This paper used ultrasound technology to examine the plain and palatalized taps in Japanese. Six participants of Japanese produced nonsense words containing /ɾ/ and /ɾ/. The mid-sagittal contours were compared in three intervocalic contexts: a_a, o_o, u_u. The results showed that /ɾ/ had a great deal of variability around the tongue dorsum. This suggests that /ɾ/ lacks a dorsal gesture; unlike ...

Parametric correspondence is a technique for matching images to a three dimensional symbolic reference map. An analytic camera model is used to predict the location and appearance of landmarks in the image, generating a projection for an assumed viewpoint. Correspondence is achieved by adjusting the parameters of the camera model until the appearances of the landmarks optimally match a symbolic...

3D scanners, iso-surface extraction procedures, and several recent geometric compression schemes sample surfaces of 3D shapes in a regular fashion, without any attempt to align the samples with the sharp edges and corners of the original shape. Consequently, the interpolating triangle meshes chamfer these sharp features and thus exhibit significant errors. The new Edge-Sharpener filter introduc...

This paper presents a technique for planar image mosiacing where a series of ordered and partial overlapping images are combined into one large image in a one-by-one sequence. Hierarchical chamfer matching algorithm (HCMA) is used in image alignment to find the best matching position from edge feature in multi-resolution pyramid. Unlike many mosaicing software packages, this technique needs no ...

Matching is a central problem in image analysis and pattern recognition. In order to develop a matching algorithm that provides the optimal fit (i.e. “center-on” fit attempting to position the model points at equal spacing from the target image) between the model and distorted target images, a hierarchical modified Chamfer matching system with the simulated annealing is proposed in this paper. ...

This paper introduces a novel approach to facial expression recognition in video sequences. Low cost contour features are introduced to effectively describe the salient features of the face. Temporalboost is used to build classifiers which allow temporal information to be utilized for more robust recognition. Weak classifiers are formed by assembling edge fragments with chamfer scores. Detectio...

We present a method for nonrigid registration of 2-D geometric shapes. Our contribution is twofold. First, we extend the classic chamfer-matching energy to a variational functional. Secondly, we introduce a meshless deformation model that can adapt computation to the shape boundary. In our method, 2-D shapes are implicitly represented by a distance transform, and the registration error is defin...