Device method and program for human hand posture estimation

A human hand posture estimating method comprising:

• acquiring a first hand image;
• calculating first shape data relating to vertical and horizontal sizes of the first hand image and a first image characteristic amount of the first hand image;
• reading, from a database holding a plurality of data sets each having a set of angle data of a finger, second shape data relating to vertical and horizontal sizes of a second hand image of the hand, the second shape data in a predetermined data set;
• collating the first hand image with the second hand image based on a difference between the first shape data and the second shape data, resulting in a first collated data set smaller than the predetermined data set, the first collated data set containing second shape data matched with the first shape data;
• reading a second image characteristic amount of the second hand image in the first collated data set;
• and
• collating the first image characteristic amount with the second image characteristic amount to estimate a human hand posture of the first hand image;
• wherein the shape data includes a first shape ratio obtained from a total number of vertical pixels of the hand image and a total number of horizontal pixels thereof and a second shape ratio obtained based on a positional relation between a predetermined base pixel in the hand image and a pixel of an outer end of the hand image.

A non-transitory computer-readable medium with an installed program, wherein the program, when executed, causes a computer apparatus to perform the steps of:

• acquiring a first hand image;
• calculating first shape data relating to vertical and horizontal sizes of the first hand image and a first image characteristic amount of the first hand image;
• reading, from a database holding a plurality of data sets each having a set of angle data of a finger, second shape data relating to vertical and horizontal sizes of a second hand image of the hand, the second shape data in a predetermined data set;
• collating the first hand image with the second hand image based on a difference between the first shape data and the second shape data, said collating resulting in a first collated data set that is a subset of the predetermined data set, the first collated data set containing second shape data matched with the first shape data;
• reading a second image characteristic amount of the second hand image in the first collated data set;
• and
• collating the first image characteristic amount with the second image characteristic amount to estimate a human hand posture of the first hand image;
• wherein the shape data includes a first shape ratio obtained from a total number of vertical pixels of the hand image and a total number of horizontal pixels thereof and a second shape ratio obtained based on a positional relation between a predetermined base pixel in the hand image and a pixel of an outer end of the hand image.