Image processing method and apparatus, and storage medium

An image processing method comprising:

• a step of inputting an image;
• a feature quantity extraction step of extracting a feature quantity distribution of the input image by said image input step;
• a template model input step of inputting a template model including a plurality of representative points and curved lines or segments interconnecting said representative points as a figure element;
• a template set generation step of generating a plurality of template sets different in size from each other, having figure elements generally similar to the figure element of said template model from said template model;
• a first matching step of performing the first matching processing between said template sets and the feature quantity distribution of said input image;
• a template selection step of selecting one of said template sets on the basis of a result of said first matching step;
• a second matching step of performing the second matching processing to said feature quantity distribution as to each representative point of the template selected in said template selection step;
• a representative point update step of shifting said representative point on the basis of a result of said second matching step;
• a template update step of generating an update template including the representative points after shift and curved lines or segments interconnecting said representative points as a figure element;
• a mask area generation step of generating a mask area including said figure element in said update template as a boundary line;
• and
• an image extraction step of extracting one of the contour line of said mask area and image data corresponding to said mask area.

An image processing apparatus comprising:

• image input means for inputting an image;
• feature quantity extraction means for extracting a feature quantity distribution of the input image by said image input means;
• template model input means for inputting a template model including a plurality of representative points and curved lines or segments interconnecting said representative points as a figure element;
• matching means for performing matching processing between said template model and said feature quantity distribution;
• shift condition set means for setting a shift condition of said each representative point on the basis of a matching result of said matching means;
• representative point update means for shifting said each representative point in accordance with said shift condition;
• template update means for generating an update template including the representative points after shift and curved lines or segments interconnecting said representative points as a figure element;
• and
• image extraction means for extracting image data in an area within said update template from said input image.

An image processing apparatus comprising:

• means for inputting an image;
• feature quantity extraction means for extracting a feature quantity distribution of the input image by said image input means;
• template model input means for inputting a template model including a plurality of representative points and curved lines or segments interconnecting said representative points as a figure element;
• template set generation means for generating a plurality of template sets different in size from each other, having figure elements generally similar to the figure element of said template model from said template model;
• first matching means for performing the first matching processing between said template sets and the feature quantity distribution of said input image;
• template selection means for selecting one of said template sets on the basis of a result of said first matching means;
• second matching means for performing the second matching processing to said feature quantity distribution as to each representative point of the template selected in said template selection means;
• representative point update means for shifting said representative point on the basis of a result of said second matching means;
• template update means for generating an update template including the representative points after shift and curved lines or segments interconnecting said representative points as a figure element;
• mask area generation means for generating a mask area including said figure element in said update template as a boundary line;
• and
• image extraction means for extracting one of the contour line of said mask area and image data corresponding to said mask area.

A storage medium storing an image processing method comprising:

• an image input step of inputting an image;
• a feature quantity extraction step of extracting a feature quantity distribution of the input image by said image input step;
• a template model input step of inputting a template model including a plurality of representative points and curved lines or segments interconnecting said representative points as a figure element;
• a matching step of performing matching processing between said template model and said feature quantity distribution;
• a shift condition set step of setting a shift condition of said each representative point on the basis of a matching result of said matching step;
• a representative point update step of shifting said each representative point in accordance with said shift condition;
• a template update step of generating an update template including the representative points after shift and curved lines or segments interconnecting solid representative points as a figure element;
• and
• an image extraction step of extracting image data in an area within said update template from said input image.

A storage medium storing an image processing method comprising:

• a step of inputting an image;
• a feature quantity extraction step of extracting a feature quantity distribution of the input image by said image input step;
• a template model input step of inputting a template model including a plurality of representative points and curved lines or segments interconnecting said representative points as a figure element;
• a template set generation step of generating a plurality of template sets different in size from each other, having figure elements generally similar to the figure element of said template model from said template model;
• a first matching step of performing the first matching processing between said template sets and the feature quantity distribution of said input image;
• a template selection step of selecting one of said template sets on the basis of a result of said first matching step;
• a second matching step of performing the second matching processing to said feature quantity distribution as to each representative point of the template selected in said template selection step;
• a representative point update step of shifting said representative point on the basis of a result of said second matching step;
• a template update step of generating an update template including the representative points after shift and curved lines or segments interconnecting said representative points as a figure element;
• a mask area generation step of generating a mask area including said figure element in said update template as a boundary line;
• and an image extraction step of extracting one of the contour line of said mask area and image data corresponding to said mask area.