Yasuyuki SUGAYA Kenichi KANATANI
Many techniques have been proposed for segmenting feature point trajectories tracked through a video sequence into independent motions, but objects in the scene are usually assumed to undergo general 3-D motions. As a result, the segmentation accuracy considerably deteriorates in realistic video sequences in which object motions are nearly degenerate. In this paper, we propose a multi-stage unsupervised learning scheme first assuming degenerate motions and then assuming general 3-D motions and show by simulated and real video experiments that the segmentation accuracy significantly improves without compromising the accuracy for general 3-D motions.
Shouji SAKAMOTO Youichi KOBUCHI
To elucidate the mechanism of topographic organization, we propose a simple topographic mapping formation model from generalized cell layer to generalized cell layer. Here generalized cell layer means that we consider arbitrary cell neighborhood relations. In our previous work we investigated a topographic mapping formation model between one dimensional cell layers. In this paper we extend the cell layer structure to any dimension. In our model, each cell takes a binary state value and we consider a class of learning principles which are extensions of Hebb's rule and Anti-Hebb's rule. We pay special attention to correlation type learning rules where a synaptic weight value is increased if pre and post synaptic cell states have the same value. We first show that a mapping is stable with respect to the correlational learning if and only if it is semi-embedding. Second, we introduce a special class of weight matrices called band type and show that the set of band type weight matrices is strongly closed and such a weight matrix can not yield a topographic mapping. Third, we show by computer simulations that a mapping, if it is defined by a non band type weight matrix, converges to a topographic mapping under the correlational learning rules.
This paper surveys recent progress in the investigation of the underlying discrete proximity structures of geometric clustering with respect to the divergence in information geometry. Geometric clustering with respect to the divergence provides powerful unsupervised learning algorithms, and can be applied to classifying and obtaining generalizations of complex objects represented in the feature space. The proximity relation, defined by the Voronoi diagram by the divergence, plays an important role in the design and analysis of such algorithms.
Hideki NODA Mehdi N. SHIRAZI Bing ZHANG Nobuteru TAKAO Eiji KAWAGUCHI
This paper proposes a Markov random field (MRF) model-based method for unsupervised segmentation of multispectral images consisting of multiple textures. To model such textured images, a hierarchical MRF is used with two layers, the first layer representing an unobservable region image and the second layer representing multiple textures which cover each region. This method uses the Expectation and Maximization (EM) method for model parameter estimation, where in order to overcome the well-noticed computational problem in the expectation step, we approximate the Baum function using mean-field-based decomposition of a posteriori probability. Given provisionally estimated parameters at each iteration in the EM method, a provisional segmentation is carried out using local a posteriori probability (LAP) of each pixel's region label, which is derived by mean-field-based decomposition of a posteriori probability of the whole region image. Experiments show that the use of LAPs is essential to perform a good image segmentation.
Hsuen-Chyun SHYU Chin-Chi CHANG Yueh-Jyun LEE Ching-Hai LEE
A structure of neural network suitable for clustering and deinterleaving radar pulses is proposed. The proposed structure consists of two networks, one for intrinsic features of pluses and the other for PRIs (pulse repetition intervals). The unsupervised learning method which adjusts the number of nodes for clusters adaptively is adopted for these two networks to learn patterns. These two networks are connected by a set of links. According to the weights of these links, the clusters categorized by the network for features can be refined further by merging or partitioning. The main defect of the unsupervised network with an adaptive number of nodes for clusters is that the result of classification closely depends on the learning sequence of patterns. This defect can be improved by the proposed refinement algorithm. In addition to the proposed structure and learning algorithms, simulation results have also been discussed.
Yasunage MIYAZAWA Jun-ichi TAKAMI Shigeki SAGAYAMA Shoichi MATSUNAGA
This paper proposes an unsupervised speaker adaptation method using an all-phoneme ergodic Hidden Markov Network" that combines allophonic (context-dependent phone) acoustic models with stochastic language constraints. Hidden Markov Network (HMnet) for allophone modeling and allophonic bigram probabilities derived from a large text database are combined to yield a single large ergodic HMM which represents arbitrary speech signals in a particular language so that the model parameters can be re-estimated using text-unknown speech samples with the Baum-Welch algorithm. When combined with the Vector Field Smoothing (VFS) technique, unsupervised speaker adaptation can be effectively performed. This method experimentally gave better performances compared with our previous unsupervised adaptation method which used conventional phonetic HMMs and phoneme bigram probabilities especially when the amount of training data was small.