Image processing apparatus and image processing method
An image processing apparatus includes a storing unit that stores dictionary data including information on a feature area that indicates an area where a feature of a subject appears; and a subject determination unit that compares, when an input image is acquired, the feature area of the dictionary data with an area of the input image corresponding to the feature area of the dictionary data, to determine whether the input image includes the subject.
1. An image processing apparatus comprising:
an analysis processing unit that extracts a frequency of appearance of a feature of a subject in each area that constitutes an input image, based on a plurality of frequency components into which the input image is converted, and classifies the areas of the input image into a plurality of feature areas according to the frequency of appearance of the feature of the subject, and creates dictionary data including information on the plurality of feature areas classified including information on a feature area that indicates an area of the input image where the frequency of appearance of the feature of the subject is higher than in other areas of the input image based on the extracted frequency of appearance; and
a subject determination unit that compares, when a detection target image for the subject to be detected from is acquired, each of the feature areas of the dictionary data with an area of the detection target image corresponding to the feature area, to determine whether the detection target image includes the subject.
2. The image processing apparatus according to claim 1 , wherein the subject determination unit makes comparison of the feature areas included in the dictionary data in descending order of the frequency of appearance of the subject.
3. An image processing method performed in an image processing apparatus, comprising: extracting a frequency of appearance of a feature of a subject in each area that constitutes an input image, based on a plurality of frequency components into which the input image is converted;
classifying the areas of the input image into a plurality of feature areas according to the frequency of appearance of the feature of the subject;
creating dictionary data including information on a feature area that indicates an area of the input image where the frequency of appearance of the feature of the subject is higher than in other areas of the input image based on the extracted frequency of appearance; and
comparing, when a detection target image for the subject to be detected from is acquired, each of the feature areas of the dictionary data with an area of the detection target image corresponding to the feature area, to determine whether the detection target image includes the subject.
4. The image processing method according to claim 3 , wherein the comparing includes comparing the feature areas included in the dictionary data in descending order of the frequency of appearance of the subject.