurality of clusters in a first feature space on the basis of a first feature vector and the occurrence frequency of the first feature vector in a plurality of feature vectors and classifying the first plurality of clusters into any one of a plurality of classes, respectively, the first feature space indicating chromaticity of the image;

generating a second plurality of clusters in a second feature space on the basis of a second feature vector and the occurrence frequency of the second feature vector in the plurality of feature vectors and classifying the second plurality of clusters into any of the plurality of classes, respectively, the second feature space indicating chromaticity of the image; and

carrying out division processing such that, when it is detected that the second feature vectors calculated in different regions included in the plurality of regions belong to different clusters respectively in the second plurality of clusters and that the first feature vectors calculated in the different regions included in the plurality of regions belong to one cluster in the first plurality of clusters, the division processing is carried out with respect to the one cluster.