Here we propose a sentence-generation method using templates that can be applied to create a speech database. This method requires the recording of a relatively small sentence set, and the resultant speech database can generate comparatively natural sounding synthesized speech. Applying this method to the Japan Broadcasting Corporation (NHK) weather report radio program reduced the size of the required sentence set to just a fraction of that required by comparable methods. We also propose a speech-synthesis method using templates. In an evaluation test, 66% of the speech samples synthesized by the proposed method using templates were preferred to those produced by the conventional concatenative speech synthesis method.

This paper considers a novel error-correcting scheme exploiting chaotic dynamics for noncoherent chaos communication. In our proposed system, two successive chaotic sequences are generated from the same chaotic map; the second sequence is generated with an initial value which is the last value of the first sequence. In this case, successive chaotic sequences having the same chaotic dynamics are created. This feature gives the receiver additional information to correctly recover the information data and thus improves the bit error performance of the receiver. Further, enhanced efficiency also comes from operating on successively modulated data; by involving less redundancy in the error correction system, it can be designed with high coding rate. In this paper, we analyze the scheme's capability, by examining computational times and accuracy rates of error correction, bounds on its capability.

We propose a system that is capable of improving intelligibility of speech by those with hearing impairment. We have found the speech often had problems in the intonation, the duration of the unvoiced consonants, and the tone of the voiced phonemes. The system systematically compensates problematic components of the speech using the counterparts in normal speech. It corrects the intonation using TD-PSOLA and elongates consonants by repeating the original waveform using inverting technique for making the result continuously connected until the duration reaches a threshold. Experimental results show that the proposed method successfully improves the intelligibility of the speech from 28% to 35% by making phonemes more articulated, and making double consonants, ‘n’ of syllabic consonant, and unvoiced consonants perceived clearer.

This research introduces an automatic scoring mechanism based on motion analysis of a player by video image processing and database of skills in gymnastics. The automatic scoring system will be made for the horizontal bar which is one of the gymnastics in particular. A scoring result is equivalent to scoring until now according to experience of a referee and the rulebook, or in order to perform highly precise scoring, it does not use the standard of scoring only with defined performance figure or a text. It is the new approach of this research to describe them as a program to be the databases which analyzed them. The result of this research considers scoring of a referee as a correct answer. Thereby, evaluation of a system can be performed, and if the system performance is enough, it will be considered to be useful that it can use for evaluation of a referee etc.

We propose a method for synthesizing a "speaker mixture voice" that has both of two speakers' individualities. We define the "speaker mixture voice" as such that 50 percent of the subjects who listen to the voice would identify either speaker A or speaker B in ABX listening test that instructs them to identify the speaker. To synthesize the speaker mixture voice, we parameterize the spectrum envelope with respect to peaks and valleys, find the correspondence between two spectrum envelopes from independent speakers using DP matching, morph one to the other, and generate waveforms using TD-PSOLA. Listening experiments showed 60 percent out of 56 synthesized voices were recognized as the speaker mixture voices. The primary application of the proposed method would be individualization of the characters in online games where multiple users play a single character as separate individuals at the same time.

In this paper, we propose a system for automatic judgment of offsides in soccer games. We detect and track players in fixed multi camera images and calculate the world coordinates of them. Furthermore, we do a formation analysis by classifying uniforms and calculate the position of an offside line. On the other hand, we calculate the 3D coordinates and the trajectories of a ball in world coordinates from the plane coordinates of a ball in multi cameras and recognize the moment of a play from the 3D trajectories of a ball. In addition, we make a judge player's interfering with play by analyzing the spatial relationship between a ball and players. Finally, we make an offside judgment by integrating these results. We apply our system to a real soccer match and demonstrate the availability of this system by showing the experimental results

An efficient speech synthesis method that uses subspace constraint in prosody is proposed. Conventional unit selection methods concatenate speech segments stored in database, that require enormous number of waveforms in synthesizing various emotional expressions with arbitrary texts. The proposed method employs principal component analysis to reduce the dimensionality of prosodic components, that also allows us to generate new speech that are similar to training samples. The subspace constraint assures that the prosody of the synthesized speech including F0, power, and speech length hold their correlative relation that training samples of emotional speech have. We assume that the combination of the number of syllables and the accent type determines the correlative dynamics of prosody, for each of which we individually construct the subspace. The subspace is then linearly related to emotions by multiple regression analysis that are obtained by subjective evaluation for the training samples. Experimental results demonstrated that only 4 dimensions were sufficient for representing the prosodic changes due to emotion at over 90% of the total variance. Synthesized emotion were successfully recognized by the listeners of the synthesized speech, especially for "anger", "surprise", "disgust", 'sorrow", "boredom", "depression", and "joy"

We propose a method that uses the participants' head orientation and utterances for automatically identifying the addressee of each utterance in face-to-face multiparty conversations, such as meetings. First, each participant's head orientation is determined through vision-based detection and the presence/absence of utterances is extracted using the power of voices captured by microphones. Second, gaze direction (whom each participant is looking at) is estimated from just detected head orientation using the support vector machine. Third, several related features such as amount and frequency of gaze and eye contact are calculated in each utterance interval. Finally, a Bayesian Network is used to classify each utterance into one of two types of utterances: (a) the speaker is addressing a single participant and (b) the speaker is addressing all participants. Experiments on addressee estimation with 3-person conversations confirm the usefulness of our method

We present a new approach to estimating muscular contraction parameters for the purposes of animating facial expressions. In this paper, first, the facial surface feature points of face image are detected by using image processing methods. Next, the muscular contraction parameters are estimated by using the neutral expression and arbitrary expression displacement of the facial model wireframe fitting, based on detected facial surface feature points. Finally, the facial expression is generated by using the vertex displacements of an individual facial model based on estimated muscular contraction parameters. The facial animation can be generated by using the image sequences. Experimental results reveal that our approach can generate facial animation of the individual facial model, which corresponds to the facial expression of the actual face image sequences.

We propose an automatic pan control system for broadcasting ball games by tracking face direction of audience. Presuming that the audience's face is directed to a notable play, we can shoot a broadcasting video by controlling the camera toward the audience's face direction. In our method, a court sensor which detects rough region where players exist is used in addition to the face sensor in order to obtain higher accuracy. Based on these sensors, the broadcasting video is generated by cylindrical mosaicing off-line. We conducted objective and subjective evaluation experiments and the result shows that our approach is better than previously proposed methods in respect of stable tracking and easy watching. Conclusively our method is as effective as the optimum camerawork.

We propose a new human interface system, the virtual 3D interface system, which allows a user to work in a virtual three-dimensional (3D) space on the computer by way of hand motions and hand poses. This system has two cameras: one takes the top-view of the desktop and the other takes the side-view. With the top-view image, the system recognizes the bending of the five fingers and interprets the command. At the same time, the system extracts the fingertip of the forefinger in both the top-view and the side-view images, and then estimates the 3D position of the fingertip. These procedures are very simple so that we can develop some real-time 3D application systems.

We propose a method for reconstruction of the 3D shape of a book surface by integrating shape that is recovered from an image sequence taken with a moving camera. The image sequence is divided into a number of blocks. The factorization method is applied to each block for obtaining a part of the 3D shape of the object. The 3D shapes reconstructed from the block of the sequence are merged into one integrated 3D model. For the merging, position and pose of each 3D shape are adjusted based on the surface normal of the overlapped area. The merged 3D model of all regions of the book surface is shown for demonstrating the effectiveness of the proposed method.

We propose a method for estimation of the 3D shape of a non-convex object from an image sequence taken with the object rotating under a fixed light source. First, all the territory candidates of the object are prepared in voxel space. The empty voxels are selected by using cross-section estimation using a silhouette, that is the conventional method. However this method cannot reconstruct the non-convex object, because change isn't shown in the silhouette by the dents. Therefore, we remove part of the dents by using the cross-section estimation using occlusion and shading. For the cross-section estimation using occlusion, we apply a technique similar to the shape from silhouette. That is to say, the ray connects the point of view and occlusion to the tangent toward the front object of occlusion and removes the territory surrounded by the corresponding two tangents of the two neighboring views. For the cross-section estimation using shading, we decide the most suitable position of the surface point in the searched ray, which connects a point of view and the surface and on which the surface point is searched. To decide a suitable position, we examine a change in brightness of backward rays, which connect a voxel and each point of view. At each voxel on the searched ray, the most suitable position is where the degree of agreement with the bi-directional reflectance model is the highest. For demonstrating the effectiveness of the proposed method, we show the reconstructed image of non-convex objects, such as balls, or a doll and chair, which are successfully recovered.

The authors propose a novel human interface system, 3-D Drawing System, which allows a user to draw on virtual 3D space in a computer with a user's hand motions and hand poses. The system has two cameras; one camera takes a top-view of the desktop and another takes a side-view. The input image of the top camera is transformed into the distance-transformed image, which is used for deciding Palm Square that gives the base size, position, and direction of hand. The Palm Square determines Finger Windows which are used for detecting each finger's expansion that is decided by the number of pixels in the Finger Window. The user's command is input to the system by the finger's expansion. At the same time, we extract the fingertip and estimate the 3D position by comparison with the image obtained with the side camera. The procedures are very simple so we can develop the real time 3D drawing system, which allows the user to draw figures in 3D space, and handle 3D virtual objects.

Proposes a method for the reconstruction of a 3D shape with super-resolved texture of a book surface by integrating the shape that is recovered from an image sequence taken with a moving camera. The image sequence is divided into a number of blocks. A factorization method is applied to each block to obtain part of the 3D shape of the object. The 3D shapes reconstructed from the blocks of the sequence are merged into a single integrated 3D model. During this time, we generate a super-resolved texture using multiple images. For the merging, the position and pose of each 3D shape is adjusted based on the surface normal of the overlapped area. The merged 3D model of all regions of the book surface is shown to demonstrate the effectiveness of the proposed method. Furthermore, we generate a super-resolved texture that is finer than the original image using multiple images.

We propose an automatic evaluation system of human skin surface condition based on subjective evaluation provided by cosmeticians. In the proposed system, image features extracted on the skin image and subjective evaluation by cosmeticians are flexibly connected by using a backpropagation neural network, so that it can automatically estimate human skin surface condition based on subjective evaluation from various skin images. We show some experimental results. Using the trained neural network, human skin surface condition based on subjective evaluation is estimated for unlearned skin images. Then subjective evaluation by this system was compared with that by cosmeticians. Since the proposed system can successfully estimate human skin surface condition like cosmeticians, the effect of the system is demonstrated.

This paper describes a new system for extracting and classifying bibliography regions from the color image of a book cover. The system consists of three major components: preprocessing, color space segmentation and text region extraction and classification. Preprocessing extracts the edge lines of the book and geometrically corrects and segments the input image, into the parts of front cover, spine and back cover. The same as all color image processing researches, the segmentation of color space is an essential and important step here. Instead of RGB color space, HSI color space is used in this system. The color space is segmented into achromatic and chromatic regions first; and both the achromatic and chromatic regions are segmented further to complete the color space segmentation. Then text region extraction and classification follow. After detecting fundamental features (stroke width and local label width) text regions are determined. By comparing the text regions on front cover with those on spine, all extracted text regions are classified into suitable bibliography categories: author, title, publisher and other information, without applying OCR.

We propose a method in order to compensate contortion of page-image which is caused by photographing a book opened and placed face-up (two pages opposite each other state) on the stage just above. For compensating contortion 3-D shape information of the page surface is necessary to apply some geometrical adjustment. To obtain much higher resolution image a page needs to be photographed partly, in this situation each neighboring image necessarily has overlap area for the purpose of joining together. We put characters existing in an overlap area to good use for seeking of corresponding points in the stereo method by which 3-D shape information (3-D coordinate of corresponding points) of book surface can be obtained. If the assumption that no change of the shape of page cross section along the binding are satisfied, satisfactory compensated images were obtained and joining them together was well performed.

In this paper, we propose a new system for estimating face pose from a facial image. In this system, an input facial image is compared with a database of images of various face pose, then the matched image provides the face pose. The database of images includes not only various face poses but also various illumination conditions, so that the face pose estimation system can be used under various illumination conditions. For collecting such various facial images, they are generated by computer, rather than using real images. The eigenspace method is used for searching a matched image with an input facial image. Since various illumination images are collected in the database of facial images, the extracted principle eigenvectors mostly depend on the face pose. By performing the matching process in the eigenspace, a matched image with the input facial image can be found. The pose of the matched image is closest to the input face. The matching process is also fast because it is performed in small dimensional space spanned by selected eigenvectors only. The proposed pose estimation system can continuously track the face pose of different persons under different light conditions.

Intelligent transport systems (ITS) have been developed as next generation systems which unite multimedia technology and the roadway. One ITS technology, image processing, for example, the detection and tracking of moving objects (e.g. vehicles), is studied. On the other hand, the coding technique of MPEG (Motion Picture Experts Group) is used as the worldwide standard method of video data compression. Japan Highway Public Corporation (JH) adopted MPEG to transmit picture data from the surveillance system on the roadway to the control center. Therefore, we propose a method to analyze moving pictures by directly manipulating the MPEG stream. Our proposed method extracts plural moving objects from the MPEG stream without a decoding process, and tracks them even if they approach and cross. It is implemented to extract moving cars on the roadway, and its effectiveness is verified.

A divide-and-conquer strategy in shape from shading problem under fully perspective conditions is proposed for the information recovery of book surfaces. The whole recovery process is composed of three sequential steps: preprocessing, apparent shape recovery, and ortho-image generation. Pure shade images are extracted in the preprocessing step by introducing a phenomenological model of interreflection and by removing pigment parts from observed images. A recurrence relation is derived from the definition of mean slope in the discrete image. Theoretically, it becomes possible to recover unique shape without iteration using the derived equations in the case of a Lambertian cylinder. However, a feedback shape recovery process is implemented as a practical algorithm in order to overcome self-shadows. Results of simulations and real experiments show the properness and acceptability of the proposed strategy and implemented algorithms.

We propose a linear model of the relationship between the physical changes in speech and perceived emotional concepts. We make use of orthogonal bases in spite of the emotional words and the physical parameters themselves in order to avoid dependence on the method of selecting words and parameters. Furthermore we regard the emotions that listeners perceive from speech as the standard or emotional concepts because the emotions that speakers intended rely on their personality and temporary psychological state. Evaluation for relative information indicates that the proposed linear model is representable for the relationship between the physical quantities and psychological quantities in speech.

This work investigates a new approach to detect human face from monocular image sequences. Our method consists of two main search procedures, both using genetic algorithms. The first one is to find a head inside the scene and the second one is to identify the existence of face within the extracted head area. For this purpose, we have developed two models to be used as a tool to calculate the fitness for each observation in the search procedure: one is a head model which is approached by an ellipse and the other is a face template the size of which is adjustable. The procedures work sequentially. The head search is activated first, and after the head area is found, the face identification is activated. The experiment demonstrates the effectiveness of the method.

Road scene analysis from a perspective image plays a very important role in road navigation and road following. It seems, however, a formidable task if the road segments show as curves. In this paper we propose a method to perform an analysis of road segments containing both straight lines and curvatures. The method used is to investigate the features of the corresponding points between the road boundaries with the road modeled as planer surface patches. A constraint existing among Euler angles of viewpoint and the vanishing point related to corresponding points on the road plane is shown. To search for the corresponding points from the perspective image we define a function which by means of the Lagrange multiplier leads to a minimum at the corresponding points. Simulations are conducted on both a straight road segment and a curvature road boundary.

Chinese character structure data can be generated automatically. The authors propose an algorithm for the automated generation of the Chinese character structure data based on extracting stokes. As the inputs of Chinese characters, the Gothic styles are used. Examples are given throughout the text, using real images of Gothic style Chinese characters.>

A method is presented for the autonomous visual navigation of a vehicle by using a white guide for path recognition. The vehicle moves over a white guide line on the flat ground or floor, which is contrasted with its background. The vehicle uses a forward-looking TV camera for sensing. The white-line recognition algorithm presented uses a state transition algorithm. A field pattern monitoring method is also presented for vehicle guidance using a state transition scheme. When the vehicle comes to branches, it selects a suitable direction according to a path planner output. The vehicle can also avoid collisions with obstacles in front of it by monitoring the field patterns and their changes. An experimental moving vehicle system was constructed. Tests conforming the effectiveness of these approaches are described.>

Line Element Chain Coding (LECC) method, which orients two-dimensional structure descriptive coding, for two-level pictures is proposed. This method encodes direction, coordinate, length, width, and shape of segment. Shape is encoded by nine types of line element chain codes. Compression rate for CCITT's test charts, vector representation coding and progressive picture coding as application of this method are described.

This paper describes new ways to construct a rewritable programmable logic array (R-PLA) of current mode logic (CML) and to control READ/WRITE operations of the R-PLA. The R-PLA is constructed by splitting a conventional Random Access Memory (RAM) of CML into two parts. Therefore, each cell structure of the new R-PLA is identified with that of the conventional RAM, differing from a complicated cell structure proposed in the past. Because of the identification the comparison for the number of cells between the new R-PLA and the RAM becomes possible according to the historical discussions of the PLA and the memory. It will be demonstrated logically and electrically that SEARCH and READ parts of the new R-PLA can perform logic-in-memory without using special AND gates in each cell in the READ mode and can enter a WRITE data from a word direction in the WRITE mode.