FEATURE EXTRACTION METHOD, SUBJECT CLASSIFICATION METHOD, SUBJECT IDENTIFICATION METHOD, FEATURE EXTRACTION DEVICE, SUBJECT CLASSIFICATION DEVICE, SUBJECT IDENTIFICATION DEVICE, FEATURE EXTRACTION/SUBJECT CLASSIFICATION/SUBJECT IDENTIFICATION PROGRAM AND RECORDING MEDIUM RECORDING SAID PROGRAM

• 特願2011-275582 (2011.12.16) JP

Provided are: a feature extraction method that is a method of extracting a feature that represents a characteristic of a subject, said feature being extracted from an image that has imaged the subject, said feature being extracted without relation to the shape of said subject

and methods that use the extracted feature to classify and identify the subject. The feature extraction method extracts the feature from the image of the subject, said subject having been imaged by an imaging means. From the image that has imaged the subject, said feature extraction method extracts the feature by means of containing: a step in which a filter bank is created from the image

a step in which a maximum brightness image is created from the filter bank

a step in which a circular image region of the maximum brightness image is set, and the center (Cc) and the radius (Rc) of the circular image region are set

a step in which a pixel of the maximum brightness image is projected into a three-dimensional space having as the axes thereof, (a) the ratio of the radius (Rc) and the distance (LD) extending from the pixel position (x, y) to the center (Cc), (b) the pixel brightness value ((FD (x, y)), and (c) the sum of the differences between the brightness value of the pixel and the brightness values of neighboring pixels

and a step in which a frequency histogram is created from the pixel projected into the three-dimensional space.

• JAPAN SCIENCE AND TECHNOLOGY AGENCY,
• YAMAZAKI KIMITOSHI,
• INABA MASAYUKI

• YAMAZAKI KIMITOSHI,
• INABA MASAYUKI

• G06T   7/00      イメージ分析，例．ビットマップから非ビットマップへ