Object extracting method using motion picture

Claim 2

An object extracting method using a motion picture, said method comprising: obtaining a difference image frame by getting a pair of still image frames separated by a predetermined time interval from a motion picture; obtaining a color image frame which satisfies color information defining a color of a particular object from one of the still image frames; performing a grid processing of a logic image frame, which is obtained from comparing the difference image frame and the color image frame, at a predetermined grid size; obtaining connected components using direction connection information of the processed grids and defining minimum areas that each includes one of the connected components; comparing each of the minimum areas with predetermined conditions, thereby selecting the minimum areas which satisfy the conditions as object area candidates; and extracting an object by selecting and optimizing an object area candidate which has a prescribed size among the object area candidates.

Claim 3

The method of claim 1 , wherein the predetermined time interval is a time that motion change of the particular object can be detected in the motion picture.

Claim 4

The method of claim 1 , wherein the difference image frame only represents an area where there is the motion change of the particular object between the two still image frames.

Claim 5

The method of claim 1 , wherein the particular object is a human face.

Claim 6

The method of claim 1 , wherein the color information is a color which a user arbitrarily defines by adjusting color condition of the object in specific color space.

Claim 7

The method of claim 1 , wherein the color information represents a skin color.

Claim 8

The method of claim 1 , wherein the color image frame is defined by RGB.

Claim 9

The method of claim 1 , wherein the color image frame is obtained from one of the still image frames.

Claim 10

The method of claim 1 , wherein the logic image frame is obtained by ANDing the difference image frame and the color image frame.

Claim 11

The method of claim 1 , wherein the direction connection information indicates a connection state of a grid to other grids with respect to eight directions.

Claim 12

The method of claim 1 , wherein each of the connected components is composed of grids which are gathered according to the direction connection information.

Claim 13

The method of claim 1 , wherein the minimum area is a rectangle which includes the connected components.

Claim 14

The method of claim 1 , wherein the predetermined conditions are: (1) A size of a variable RECT[i]>a threshold value of a size of the minimum area; (2) A minimum value<the row/column ratio of the variable RECT[i]<a maximum value; (3) A density of the variable RECT[i]<a threshold value of a density, wherein the threshold value of the size of the minimum area, and wherein the minimum value and the maximum value of the row/column ratio of the variable RECT[i] are previously defined values in accordance with the object, and the density of the variable RECT[i] is a value of which the density of the connected components is divided by an area size of the variable RECT[i].

Claim 15

The method of claim 1 , wherein the prescribed size is a largest size among the object area candidates, and wherein the largest object candidate area is located nearest to a camera.

Claim 16

The method of claim 1 , wherein in the optimizing the selected object area candidate, each row or each column of the object area candidate obtains its density and each density is compared with the defined threshold value of the density and the row or column of which density is smaller than the threshold value is deleted.

Claim 17

The method of claim 15 , wherein the density is in the minimum area variable RECT[i] which includes the connected components the density is a value of which the number of grids in a row or a column of one of the connected components is divided by a length of the row or the column thereof.

Claim 18

The method of claim 1 , wherein the extracting the object comprises optimizing each of the object area candidates and selecting the largest area candidate thereamong.

Claim 19

The method of claim 1 , wherein the predetermined conditions are not based on pixel color.

Claim 20

The method of claim 1 , wherein the grid processing divides the logic image frame into a plurality of fixed size grids and compares a value representing pixels of each grid to a prescribed value to express said each grid as a binary grid image, wherein when the value of said each grid is greater than the prescribed value the binary grid image is set to one (1).

Claim 21

An object extracting method using a motion picture, said method comprising: obtaining a difference image frame representing motion changes of at least an object in the motion picture by retrieving a pair of still image frames separated by a predetermined time interval from the motion picture; obtaining a color image frame representing color information defining a color of said at least one object from one of the pair of still image frames; logically processing the difference image frame and the color image frame at a predetermined grid size to determine a logic image frame representing color and motion information of the motion picture; determining a binary value for each of a plurality of grids having the predetermined grid size in the logical frame, wherein said each grid of the logical frame having a first value of the binary values is a component; obtaining connected components that each contain at least two corresponding components using direction connection information of each of the corresponding components; defining minimum areas that each include one of the connected components; comparing each of the minimum areas with predetermined conditions to select minimum areas that satisfy the predetermined conditions as object area candidates; and extracting said at least one object by selecting an object area candidate that has a prescribed size among the object area candidates.

Claim 22

An object extracting method using a motion picture, said method comprising: obtaining a difference image frame representing motion changes of at least an object in the motion picture by retrieving a pair of still image frames separated by a predetermined time interval from the motion picture; obtaining a color image frame representing color information defining a color of said at least one object from one of the pair of still image frames; logically processing the difference image frame and the color image frame at a predetermined grid size to determine a logic image frame representing color and motion information of the motion picture; determining a binary value for each of a plurality of grids having the predetermined grid size in the logical frame, wherein said each grid of the logical frame having a first value of the binary values is a component; obtaining connected components that each contain at least two corresponding components using direction connection information of each of the corresponding components; defining minimum areas that each include one of the connected components; comparing each of the minimum areas with predetermined conditions to select minimum areas that satisfy the predetermined conditions as object area candidates; and extracting said at least one object by selecting an object area candidate that has a prescribed size among the object area candidates.

Claim 23

The method of claim 20 , wherein the predetermined conditions are one of the following: (1) a size of a variable RECT[i]>a threshold value of a size of the minimum area; (2) a minimum value<the row/column ratio of the variable RECT[i]<a maximum value; and (3) a density of the variable RECT[i]<a threshold value of a density, wherein the threshold value of the size of the minimum area, the minimum value and the maximum value of the row/column ratio of the variable RECT[i] are previously defined values in accordance with the object, and the density of the variable RECT[i] is a value of which the density of the connected grid components is divided by an area size of the variable RECT[i].

Claim 24

The method of claim 20 , wherein the predetermined conditions are not based on pixel color.

Claim 25

The method of claim 20 , wherein the predetermined conditions are at least one of row density, column density and minimum area density.

Claim 26

The method of claim 20 , wherein each component has four sides and four corners, wherein the obtaining connected components comprises: selecting one component as a current component; evaluating components by combining the components adjacent to any one of the sides and the corners of the current component to be a current intermediate connected component; joining any component adjacent to one of sides and corners of the current intermediate connected component together to be the current intermediate connected component; repeating the joining step until no components are joined to the current intermediate connected component; defining the current intermediate connected component as one of said connected components; setting one of unevaluated components as the current component; and repeating the evaluating through setting steps until no unevaluated components remain.

Claim 27

An object extracting method using a motion picture, said method comprising: retrieving a pair of still image frames separated by a prescribed time interval from a motion picture; determining a difference image frame containing relative motion information by comparing motion information of the two still images of the pair; comparing prescribed color information to at least one of the two still images to determine a color image frame that indicates areas of the color image frame that satisfy the prescribed color information from said one of the still image frames; determining a logic image frame by logically comparing the difference image frame containing the relative motion information and the color image frame representing prescribed color information; grid processing the logic image frame at a prescribed grid size to determine a plurality of grid components in the logic image frame having the prescribed grid size; determining connected components from the plurality of grid components using direction connection information to combine adjacent grid components into one of said connected components; defining a minimum size; determining any connected components greater than the minimum size as candidate regions; comparing each of the candidate regions with prescribed conditions to select the candidate regions that satisfy the prescribed condition as object area candidates; selecting an object area candidate having a prescribed two-dimensional size among the object area candidates containing an object; and extracting the object from the motion picture.

Claim 28

An object extracting method using a motion picture, said method comprising: retrieving a pair of still image frames separated by a prescribed time interval from a motion picture; determining a difference image frame containing relative motion information by comparing motion information of the two still images of the pair; comparing prescribed color information to at least one of the two still images to determine a color image frame that indicates areas of the color image frame that satisfy the prescribed color information from said one of the still image frames; determining a logic image frame by logically comparing the difference image frame containing the relative motion information and the color image frame representing prescribed color information; grid processing the logic image frame at a prescribed grid size to determine a plurality of grid components in the logic image frame having the prescribed grid size; determining connected components from the plurality of grid components using direction connection information to combine adjacent grid components into one of said connected components; defining a minimum size; determining any connected components greater than the minimum size as candidate regions; comparing each of the candidate regions with prescribed conditions to select the candidate regions that satisfy the prescribed condition as object area candidates; selecting an object area candidate having a prescribed two-dimensional size among the object area candidates containing an object; and extracting the object from the motion picture.

Claim 29

The method of claim 25 , wherein the prescribed conditions are not based on pixel color, and wherein the prescribed conditions are not one of a set of patterns.

Claim 30

The method of claim 25 , further comprising determining one of first and second binary values for each of the plurality of grid components having the prescribed grid size in the logical frame, wherein said each grid having the first value of the binary values is a grid component.

Claim 31

The method of claim 25 , wherein each grid of the logic image value is given a binary value responsive to the underlying pixels of the difference image frame and the color image frame forming said each grid, and wherein the candidate regions are polygons that each include a single corresponding one of the connected components.

Claim 32

The method of claim 25 , wherein the predetermined conditions are one of the following: (1) a size of a variable RECT[i]>a threshold value of a size of the minimum area; (2) a minimum value<the row/column ratio of the variable RECT[i]<a maximum value; and (3) a density of the variable RECT[i]<a threshold value of a density, wherein the threshold value of the size of the minimum area, the minimum value and the maximum value of the row/column ratio of the variable RECT[i] are previously defined values in accordance with the object, and the density of the variable RECT[i] is a value of which the density of the connected grid components is divided by an area size of the variable RECT[i].

Claim 33

The method of claim 25 , wherein each grid component has four sides and four corners, wherein the determining connected components comprises: selecting one component as a current component; evaluating components by combining the components adjacent to any one of the sides and the corners of the current component to be a current intermediate connected component; joining any component adjacent to one of sides and corners of the current intermediate connected component together to be the current intermediate connected component; repeating the joining step until no components are joined to the current intermediate connected component; defining the current intermediate connected component as one of said connected components; setting one of unevaluated components as the current component; and repeating the evaluating through setting steps until no unevaluated components remain.