Image processing system and method thereof in which three dimensional shape is reproduced from two dimensional image data

A method of detecting fingers of a human hand comprising the steps of:

• reading the hand and outputting image data of the hand in a form of two-dimensional pixel data;
• detecting edges of the hand on the basis of said pixel data;
• determining image lines as lines having greatest number of edge pixels;
• determining the orientation line of the hand as the line having the average slope and Y intercept of said image lines;
• searching the pixel data for edge pixels wherein the search is statistically biased in a direction parallel to the orientation line;
• and
• clustering edge pixels defining said finger tips;
• wherein said clustering step includes
• choosing arbitrary locations in a cluster,
• assigning the termination pixel of each search to a cluster location of the basis of a least euclidean distance, and
• determining new cluster locations by computing the centroid of all said pixels assigned to the cluster.

A method of extracting features of an object, comprising the steps of:

• photographing the object and outputting image data of the object in a form of two-dimensional pixel data;
• detecting edges of the object on the basis of said pixel data;
• determining image lines as lines having greatest number of edge pixels;
• determining the orientation line of the hand as the line having the average slope and Y intercept of said image lines;
• searching the pixel data for edge pixels wherein the search is statistically biased in a direction parallel to the orientation line;
• and
• clustering edge pixels defining said finger tips;
• wherein said steps of determining image lines and the determining the orientation line include
• transforming a rectilinear coordinate system of said detected edges into a polar coordinate system,
• accumulating edge points in the parameter space, and
• obtaining the highest accumulated values for each of said lines to determine said orientation line of the object.

A method of extracting features of an object, comprising the steps of:

• photographing the object and outputting image data of the object in a form of two-dimensional pixel data;
• detecting edges of the object on the basis of said pixel data;
• determining image lines as lines having greatest number of edge pixels;
• determining the orientation line of the hand as the line having the average slope and Y intercept of said image lines;
• searching the pixel data for edge pixels wherein the search is statistically biased in a direction parallel to the orientation line;
• and
• clustering edge pixels defining said finger tips;
• wherein said clustering step includes
• choosing arbitrary locations in a cluster,
• assigning the termination pixel of each search to a cluster location of the basis of a least euclidean distance, and
• determining new cluster locations by computing the centroid of all of said pixels assigned to the cluster.