Image classification apparatus with first and second feature extraction units and recording medium having program recorded therein
An image-classification apparatus includes: a first feature extraction unit to acquire a feature value of each of block images obtained by segmenting an input image; an area-segmentation unit to assign each of the block images to any one of K areas based on the feature value; a second feature extraction unit to acquire, based on an area-segmentation result, a feature vector whose elements including, the number of adjacent spots, each including two block images adjacent to each other in the input image, for each combination of the areas whereto the two block images are assigned; or a ratio of the number of block images assigned to each of the K areas to all the number of block images adjacent to a block image assigned to each of the K areas; and a classification unit to classify to which of a plurality of categories the input image belongs.
1. An image classification apparatus comprising;
a first feature extraction unit structured to segment an input image into a plurality of block images each having a predetermined size, and acquire a feature value of each of the plurality of block images;
an area segmentation unit structured to segment the input image into K areas by assigning each of the plurality of block images to any one of the K areas based on the feature value, K denoting an integer equal to or greater than two;
a second feature extraction unit structured to acquire, based on an area segmentation result of the area segmentation unit, a feature vector whose elements including,
the number of adjacent spots in each of areas, the adjacent spots is where two of the block images are adjacent to each other, the each of areas corresponding to an area to which the each of the two of the block images are assigned; or
a probability that one of the block images, which is assigned to one of the K areas, is adjacent to another one of the block images, the another one of the block images is assigned to the same area as to which the one of the block images is assigned or is assigned to a different area from the area to which one of the block images is assigned; and
a classification unit structured to classify which of a plurality of categories the input image belongs to, based on the feature vector.
2. The image classification apparatus of claim 1 , wherein
the second feature extraction unit structured to acquire, based on an area segmentation result from the area segmentation unit, the feature vector whose elements including,
the number of adjacent spots are counted in the vertical direction, in the lateral direction, and in the diagonal direction, or
the probability is acquired in the vertical direction, in the lateral direction, and in the diagonal direction.
3. The image classification apparatus of claim 2 , further comprising:
a storage unit structured to store therein an area segmentation result obtained by segmenting each of a plurality of learning images into the K areas, based on the feature value of each of the plurality of block images obtained by segmenting each of the plurality of learning images, wherein
the area segmentation unit is structured to segment the input image into the K areas based on the area segmentation result stored in the storage unit.
4. The image classification apparatus of claim 3 , wherein
the input image includes an image of a cell mass cultured in a cell culture device.
5. The image classification apparatus of claim 2 , wherein
the input image includes an image of a cell mass cultured in a cell culture device.
6. The image classification apparatus of claim 1 , further comprising:
a storage unit structured to store therein an area segmentation result obtained by segmenting each of a plurality of learning images into the K areas, based on the feature value of each of the plurality of block images obtained by segmenting each of the plurality of learning images, wherein
the area segmentation unit is structured to segment the input image into the K areas based on the area segmentation result stored in the storage unit.
7. The image classification apparatus of claim 6 , wherein
the input image includes an image of a cell mass cultured in a cell culture device.
8. The image classification apparatus of claim 1 , wherein
the input image includes an image of a cell mass cultured in a cell culture device.
9. A non-transitory recording medium having a program recorded therein, the program causing a computer whereto an input image to be classified is inputted, to execute:
segmenting the input image into a plurality of block images each having a predetermined size;
acquiring a feature value of each of the plurality of block images;
segmenting the input image into the K areas by assigning each of the plurality of block images to any one of K areas based on the feature value, K denoting an integer equal to or greater than two;
acquiring, based on an area segmentation result obtained by segmenting the input image into the K areas, a feature vector whose elements include,
the number of adjacent spots in each of areas, the adjacent spots is where two of the block images are adjacent to each other, the each of areas corresponding to an area to which the each of the two of the block images are assigned, or
a probability that one of the block images, which is assigned to one of the K areas, is adjacent to another one of the block images, the another one of the block images is assigned to the same area as to which the one of the block images is assigned or is assigned to a different area from the area to which one of the block images is assigned; and
classifying which of a plurality of categories the input image belongs to based on the feature vector.