This paper describes a method of generating F0 contours from natural F0 segmental shapes for speech synthesis. The extracted shapes of the F0 units are basically held invariant by eliminating any averaging operations in the analysis phase and by minimizing modification operations in the synthesis phase. The use of natural F0 shapes has great potential to cover a wide variety of speaking styles with the same framework, including not only read-aloud speech, but also dialogues and emotional speech. A linear-regression statistical model is used to "manipulate" the stored raw F0 shapes to build them up into a sentential F0 contour. Through experimental evaluations, the proposed model is shown to provide stable and robust F0 contour prediction for various speakers. By using this model, linguistically derived information about a sentence can be directly mapped, in a purely data-driven manner, to acoustic F0 values of the sentential intonation contour for a given target speaker.

The enlargement of the left lobe of the liver and the shrinkage of the right lobe are helpful signs at MR imaging in diagnosis of cirrhosis of the liver. To investigate whether the volume ratio of left-to-whole (LTW) is effective to differentiate cirrhosis from a normal liver, we developed an automatic algorithm for three-dimensional (3D) segmentation and volume calculation of the liver region in multi-detector row CT scans and MR imaging. From one manually selected slice that contains a large liver area, two edge operators are applied to obtain the initial liver area, from which the mean gray value is calculated as threshold value in order to eliminate the connected organs or tissues. The final contour is re-confirmed by using thresholding technique. The liver region in the next slice is generated by referring to the result from the last slice. After continuous procedure of this segmentation on each slice, the 3D liver is reconstructed from all the extracted slices and the surface image can be displayed from different view points by using the volume rendering technique. The liver is then separated into the left and the right lobe by drawing an inter-segmental plane manually, and the volume in each part is calculated slice by slice. The degree of cirrhosis can be defined as the ratio of volume in these two lobes. Four cases including normal and cirrhotic liver with MR and CT slices are used for 3D segmentation and visualization. The volume ratio of LTW was relatively higher in cirrhosis than in the normal cases in both MR and CT cases. The average error rate on liver segmentation was within 5.6% after employing in 30 MR cases. These results demonstrate that the performance in our 3D segmentation was satisfied and the LTW ratio may be effective to differentiate cirrhosis.

In this paper, we proposed the novel method for the recognition of English calling cards by using the contour tracking algorithm and the enhanced fuzzy RBF (Radial Basis Function) neural networks. The recognition of calling cards consists of the extraction phase of character areas and the recognition phase of extracted characters. In the extraction phase, first of all, noises are removed from the images of calling cards, and the feature areas including character strings are separated from the calling card images by using the horizontal smearing method and the 8-directional contour tracking method. And using the image projection method the feature areas are split into the areas of individual characters. We also proposed the enhanced fuzzy RBF neural network that organizes the middle layer effectively by using the enhanced fuzzy ART neural network adjusting the vigilance parameter dynamically according to the similarity between patterns. In the recognition phase, the proposed fuzzy neural network was applied to recognize individual characters. Our experiment result showed that the proposed recognition algorithm has higher success rate of recognition and faster learning time than the conventional RBF network based recognitions.

This paper proposes a noise robust speech recognition method using prosodic information. In Japanese, the fundamental frequency (F0) contour represents phrase intonation and word accent information. Consequently, it conveys information about prosodic phrases and word boundaries. This paper first describes a noise robust F0 extraction method using the Hough transform, which achieves high extraction rates under various noise environments. Then it proposes a robust speech recognition method using multi-stream HMMs which model both segmental spectral and F0 contour information. Speaker-independent experiments are conducted using connected digits uttered by 11 male speakers in various kinds of noise and SNR conditions. The recognition error rate is reduced in all noise conditions, and the best absolute improvement of digit accuracy is about 4.5%. This improvement is achieved by robust digit boundary detection using the prosodic information.

The artifacts of low-bit rate quantization in images cannot be removed satisfactorily by known methods. We propose decomposition of images as HSI and LSI (higher- and lower- significance images), followed by subsampling and reconstruction methods for LSI. Experiments show significant improvement in image quality, as compared to other methods.

The model for the process of F0 contour generation, first proposed by Fujisaki and his coworkers, has been successfully applied to Standard Chinese, which is a typical tone language with a distinct feature that both positive and negative tone commands are required. However, the inverse problem, viz., automatic derivation of the model parameters from an observed F0 contour of speech, cannot be solved analytically. Moreover, the extraction of model parameters for Standard Chinese is more difficult than for Japanese and English, because the polarity of tone commands cannot be inferred directly from the F0 contour itself. In this paper, an efficient method is proposed to solve the problem by using information on syllable timing and tone labels. With the same framework as for the successive approximation method proposed for Japanese and English, the method presented here for Standard Chinese is focused on the first-order estimation of tone command parameters. A set of intra-syllable and inter-syllable rules are constructed to recognize the tone command patterns within each syllable. The experiment shows that the method works effectively and gives results comparable to those obtained by manual analysis.

Image segmentation is an essential technique of image analysis. In spite of the issues in contour initialization and boundary concavities, active contour models (snakes) are popular and successful methods for segmentation. In this paper, we present a new active contour model, Gaussian Gradient Force snake (GGF snake), for segmentation of an endoscopic image. The GGF snake is less sensitive to contour initialization and it ensures a high accuracy, large capture range, and fast CPU time for computing an external force. It was observed that the GGF snake produced more reasonable results in various image types : simple synthetic images, commercial digital camera images, and endoscopic images, than previous snakes did.

In this paper, a novel description method of the contour of a shape using extended fractal interpolation functions (EFIFs) is presented. Although the scope of application of traditional FIFs has been limited to cases in which a given signal is represented by a single-valued function, the EFIFs derived by the introduction of a new parameter can describe a multiple-valued signal such as the contour of a shape with a high level of accuracy. Furthermore, the proposed description method possesses the useful property that once a given contour has been modeled by the proposed description method, the shape can be easily expanded at an arbitrary expansion rate. Experimental results show the effectiveness and usefulness of the proposed description method for representing contours.

In the past decade, significant effort has been made toward increasing the accuracy and robustness of three-dimensional scanning methods. In this paper, we present a new prototype vision system named 3D Model Studio, which has been built to reconstruct a complete 3D model in as less as a few minutes. New schemes for a probe calibration and a 3D data merging (axis consolidation) are employed. We also propose a new semi-automatic contour registration method to generate accurate contour model from 3D data points, along with a contour triangulation based surface reconstruction. Experimental result shows that our system works well for reconstructing a complete 3D surface model of a human body.

We propose a new method to precisely detect pupil contours in face images. Pupil contour detection is necessary for various applications using face images. It is, however, difficult to detect pupils precisely because of their weak edges or lack of edges. The proposed method is based on minimizing the energy of pattern and edge. The basic idea of this method is that the energy, which consists of the pattern and the edge energy, has to be minimized. An efficient search method is also introduced to overcome the underlying problem of efficiency in energy minimization methods. "Guide patterns" are introduced for this purpose. Moreover, to detect pupils more precisely we use an ellipse model as pupil shape in this paper. Experimental results show the effectiveness of the proposed method.

A new method for computing precise estimates of the motion vectors of moving objects in a sequence of images is proposed. The proposed method is based on dynamic programming matching applied along chain-coded binary contours of images. This significantly reduces the computational complexity of the correspondence matching applied to the 2-D optimization problem. Computer simulation and experimental results demonstrate a good performance of the method in terms of dynamic motion analysis.

We introduce a crystalline flow for a contour figure analysis. The crystalline flow is a special family of evolving polygons, and is considered as a discrete version of a classical curvature flow. In the evolving process of the crystalline flow, each facet moves toward its normal direction. The velocity of the facet is determined by the nonlocal curvature, which depends on the length of the facet. Different from a classical curvature flow, it is easy to track each facet in a given contour through the evolving process, because a given polygon remains polygonal. This aspect helps us to make a scale-space representation of a contour in an image. In this article, we present a method for extracting dominant corners using a crystalline flow. Experimental results show that our method extracts several sets of dominant corner facets successfully from a given contour figure.

A new multi-luminance-level subfield method is proposed to reduce the low gray-level contour of an alternate current plasma display panel (AC-PDP). The minimum or maximum luminance level per sustain-cycle can be altered by simultaneously applying the proper auxiliary short pulses. As a result, the multi-luminance levels per one or two sustain pulse pairs can be expressed by properly adjusting the auxiliary short pulses for the one or two sustain-cycle subfields, thereby suppressing a low gray-level contour of AC-PDP.

This paper deals with contour extraction of fetus' head from echocardiogram and its application to diagnosis in obstetrics. Active contour model "SNAKES" is modified and used for contour extraction. After contour extraction we automatically obtained the biparietal diameter (BPD) and the occipitofrontal diameter (OFD) from the contour.

We present a method to track and recognize shape-changing hand gestures simultaneously. The switching linear model using active contour model well corresponds to temporal shapes and motions of hands. However, inference in the switching linear model is computationally intractable, and therefore the learning process cannot be performed via the exact EM (Expectation Maximization) algorithm. Thus, we present an approximate EM algorithm using a collapsing method in which some Gaussians are merged into a single Gaussian. Tracking is performed through the forward algorithm based on Kalman filtering and the collapsing method. We also present a regularized smoothing, which plays a role of reducing jump changes between the training sequences of shape vectors representing complex-variable hand shapes. The recognition process is performed by the selection of a model with the maximum likelihood from some trained models while tracking is being performed. Experiments for several shape-changing hand gestures are demonstrated.

A plasma display panel (PDP) represents gray levels by the pulse number modulation technique that results in undesirable dynamic false contours on moving images. Among the various techniques proposed for the reduction of dynamic false contours, the optimization of the subfield pattern can be most easily implemented without the need for any additional dedicated hardware or software. In this paper, a systematic method for selecting the optimum subfield pattern is presented. In the proposed method, a subfield pattern that minimizes the quantitative measure of the dynamic false contour on the predefined test image is selected as the optimum pattern. The selection is made by repetitive calculations based on a genetic algorithm. Quantitative measure of the dynamic false contour calculated by simulation on the test image serves as a criterion for minimization by the genetic algorithm. In order to utilize the genetic algorithm, a structure of a string is proposed to satisfy the requirements for the subfield pattern. Also, three genetic operators for optimization, reproduction, crossover, and mutation, are specially designed for the selection of the optimum subfield pattern.

This paper describes a new method for detection and tracking of moving objects from a moving camera image sequence using robust estimation and active contour models. We assume that the apparent background motion between two consecutive image frames can be approximated by affine transformation. In order to register the static background, we estimate affine transformation parameters using LMedS (Least Median of Squares) method which is a kind of robust estimator. Split-and-merge contour models are employed for tracking multiple moving objects. Image energy of contour models is defined based on the image which is obtained by subtracting the previous frame transformed with estimated affine parameters from the current frame. We have implemented the method on an image processing system which consists of DSP boards for real-time tracking of moving objects from a moving camera image sequence.

This paper considers the problem of generating various calligraphy from some sample fonts. Our method is based on the deformable contour model g-snake. By representing the outline of each stroke of a character with a g-snake, we cast the generation problem into global and local deformation of g-snake under different control parameters, where the local deformation obeys the energy minimization principle of regularization technique. The base values of the control parameters are learned from given sample fonts. The experimental results on alphabet and Japanese characters Hiragana show such processing as a reasonable method for generating calligraphy.

A discrete dynamic model for defining contours in 2-D medical images is presented. An active contour in this objective is optimized by a dynamic programming algorithm, for which a new constraint that has fast and stable properties is introduced. The internal energy of the model depends on local behavior of the contour, while the external energy is derived from image features. The algorithm is able to rapidly detect convex and concave objects even when the image quality is poor.

In this paper a new snake model for image morphing with semiautomated delineation which depends on Hermite's interpolation theory, is presented. The snake model will be used to specify the correspondence between features in two given images. It allows a user to extract a contour that defines a facial feature such as the lips, mouth, and profile, by only specifying the endpoints of the contour around the feature which we wish to define. We assume that the user can specify the endpoints of a curve around the features that serve as the extremities of a contour. The proposed method automatically computes the image information around these endpoints which provides the boundary conditions. Then the contour is optimized by taking this information into account near its extremities. During the iterative optimization process, the image forces are turned on progressively from the contour extremities toward the center to define the exact position of the feature. The proposed algorithm helps the user to easily define the exact position of a feature. It may also reduce the time required to establish the features of an image.