1991 Fiscal Year Final Research Report Summary
Experimental Research on Intelligent Image Segmentation System
| Project/Area Number |
01850077
|
|---|
| Research Category |
Grant-in-Aid for Developmental Scientific Research
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
計算機工学
|
|---|
| Research Institution | Osaka University |
|---|
Principal Investigator |
SHIRAI Yoshiaki Osaka University, Faculty of Engineering, Professor, 工学部, 教授 (50206273)
|
|---|
| Co-Investigator(Kenkyū-buntansha) |
ETOH Minoru Matsushita Electric Industrial Co., Ltd., Researcher (CENTRAL RESEARCH LAB.), 中央研究所, 研究員
MIURA Jun Osaka University, Faculty of Engineering, Research Associate, 工学部, 助手 (90219585)
ASADA Minoru Osaka University, Faculty of Engineering, Associate Professor, 工学部, 助教授 (60151031)
|
|---|
| Project Period (FY) |
1990 – 1991
|
| Keywords | Image Processing / Segmentation / Stereo Vision / Image Understanding / Image Processor / Multi-Stage Processing |
|---|
| Research Abstract |
1 Rough Segmentation of Specified Object Region
We segmented a color image into several regions using color similarity, and used the result as an initial scene interpretation. We used the partial 3-D information derived from the initial segmentation to interpret the scene in details. The validity of our method was shown by applying it to several kinds of real scenes. Moreover, we developed a method of interpreting more complicated scenes using the depth information obtained by our stereo matching method.
2 Accurate Region Extraction from Rough Segmentation
We found that the existing methods were not applicable to objects like humans that consist of multiple parts such as faces and clothes. Then, we developed a method which detects an accurate boundary between a specified object and the background assuming it consists of several parts.
3 Design and Preliminary Implementation of High-Speed Processor for Image Segmentation
Conventional high-speed image processors are not sufficient for unage segmentation. Construction of 2-D histogram for initial color image segnientation and spatial convolution (2Ox2O) for feature extraction are major processing to speed up the image segmentation. A high-speed processors are constructed by adding these modules to a structure-variable image processor. We checked the effectiveness of the processing time by applying it to the image segmentation.
|
