Image analysis – Image segmentation
Reexamination Certificate
1998-10-05
2001-12-25
Chang, Jon (Department: 2623)
Image analysis
Image segmentation
C358S464000, C358S466000
Reexamination Certificate
active
06333993
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to method and device of an object detectable and background removal and storage media for storing therein a program thereof for the sake of obtaining of an object with a background removed from an image. More to particularly this invention relates to method and device of object detectable and background removal and storage media for storing program for the sake of obtaining of an object from the image having virtually even background.
DESCRIPTION OF THE RELATED ART
A method and a device of object detectable and background removal, and a storage media for storing program thereof is applicable to various field of application. The object detectable and background removal method is based on a technology to isolate an object from an image with a virtually even background. The object is taken a photograph with the exception of a background area.
FIG. 1
is a view showing one example of a processing target image. In the input image signal
1
of
FIG. 1
, a target object
3
whose photograph is taken is shown in virtually even background area
2
. If it is capable of being isolated completely only the target object
3
while removing the background area
2
, it is capable of being applied to the image composition technique in the field of computer vision instead of the object recognition processing, the robot visual sensation, or the chromakey technique.
In the television program, a scene in which a person is mated with another background is often televised. The chromakey technique which is one of techniques for cutting a target object out of the background is in use for the television station frequently. The chromakey is described in accordance with the literature: “Television Image Rejection Engineering Handbook” (Television Society, pp. 704, 1990).
One of the techniques for isolating the target object to be removed the background therefrom is described in accordance with the literature: Japanese Patent Application Laid-Open No. HEI 2-206885 “Image Processing Device”. In the present literature, by way of the processing target, there is supposed that the image is composed of the background having intermediate brightness, and the object which comes to be target of cutting consists of either a brighter area than the background or a darker area than the background. The threshold which is established by some way or other is utilized, subsequently, implementing the threshold processing for isolating the pixel with brightness value beyond the threshold, thus isolating the pixel which is brighter than the background. Similarly, by virtue of the threshold processing of utilizing the threshold established separately, thus isolating the darker pixel than the back ground. Thus, it is capable of being isolated the whole object by synthesizing the results of the two threshold processing.
There is described one of the techniques for calculating stably the characteristic quantity such as the center of gravity location or the area thereof from the target object isolated out of the background. It is described in accordance with the literature: the Japanese Patent Publication No. HEI 4-116778 “Image Processing Method”.
In general, there mostly exists so called shading which is a gentle slope of brightness value in the background. In most case, the brightness value of the object also has various values, and fluctuates. In these cases, it is difficult to detect a boundary line between the background and the object accurately over the whole areas by one kind of the threshold. Accordingly, in the present literature, the user establishes two kind thresholds. One threshold is capable of detecting the target object accurately and another threshold is capable of detecting the background area accurately. The user sets these two kind of thresholds interactively to be binarized, and in terms of the pixel having intermediate value in between the two thresholds, there is allocated the value corresponding to the intermediate value. Due to the use of this method, even though the boundary line is incapable of being obtained accurately, it is capable of obtaining the center of gravity location of the target object stably.
Another binarization method is described referring to the literature: “Image Analysis Handbook” (Supervision of M. Takagi, Y. Shimoda, Tokyo University Publication Party, pp 502-505, 1991).
In the method introduced thus far, the user determined the threshold applied to whole area of picture in such away that the user set the threshold interactively while watching the image of the processing result. As shown in the literature, there is proposed a p-tile way, a method of Otu, or a method of Kittler by way of automatic determining method of the threshold. For instance, the method of Otu is so called as a discriminant analysis way in that on the assumption that a gray level histogram of an image is constituted by the sum of two normal distributions, this is the method for obtaining the threshold enabling them to be separated completely. At the same time, it is capable of calculating a degree of separation which is in use for measuring scale that it is capable of judging two distributions are separated to what degree, and that it is capable of judging whether or not bimodality of the histogram is high. Namely, the degree of separation is capable of being utilized by way of determination scale for determining whether or not the threshold being obtained is appropriate.
However, as described above, generally, the shading exists in the background mostly, accordingly there is a limit in the binarization method which sets the same threshold on the whole picture. Now, there is a method of a dynamic threshold processing for calculating the most suitable threshold in every pixel. According to the literature, the dynamic threshold processing is classified into two methods of a movement mean method and a sectional image division method.
The movement mean method is a simple method that when it causes brightness value of some pixel to be binarized, obtaining the mean value of the sectional image including the neighborhood thereof to be taken as the threshold.
The sectional image division method determines automatically the most suitable threshold in every respective sectional images while dividing the whole picture into a plurality of sectional images. The method causes the determined thresholds to be connected smoothly, thus constituting surface of the threshold over the whole picture so that the image is binarized.
There is described one example of the sectional image division method referring to the literature. Firstly, the image is divided into small area sectional images.
FIG. 2
is a typical view. When the input image signal
1
shown in
FIG. 1
is inputted, dividing the inputted image into sectional image signals
4
,
5
,
6
,
7
,
8
and so forth such that these sectional image signals overlap one another as shown in FIG.
2
. Within the respective sectional image signals, the threshold and the degree of separation are calculated at this position while applying the binarization method of Otu. In the sectional image whose degree of separation comes into high rather than value set beforehand, since there is included both of the background and the target object, thus being judged that appropriate threshold is obtained. The appropriate threshold is adopted by way of the threshold value in the pixel of the center position of the sectional image, while in the another position of the pixel, the thresholds are connected smoothly, thus surface of the threshold of the whole picture is determined. By virtue of the above described procedure, it is capable of obtaining appropriate threshold over the whole picture, thus enabling suitable binarization result to be obtained even though there exists the shading or the like.
There are two problems in the chromakey technique that it should be prepared the background constituted by peculiar color beforehand and it is incapable of being used clothing and so forth whose color are identical with background color. The m
Chang Jon
Foley & Lardner
NEC Corporation
Wu Jingge
LandOfFree
Method and device of object detectable and background... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and device of object detectable and background..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and device of object detectable and background... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2591526