Image processing method, image processing apparatus, and image forming apparatus
The number of pixels in an identified pixel region is counted, a feature point of the pixel region is extracted and the number of the feature points is counted when the number of the pixels counted has been determined to be equal to or higher than a first threshold value, whether the counted number of the feature points is equal to or lower than a second threshold value is determined, features is calculated based on the feature point extracted from the pixel region when the number of the feature points has been determined to be above the second threshold value, and the first threshold value is changed when the number of the feature points has been determined to be equal to or lower than the second threshold value. Image similarity determination process can be stably performed without any degradation in determination accuracy.
1. An image processing method for identifying, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, extracting, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, calculating features of an image based on the extracted feature point, and determining similarity among images based on the calculated features, the method comprising steps of:
counting the number of the pixels in the identified pixel region;
determining whether the number of the pixels in the identified pixel region is equal to or higher than a first threshold value;
extracting the feature point of the pixel region and counting the number of the feature points when the number of the pixels in the identified pixel region has been determined to be equal to or higher than the first threshold value;
determining whether the counted number of the feature points is equal to or lower than a second threshold value;
calculating the features based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value; and
changing the first threshold value when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.
2. An image processing method for identifying, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, extracting, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, calculating features of an image based on the extracted feature point, and determining similarity among images based on the calculated features, the method comprising steps of:
dividing a document image into a plurality of regions;
setting a first threshold value for each divided region;
counting, in each divided region, the number of pixels of the identified pixel region;
determining whether the number of the pixels of the identified pixel region in the divided region is equal to or higher than the first threshold value in the divided region;
extracting the feature point of the pixel region and counting the number of the feature points when the number of the pixels of the identified pixel region in the divided region has been determined to be equal to or higher than the first threshold value in the divided region;
determining whether the counted number of the feature points is equal to or lower than a second threshold value;
calculating the features based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value; and
changing the first threshold value when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.
3. An image processing apparatus for identifying, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, extracting, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, calculating features of an image based on the extracted feature point, and determining similarity among images based on the calculated features, the apparatus comprising:
a pixel counting section for counting the number of the pixels in the identified pixel region;
a first determination section for determining whether the number of the pixels in the identified pixel region is equal to or higher than a first threshold value;
a feature point counting section for extracting the feature point of the pixel region and counting the number of the feature points when the number of the pixels in the identified pixel region has been determined to be equal to or higher than the first threshold value; and
a second determination section for determining whether the counted number of the feature points is equal to or lower than a second threshold value,
wherein the features is calculated based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value, and the first threshold value is changed when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.
4. An image processing apparatus for identifying, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, extracting, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, calculating features of an image based on the extracted feature point, and determining similarity among images based on the calculated features, the apparatus comprising:
a dividing section for dividing a document image into a plurality of regions;
a setting section for setting a first threshold value for each divided region;
a pixel counting section for counting, in each divided region, the number of the pixels of the identified pixel region;
a first determination section for determining whether the number of the pixels of the identified pixel region in the divided region is equal to or higher than the first threshold value in the divided region;
a feature point counting section for extracting the feature point of the pixel region and counting the number of the feature points when the number of the pixels of the identified pixel region in the divided region has been determined to be equal to or higher than the first threshold value in the divided region; and
a second determination section for determining whether the counted number of the feature points is equal to or lower than a second threshold value,
wherein the features is calculated based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value, and the first threshold value is changed when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.
5. An image forming apparatus comprising:
the image processing apparatus of claim 3 ; and
an image output apparatus for forming an image processed by the image processing apparatus.
6. An image forming apparatus comprising:
the image processing apparatus of claim 4 ; and
an image output apparatus for forming an image processed by the image processing apparatus.
7. A computer-readable memory product that stores a computer program for causing a computer to identify, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, to extract, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, to calculate features of an image based on the extracted feature point, and to determine similarity among images based on the calculated features
wherein the computer program comprises steps of:
causing the computer to count the number of the pixels in the identified pixel region;
causing the computer to determine whether the number of the pixels in the identified pixel region is equal to or higher than a first threshold value;
causing the computer to extract the feature point of the pixel region and to count the number of the feature points when the number of the pixels in the identified pixel region has been determined to be equal to or higher than the first threshold value;
causing the computer to determine whether the counted number of the feature points is equal to or lower than a second threshold value;
causing the computer to calculate the features based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value; and
causing the computer to change the first threshold value when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.
8. A computer-readable memory product that stores a computer program for causing a computer to identify, from a binary image, a plurality of pixel regions where pixels determined to be having the same pixel values are adjacent to each other, to extract, based on a pixel coordinate value of the identified pixel region, a feature point of the pixel region, to calculate features of an image based on the extracted feature point, and to determine, similarity among images based on the calculated features,
wherein the computer program comprises steps of:
causing the computer to divide a document image into a plurality of regions;
causing the computer to set a first threshold value for each divided region;
causing the computer to count, in each divided region, the number of the pixels of the identified pixel region;
causing the computer to determine whether the number of the pixels of the identified pixel region in the divided region is equal to or higher than the first threshold value in the divided region;
causing the computer to extract the feature point of the pixel region and to count the number of the feature points when the number of the pixels of the identified pixel region in the divided region has been determined to be equal to or higher than the first threshold value in the divided region;
causing the computer to determine whether the counted number of the feature points is equal to or lower than a second threshold value;
causing the computer to calculate the features based on the feature point extracted from the pixel region when the counted number of the feature points has been determined to be above the second threshold value; and
causing the computer to change the first threshold value when the counted number of the feature points has been determined to be equal to or lower than the second threshold value.