Image processing method and computer-readable recording medium having recorded thereon image processing program
An image processing method that includes obtaining an original image including a cultured cell image with a background image, dividing the original image into blocks, each composed of a predetermined number of pixels, and obtaining a spatial frequency component of an image in each block for each block, and classifying each block as the one belonging to a cell cluster corresponding to the cell or the one belonging to other than the cell cluster in a two-dimensional feature amount space composed of a first feature amount which is a total of intensities of low frequency components having a frequency equal to or lower than a predetermined frequency and a second feature amount which is a total of intensities of high frequency components having a higher frequency than the low frequency component, and segmenting the original image into an area occupied by the blocks classified as the cell cluster and another area.
1. An image processing method, comprising:
obtaining an original image including a cultured cell image with a background image;
dividing the original image into blocks each composed of a predetermined number of pixels and obtaining a spatial frequency component of an image in each block for each block;
setting a total of intensities of low frequency components having a frequency equal to or lower than a predetermined frequency as a first feature amount, setting a total of intensities of high frequency components having a higher frequency than the low frequency component as a second feature amount, and classifying each block as the one belonging to a cell cluster corresponding to the cell or the one belonging to other than the cell cluster in a two-dimensional feature amount space composed of the first feature amounts and the second feature amounts;
segmenting the original image into an area occupied by the blocks classified as the cell cluster and another area;
receiving an instruction input by a user on a point belonging to the cell image and a point belonging to a background image in the original image;
obtaining the first feature amount and the second feature amount for each of at least one block including the point belonging to the cell image and at least one block including the point belonging to the background image based on a result of the input instruction; and
specifying a range of the cell cluster in the two-dimensional feature amount space based on obtained results,
wherein an intensity of a direct-current component, out of the spatial frequency components, is set as the first feature amount and a total of intensities of all alternating-current components is set as the second feature amount.
2. The image processing method according to claim 1 , wherein a two-dimensional discrete cosine transform is performed for each block based on pixel values of the pixels included in this block, and the intensity of each frequency component is obtained as a discrete cosine transform coefficient of this frequency component.
3. The image processing method according to claim 2 , wherein each block is a square, a size of one side of which is equivalent to 4 pixels.
4. The image processing method according to claim 1 , further comprising converting a pixel size of the original image from an original pixel size when the original image was obtained to a pixel size for block division different from the original pixel size prior to division of the original image into blocks.
5. The image processing method according to claim 1 , wherein the original image is an image obtained by bright field imaging a cell.
6. The image processing method according to claim 1 , wherein size of the block corresponds to size of one cell.
7. An image processing method, comprising:
obtaining an original image including a cultured cell image with a background image;
dividing the original image into blocks each composed of a predetermined number of pixels and obtaining a spatial frequency component of an image in each block for each block;
setting a total of intensities of low frequency components having a frequency equal to or lower than a predetermined frequency as a first feature amount, setting a total of intensities of high frequency components having a higher frequency than the low frequency component as a second feature amount and classifying each block as the one belonging to a cell cluster corresponding to the cell or the one belonging to other than the cell cluster in a two-dimensional feature amount space composed of the first feature amounts and the second feature amounts; and
segmenting the original image into an area occupied by the blocks classified as the cell cluster and another area, and
prior to classification, receiving an instruction input by a user on a point belonging to the cell image and a point belonging to a background image in the original image, obtaining the first feature amount and the second feature amount for each of at least one block including the point belonging to the cell image and at least one block including the point belonging to the background image based on a result of the input instruction, and specifying a range of the cell cluster in the two-dimensional feature amount space based on obtained results, wherein a two-dimensional discrete cosine transform is performed for each block based on pixel values of the pixels included in this block, and the intensity of each frequency component is obtained as a discrete cosine transform coefficient of this frequency component, and wherein the two-dimensional discrete cosine transform is performed based on values obtained by subtracting an average pixel value of the entire original image from the pixel values of the respective pixels.
8. An image processing method, comprising:
obtaining an original image including a cultured cell image with a background image;
dividing the original image into blocks each composed of a predetermined number of pixels and obtaining a spatial frequency component of an image in each block for each block;
setting a total of intensities of low frequency components having a frequency equal to or lower than a predetermined frequency as a first feature amount, setting a total of intensities of high frequency components having a higher frequency than the low frequency component as a second feature amount and classifying each block as the one belonging to a cell cluster corresponding to the cell or the one belonging to other than the cell cluster in a two-dimensional feature amount space composed of the first feature amounts and the second feature amounts; and
segmenting the original image into an area occupied by the blocks classified as the cell cluster and another area, and
prior to classification, receiving an instruction input by a user on a point belonging to the cell image and a point belonging to a background image in the original image, obtaining the first feature amount and the second feature amount for each of at least one block including the point belonging to the cell image and at least one block including the point belonging to the background image based on a result of the input instruction, and specifying a range of the cell cluster in the two-dimensional feature amount space based on obtained results, wherein a two-dimensional discrete cosine transform is performed for each block based on pixel values of the pixels included in this block, and the intensity of each frequency component is obtained as a discrete cosine transform coefficient of this frequency component, and wherein a total of intensities of a plurality of frequency components is obtained as a sum of absolute values of discrete cosine transform coefficients of the respective frequency components.
9. A non-transitory computer-readable recording medium having recorded thereon a program for performing the image processing method according to claim 1 .