|
1. |
Recognition of material types and interreflection using color images |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 1-12
Tadashi Hashimoto,
Hirokazu Kato,
Kosuke Sato,
Seiji Inokuchi,
Kosuke Moriwaki,
Preview
|
PDF (1127KB)
|
|
摘要:
AbstractIn computervision it is expected that the capability of recognizing an object is increased significantly by additional information of material types to conventional geometrical information such as the position, shape, and posture of the object. To materialize this idea, this paper proposes a simple color‐reflection model which classifies colored opaque objects seen under white light according to their gloss into three categories: “metallic;” “matte nonmetallic;” and “glossy nonmetallic.” This model is based on the dichromatic reflection model proposed by Shafer but with an extended capability to include metallic objects. The model can recognize not only apparent material but can also detect interreflection of the object. The effectiveness of the method was confirmed successfully by applying it to actual scenes containing metallic and nonmet
ISSN:0882-1666
DOI:10.1002/scj.4690231201
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
2. |
Analysis of facial expressions using a three‐dimensional facial model |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 13-28
Chang Seok Choi,
Tsuyosi Takebe,
Hiroshi Harashima,
Preview
|
PDF (2346KB)
|
|
摘要:
AbstractThis paper proposes a method which analyzes an expression from a facial image using a three‐dimensional facial model and then extracts the facial expression.First, the head motion and the facial actions (such as those of eyebrows, eyes, and lips) are separated from the facial image. This is realized by estimating the three‐dimensional motion of the face based on the three‐dimensional facial model and by compensating the motion.Next, the expression information is extracted from the separated facial actions in two ways. One is the method to extract successively the facial expressions considering the characteristics of the facial actions based on the facial muscles. The other is the method to estimate the facial expression as a whole using the least‐square method and regarding the facial actions by the facial muscles as a vector. Those methods are combined with the expression synthesis rules. This makes it possible to reconstruct the original expression from the extracted facial expression parameters.Finally, the result of the analysis of the facial expression from the actual image is compared to the result of evaluation by a psychologist to demonstrate the usefulness of the proposed method. The image reconstructed from the result of analysis also is compared with the origina
ISSN:0882-1666
DOI:10.1002/scj.4690231202
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
3. |
Constructing hierarchies for incomplete frames |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 29-43
Takenao Ohkawa,
Kazuhiko Koizumi,
Noboru Babaguchi,
Yoshikazu Tezuka,
Preview
|
PDF (1188KB)
|
|
摘要:
AbstractA frame is characterized as the hierarchical description with the object as the unit. On the other hand, it is not always true that the information is obtained by an interview with an expert or by observation in a systematic form. Then the obtained frames are described independently. It is desirable to organize the frames systematically by generating the class hierarchy. However, the frame contains incomplete information, such as undefined or indefinite attribute,and the traditional classification techniques based on the conceptual clustering cannot handle such information.This paper proposes a method to generate the class frame and construct the hierarchy for the frames with mixed undefined and indefinite attributes. In the classification of the frames containing incomplete information, the proposed method considers the attribute values other than the attributes describing the incomplete information and constructs the hierarchy by classifying the frames to the class containing the most similar frame.The validity of the generated classes, the effectiveness of the expansion procedure for the hierarchical tree, the validity of the evaluation criterion for the quality of the hierarchical tree, and the estimation performance for the attribute value in the classification of the undefined attribute are examined.
ISSN:0882-1666
DOI:10.1002/scj.4690231203
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
4. |
Space interface device for artificial reality—SPIDAR |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 44-54
Makoto Sato,
Yukihiro Hirata,
Hiroshi Kawarada,
Preview
|
PDF (1010KB)
|
|
摘要:
AbstractTo realize the human interface which efficiently models a three‐dimensional shape on a computer, it is necessary to provide an environment in which the shape model can be manipulated directly as the actual three‐dimensional object. Such an environment is called the virtual work space. In the human manipulation of an object by hand, such sensations as visual, tactile (touch), and force are utilized unconsciously.To compose the virtual work space, it is important that the human be given such sensory information in an integrated way. Such information must totally be generated artificially by computer processing. Based on such an idea, this paper proposes anew a space interface device called SPIDAR, as the I/O device needed in composing the virtual work space. The device functions to derive the information concerning the finger position and to provide the force sense information to the finger tip.The virtual work space for generation and manipulation of the three‐dimensional shape is composed using SPIDAR. An experiment is conducted to examine the effect of the force sense on the direct manipulation of the three‐dimensional shape in the virtual work space, and the usefulness of the method is v
ISSN:0882-1666
DOI:10.1002/scj.4690231204
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
5. |
Adaptive laplacian‐gaussian filter method for edge detection and diameter estimation of coronary arteries on cineangiograms: Applications to phantom profiles |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 55-65
Takahiro Oie,
Shunsuke Sato,
Preview
|
PDF (807KB)
|
|
摘要:
AbstractRecently, the estimation of the vessel diameter and cross‐sectional area from the images of the coronary arteries has been considered, aiming at the quantitative diagnosis of the coronary artery stenoses. The edge detection of the vessel image is the clue to the estimation of the vessel diameter and the cross‐sectional area. However, no method has been established with a sufficient accuracy.This paper proposes an adaptive Laplacian‐Gaussian filter method for the accurate edge detection of the vessel image which is an improvement of the zero‐crossing method. By the proposed method, it is shown that the edge is detected at the position corresponding to the vessel radius if the image of the vessel retains a similar shape even if the vessel diameter changes. On the other hand, the similarity of the vessel image is not maintained if there exists a blur in the imaging system.It is shown also that the diameter can be estimated if the blur is represented by a Gaussian function. The blur of the imaging system is examined by a phantom experiment, and it is seen that the blur can be represented by the weighted sum of two Gaussian functions. Finally, it is shown that the proposed method can almost accurately extract the edge of the vessel image in such a case, and the vessel diameter can be estimated with a high a
ISSN:0882-1666
DOI:10.1002/scj.4690231205
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
6. |
Motion field estimation based on shading models |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 66-74
Naoki Mukawa,
Preview
|
PDF (1585KB)
|
|
摘要:
AbstractThis paper proposes a motion field estimation algorithm based on a shading model from image sequences. Existing motion field estimation algorithms do not render motion field of shaded objects with a sufficient degree of accuracy. A shading model is used to analyze the scene of shaded objects so that constraint on motion and shade can be well understood and exploited. The proposed algorithm has been implemented and tested against synthetic images. Test results indicate that this algorithm reduces the motion estimation error by about 50 percent compared to the existing algorithm. Furthermore, the new algorithm also outperforms the old ones when tested against real images derived from a TV camera.
ISSN:0882-1666
DOI:10.1002/scj.4690231206
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
7. |
Three‐dimensional helical‐scan computed tomography using cone‐beam projections |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 75-82
Hiroyuki Kudo,
Tsuneo Saito,
Preview
|
PDF (914KB)
|
|
摘要:
AbstractIn this paper, we propose an image reconstruction method and computed tomography (CT) equipment with high resolving power that generates three‐dimensional CT images at a high speed. In the proposed method, an X‐ray source that irradiates conical X‐rays and a two‐dimensional detector which consists of fan‐beam detector arrays stacked in the direction of the object's axis rotate continuously at the same time the bed carrying the object translates in the visual field. This method is called a helical scan because the object is fixed and the X‐rays move on a helix and the same measurement data are obtained. We have previously proposed a scanning method in which the X‐ray source moves on a helix [4, 6]. However, the physical implementation of the previous proposal was difficult because it was assumed that the X‐ray beam completely covers the object. In this paper, in order to solve this problem, the implementation of a helical scan is based on a practical model that combines continuous rotation of an X‐ray source and a two‐dimensional detector and translation of the object. We derive an approximate reconstruction method based on the convolution/back‐projection method for fan‐beam projections. We also perform simulation tests based on a model of the human head and demonstrate the effectiveness
ISSN:0882-1666
DOI:10.1002/scj.4690231207
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
8. |
Recognition of letters in lateral printed strings using a three‐layered BP model with feedback connections |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 83-92
Katsuji Imai,
Kazutoshi Gouhara,
Yoshiki Uchikawa,
Preview
|
PDF (649KB)
|
|
摘要:
AbstractAlthough there is a simple and fast method to separate and classify letters in lateral printed strings by regarding a valley of the projection of the original image as a gap of letters, this method cannot be applied to cases where adjacent letters are connected or large clutter is involved [1].This paper proposes a method which separates and recognizes each letter even in such cases as described in the foregoing, using a three‐layered BP model with feedback connections. The recognition experiments using the proposed method were carried out with lateral strings of five printed letters (capital A to E) binarized through a CCD camera. The results show that the method is superior to conventional methods when applied to a letter string recognition system used in the process of factory automatio
ISSN:0882-1666
DOI:10.1002/scj.4690231208
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
9. |
Advanced explanation capabilities for intelligent tutoring systems: The explanation structure model (EXSEL) |
|
Systems and Computers in Japan,
Volume 23,
Issue 12,
1992,
Page 93-107
Akihiro Kashihara,
Tsukasa Hirashima,
Jun'ichi Toyoda,
Yuichi Nakamura,
Preview
|
PDF (1239KB)
|
|
摘要:
AbstractThis paper introduces an advanced explanation capability for the intelligent tutoring system (ITS) to assist students in understanding objects such as electric circuits designed by humans. In general, an object can be explained in various ways. To advance the explanation capability, it is necessary to clarify how these explanations are used properly according to some tutoring goals in the domain. Moreover, the design of ITS based on such a capability requires: (1) classification of explanations based on the tutoring goals, and (2) development of a facility to generate the classified explanations.First, this paper defines object understanding by using two concepts, i.e., viewpoint and object model, and classifies explanations by regarding the defined object understanding as a tutoring goal.Next, the explanation facility, Explanation Structure model (EXSEL) is proposed. EXSEL has a mechanism to generate an explanation structure that is regarded as a resource of explanation and is designed in due consideration of being applied to ITS.The definition of object understanding, the classification of explanations and EXSEL are applicable to the objects explainable at three abstraction levels: structure, behavior, and function. Providing the mechanisms to operate EXSEL according to tutoring requisites such as the student's understanding, it is possible to realize various ITSs to support greatly object understanding.
ISSN:0882-1666
DOI:10.1002/scj.4690231209
出版商:Wiley Subscription Services, Inc., A Wiley Company
年代:1992
数据来源: WILEY
|
|