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

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.

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.