Takashi Takahashi

Takashi Takahashi
Ryukoku University · Department of Applied Mathematics and Informatics

Ph.D.

About

17
Publications
1,713
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
155
Citations

Publications

Publications (17)
Article
Full-text available
There are two major approaches to content-based image retrieval using local image descriptors. One is descriptor-by-descriptor matching and the other is based on comparison of global image representation that describes the set of local descriptors of each image. In large-scale problems, the latter is preferred due to its smaller memory requirements...
Article
Full-text available
This paper introduces a novel method for image classification using local feature descriptors. The method utilizes linear subspaces of local descriptors for characterizing their distribution and extracting image features. The extracted features are transformed into more discriminative features by the linear discriminant analysis and employed for re...
Conference Paper
Full-text available
Recently, kernel Principal Component Analysis is becoming a popular technique for feature extraction. It enables us to extract nonlinear features and therefore performs as a powerful preprocessing step for classification. There is one drawback, however, that extracted feature components are sensitive to outliers contained in data. This is a charact...
Article
This paper proposes a viewpoint invariant face recognition method in which several viewpoint dependent classifiers are combined by a gating network. The gating network is designed as autoencoder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different views. B...
Article
This paper describes an approach for constructing a classifier which is unaffected by occlusions in images. We propose a method for integrating an auto-associative network into a simple classifier. As the auto-associative network can recall the original image from a partly occluded input image, we can employ it to detect occluded regions and comple...
Conference Paper
Full-text available
The paper describes how to improve the robustness to occlusions in face recognition and detection. We propose a neural network architecture which integrates an auto-associative neural network into a simple classifier. The auto-associative network is employed to recall the original face from a partially occluded face image and to detect the occluded...
Conference Paper
Full-text available
This paper proposes a neural network classifier which can automatically detect the occluded regions in the given image and replace that regions with estimated values. An auto-associative memory is used to detect outliers, such as pixels in the occluded regions. Certainties of each pixels are estimated by comparing the input pixels with the outputs...
Article
Full-text available
We investigate a method to navigate a mobile robot by using self-organizing map and reinforcement learning. Modeling hippocampal place cells, the map consists of units activated at specified locations in an environment. In order to adapt the map to a realworld environment, preferred locations of these units are self-organized by Kohonen's algorithm...
Conference Paper
Full-text available
We investigate a self-organizing network model to account for the computational property of the inferotemporal cortex. The network can learn sparse codes for given data with organizing their topographic mapping. Simulation experiments are performed using real face images composed of different individuals at different viewing directions, and the res...
Conference Paper
Full-text available
We investigate methods to reconstruct the optical flow generated by camera rotation using autoassociative learning. A multi-layer perceptron is trained to reduce the dimensionality of flow data which are obtained from real image sequences while the camera is rotating against static scenes. After this learning, the perceptron is able to produce reco...
Conference Paper
Full-text available
This paper proposes a viewpoint invariant face recognition method in which several viewpoint de- pendent classifiers are combined by a gating net- work. The gating network is designed as autoen- coder with competitive hidden units. The viewpoint dependent representations of faces can be obtained by this autoencoder from many faces with different vi...
Conference Paper
Full-text available
We investigate an energy function for MLP called superposed energy. Applying to autoassociative learning of a sandglass-type MLP, it can adaptively adjust the effective number of the bottleneck-layer units to the intrinsic dimensionality of nonlinear data, and the optimal dimensionality reduced representation can be extracted after learning.
Article
Local iterated function system (LIFS) image coding is currently a main topic of fractal image coding and is being studied from various points of view. However, its performance is still inferior to conventional schemes such as JPEG. This paper proposes a novel local transformation called extended condensation and reports that the LIFS coding scheme...
Conference Paper
Full-text available
This paper investigates two simple energy functions which are valid for two different purposes of dimensionality reduction: feature extraction and data compression. These energy functions enable nonlinear perceptrons to organize data representations whose parameters, namely, outputs of the bottleneck layer units, are arranged in the order of their...
Article
A self-organizing neural network model of spatio-temporal visual receptive fields is proposed. It consists of a one-layer linear learning network with multiple temporal input channels, and each temporal channel has different impulse response. Every weight of the learning network is modified according to a Hebb-type learning algorithm proposed by Sa...
Article
筑波大学博士 (工学) 学位論文・平成11年3月25日授与 (甲第2123号) 本論文では、ニューラルネットワークによる情報圧縮を研究対象とする。ここでいう情報圧縮とは、複数個の多次元データから成るデータ集合が与えられたときに、その本質的な情報・特徴をできる限り失うことなくデータの数 ... http://www.tulips.tsukuba.ac.jp/limedio/dlam/B14/B1459435/1.pdf

Network

Cited By

Projects

Project (1)