Image segmentation method and apparatus therefor

• US 5,247,583 A
• Filed: 10/31/1990
• Issued: 09/21/1993
• Est. Priority Date: 11/01/1989
• Status: Expired due to Fees

• Current Assignee: Hitachi, Ltd.
• Original Assignee: Hitachi, Ltd.
• Inventors: Morita, Toyohisa, Okawara, Hiroyuki, Kato, Makoto, Nohmi, Makoto, Miyaoka, Shinichiro
• Primary Examiner(s): Moore, David K.
• Assistant Examiner(s): Fox, David
• Application Number:
  US07/606,629
• Time in Patent Office: 1,056 Days
• Field of Search: 382/9, 382/17, 382/36, 340/701, 340/703, 340/729, 340/706, 340/709, 358/22 CK, 358/75, 358/76, 358/903, 364/526, 364/709.11, 250/226, 395/131
• US Class Current: 382/164
• CPC Class Codes: G06T 2207/10024 Color image
• CPC Class Codes: G06T 2207/20021 Dividing image into blocks, subimages or windows
• CPC Class Codes: G06T 2207/20104 Interactive definition of region of interest [ROI]
• CPC Class Codes: G06T 7/12 Edge-based segmentation
• CPC Class Codes: G06T 7/181 involving edge growing; involving edge linking

Abstract

An image processing area is divided into a plurality of small areas which are allowed to overlap one another. One or a plurality of pixels in a region to be segmented and in a region not to be segmented are specified. A representative point of the region to be segmented and a reference point of the region not to be segmented are determined from the color information of each of the pixels. A discriminating plane, a plane or a curved surface that intersects the line segment connecting the representative point and the reference point a right angles is used in processing. By the processing a particular region can be segmented out of the image. Further, a shape model is made by two-dimensionally projecting from a given direction the three-dimensional structure expressed by a line drawing consisting of nodes and curves connecting the nodes based on priori property relating the structure of the region to be segmented in the image. The shape model is then roughly correlated in position with the nodes on the contour of the image. An image processing provides stripe images having widths for each of the curves that is recomposed and used to find the contour and structure of the object in detail.

Claims

1. In an image processing apparatus for processing a color or a monochromatic density image that is digitally expressed, an image segmentation method that segments a particular object out of the image comprising:

a step of inputting information that contains at least one parameter of a position and an attribute of at least one of a region of the image to be segmented and of a region not to be segmented;

a step of decomposing the processing area in the image into a plurality of small areas that are allowed to overlap each other based upon said inputted information;

a step of setting color information to at least a pixel in said at least one region containing said at least one parameter; and

a step of deciding a discriminating boundary of pixels in said region to be segmented and pixels in said region not to be segmented, on the basis of said color information, wherein said step of setting color information sets color information to at least a pixel (representative point) of said region to be segmented and at least a pixel (reference point) of said region not to be segmented, further comprising;

a step of setting according to said color information one of a planar and a curved surface intersecting the line segment connecting said representative point and said reference point at right angles as a discriminating surface; and

said deciding step discriminating said boundary on the basis of said discriminating surface.

2. An image segmentation method according to claim 1, wherein said discriminating surface is a surface that internally divide said line segment at a ratio of t:

1-t, wherein said t is an arbitrary member of 0≦

t≦

1.

3. An image segmentation method according to claim 2, wherein said value t is such that said discriminating surface is located in a position corresponding to a minimum portion in the histogram of the color information.

4. An image segmentation method according to claim 3, wherein said value t is 0.5.

5. An image segmentation method according to claim 1, wherein when there are a plurality of said representative points and a plurality of said reference points, a logical product of discrimination results of a representative point and the plurality of reference points are obtained and then a logical sum of the results for every representative point are obtained.

6. In an image processing apparatus for processing a color or a monochromatic density image that is digitally expressed an image segmentation method, that segments a particular object out of the image, comprising:

a step of inputting information that contains at least one parameter of a position and an attribute of at least one of a region of the image to be segmented and of a region not to be segmented;

a step of decomposing the processing area in the image into a plurality of small areas that are allowed to overlap each other based upon said inputted information;

a step of setting color information to at least a pixel in said at least one region containing said at least one parameter; and

a step of deciding a discriminating boundary of pixels in said region to be segmented and pixels in said region not to be segmented, on the basis of said color information, wherein a logical operation is carried out for overlapping parts of said small areas to unify them, in order to generate a region to be segmented.

7. An image processing apparatus for segmenting a particular object out of a digitally expressed color image, comprising:

a planar apparatus having data output means for inputting a color discriminating plane corresponding to said planar apparatus itself, as three dimensional data;

means for setting color information to at least a pixel in a region to be segmented, and to at least a pixel in a region not to be segmented; and

,

means for discriminating said region to be segmented from said region not to be segmented based on said inputted discriminating plane and said color information set to the pixels, wherein said planar apparatus comprises;

a plurality of pulse transmitters provided on said planar apparatus itself;

a plurality of receivers for receiving pulses transmitted from at least one of said pulse transmitters;

means for measuring a time of transmission from a transmitter to a receiver in said plurality of pulse transmitters and receivers; and

a measuring device for measuring the position of said discriminating plane, according to the measured transmission time.