초록 ▼

In a method for extracting an object image, an extraction area for extraction of a candidate for a predetermined object image from an image is determined. The center point of a view window, which has a predetermined size, is caused to travel to the position of the candidate for the predetermined obj

In a method for extracting an object image, an extraction area for extraction of a candidate for a predetermined object image from an image is determined. The center point of a view window, which has a predetermined size, is caused to travel to the position of the candidate for the predetermined object image. The extraction area is determined in accordance with the size and/or the shape of the candidate for the predetermined object image, the center point of the view window being taken as a reference during the determination of the extraction area. The extraction of the candidate for the predetermined object image is carried out by using a neural network. Even if a plurality of object images, which are to be extracted, are embedded in a given image, the object images are extracted efficiently such that an object image, which has already been extracted, may not be extracted again.

대표청구항 ▼

[ What is claimed is:] [1.] A method for extracting a contour line of an object image, wherein a contour line of a candidate for a predetermined object image is extracted from an image, the method for extracting the contour line of an object image comprises the steps of:i) setting a view window havi

[ What is claimed is:] [1.] A method for extracting a contour line of an object image, wherein a contour line of a candidate for a predetermined object image is extracted from an image, the method for extracting the contour line of an object image comprises the steps of:i) setting a view window having a predetermined size smaller than the image, in a portion of the image having the candidate for a predetermined object image;ii) enlarging the size of the view window so that the entire candidate for the predetermined object image is within the view window, if the size of the predetermined object image is larger than the view window;iii) causing the center of the view window to travel to the center of the candidate for the predetermined object image;iv) fetching the candidate for a predetermined object image falling within said view window;v) normalizing the size and/or the shape of the fetched candidate for the predetermined object image based on the center point of said view window and a contour line of said candidate for the predetermined object image as references; andvi) thereafter extracting a contour line of the normalized candidate for the predetermined object image.