Browsing by Author "Fu, HC"

Now showing 1 - 20 of 28

A fully automated web-based TV-News system
(2004)
Lai, PS
;
Lai, LY
;
Tseng, TC
;
Chen, YH
;
Fu, HC
This paper proposes a web-based multimedia TV-News system, which can records and analyzes news video to generate hierarchy news contents automatically. To achieve this goal, various neural network based techniques, including image processing, audio processing, and optical characters recognition are applied. Since July 2003, the multimedia TV-News system has been implemented and continuously been up running at http://nn.csie.nctu.edu.tw/TVNews/intro.htm for general public browsing and studying.
A model-selection-based self-splitting Gaussian mixture learning with application to speaker identification
(2004-12-15)
Cheng, SS
;
Wang, HM
;
Fu, HC
;
資訊工程學系
;
Department of Computer Science
We propose a self-splitting Gaussian mixture learning (SGML) algorithm for Gaussian mixture modelling. The SGML algorithm is deterministic and is able to find an appropriate number of components of the Gaussian mixture model (GMM) based on a self-splitting validity measure, Bayesian information criterion (BIC). It starts with a single component in the feature space and splits adaptively during the learning process until the most appropriate number of components is found. The SGML algorithm also performs well in learning the GMM with a given component number. In our experiments on clustering of a synthetic data set and the text-independent speaker identification task, we have observed the ability of the SGML for model-based clustering and automatically determining the model complexity of the speaker GMMs for speaker identification.
A neural network based transcoder for MPEG2 video compression
(1999)
Fu, HC
;
Chen, ZH
;
Xu, YY
;
Wang, CH
;
資訊工程學系
In this paper, we proposed a neural network method for the high efficiency requatization in the design of a transcoder In our design, there are two types of video bitrate control in the proposed transcoder. One is the global adjusting of quantizer scales in which the adjusting is based on the complication of the whole frame, the other is the adaptive adjusting of quantizer scales, that the adjusting is the complication of the current macroblock. From our experimental results, the prototype transcoder can achieve desirable bitrate (1.5 Mbps) with an acceptable image quality. In additional, we constructed a video multiplexer for PPV or NVOD applications on the proposed transcoder.
A neural network for the automatic diagnosis of the telephone switching systems
(1995)
Fu, HC
;
Tung, WL
;
Shen, LJ
;
資訊工程學系
;
Department of Computer Science
A principal component based BDNN for face recognition
(1997)
Shen, LJ
;
Fu, HC
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
In this paper we propose a high performance two-stage hybrid structure for face recognition. The first stage is an eigenface based recognizer, which serves as a candidate faces selector. As our experience, the Top 1 recognition rate is only 65%, however the Top 10 hit rate can be up to 98.15%. The Top 10 candidate faces are similar to each other, thus these faces are called simial faces. Since the projections of tile similar faces are too close in the eigenspace, it's very hard to distinguish a target face from similar face set. Thus, we propose the ''Horizontal Average Gray Scale (HAGS)'' as a new type of feature for the second stage recognizer. A paired-Bayesian-decision neural network (pBDNN) is used for the second stage recognizer, which identifies the target from the similar faces. Supporting by the proposed feature, a pDBNN could make an accurate classification between any two similar faces. In order to demonstrate the proposed hybrid system, we conducted some experiments on an in house database, which contains 675 images taken from 135 people. The training data for the pBDNN were small orientation (-22.5 degrees, 0 degrees, 22.5 degrees), and the large orientation (-45 degrees and 45 degrees) images were for testing. Our experimental results show that the hybrid recognition structure improvs the recognition rate for 17% more than the eigenface system alone (65%) without any rejection, and 26% more with 31% of rejection.
A principal component based probabilistic DBNN for face recognition
(1996)
Shen, LJ
;
Fu, HC
;
Xu, YY
;
Hsu, FR
;
Chang, HT
A Self-growing Probabilistic decision-based neural network for anchor/speaker identification
(2003)
Chen, YH
;
Tseng, CL
;
Fu, HC
;
Pao, HT
;
資訊工程學系
In this paper, we propose a new clustering algorithm for a mixture Gaussian based neural network, called Self-growing Probabilistic decision-based neural networks (SPDNN). The proposed Self-growing cluster learning (SGCL) algorithm is able to find the natural number of prototypes based on a self-growing validity measure, Bayesian Information Criterion (BIC). The learning process starts with a single prototype randomly initialized in the feature space and grows adaptively during the learning process until most appropriate number of prototypes are found. We have conduct numerical and real world experiments to demostrate the effectiveness of the SGCL algorithm. In the results of using SGCL to trainin the SPDNN for anchor/speaker identification, we have observed noticeable improvement among various model-based or vector quantization-based classification schemes.
A self-growing probabilistic decision-based neural network with automatic data clustering
(2004-10-01)
Tseng, CL
;
Chen, YH
;
Xu, YY
;
Pao, HT
;
Fu, HC
In this paper, we propose a new clustering algorithm for a mixture of Gaussian-based neural network and self-growing probabilistic decision-based neural networks (SPDNN). The proposed self-growing cluster learning (SGCL) algorithm is able to find the natural number of prototypes based on a self-growing validity measure, Bayesian information criterion (BIC). The learning process starts from a single prototype randomly initialized in the feature space and grows adaptively during the learning process until most appropriate number of prototypes are found. We have conducted numerical and real-world experiments to demonstrate the effectiveness of the SGCL algorithm. In the results of using SGCL to train the SPDNN for data clustering and speaker identification problems, we have observed a noticeable improvement among various model-based or vector quantization-based classification schemes. (C) 2004 Elsevier B.V. All rights reserved.
A WWW-based intelligent multimedia information query and retrieve system
(2000)
Xu, YY
;
Fu, HC
;
Pao, HT
;
資訊工程學系
;
Department of Computer Science
In this paper, we propose and implement a World Wide Web based video query system: the intelligent Multimedia Information Processing System (IMIPS). The IMIPS first collects videos available over the WWW, analyzes these videos to extract keyframes, and indexes these keyframes at a local database. By using the proposed Multiple-Instance learning algorithm, a user can select a few keyframes to train a desired image query model. When a query model is selected, the proposed IMIPS will retrieve marched images from the local database, and display them as a small icon at the user interface. Then a user can click on the interested icon to retrieve and to play the video from the original web site. According to the implemented prototype system, a user can find one's desired videos on the WWW with only a few (2-3) times of retraining to achieve 70% hit rate on 50 retrieved videos among 5 different query models.
Adaptive watermarking using relationships between wavelet coefficients
(2005)
Chen, YH
;
Su, JM
;
Fu, HC
;
Huang, HC
;
Pao, HT
In this paper, we propose an approach that hides watermarks in relationships between wavelet coefficients. This approach would minimize the perceptual distortion of watermarked images, measured with PSNR or just noticeable distortion (JND). Therefore, the strength of watermarks can be enlarged to increase the robustness of the watermarks, while keeping the quality of watermarked images visually accepted. Experimental results show that the watermark is still detectable after common image processing operations such as JPEG compression, Gaussian filtering and sharpening.
Automated information. mining on multimedia TV news archives
(2005)
Lai, PS
;
Cheng, SS
;
Sun, SY
;
Huang, TY
;
Su, JM
This paper addresses an integrated information mining techniques for multimedia TV-news archive. The utilizes techniques from the fields of acoustic, image, and video analysis, for information retrieval on news story title, newsman and scene identification. The goal is to construct a compact yet meaningful abstraction of broadcast news video, allowing users to browse through large amounts of data in a non-linear fashion with flexibility and efficiency. By using acoustic analysis, the system can classify video into news versus commercials, with 90% accuracy on a data set of 400 hours TV-news recorded off the air from July 2003 to August of 2004. By applying speaker identification and/or image detection techniques, each news stories can be segmented with an accuracy of 96%. On screen captions or subtitles are recognized by OCR techniques to produce the text title of each news stories. The extracted title words can be used to link or to navigate more related News contents on the WWW. In cooperation with facial and scene analysis and recognition techniques, OCR results can provide users with multimodality query for specific news stories. Some experimental results are presented and discussed for the system reliability and performance evaluation and comparison.
Cascade-CMAC neural network applications on the color scanner to printer calibration
(1997)
Huang, KL
;
Hsieh, SC
;
Fu, HC
;
交大名義發表
;
光電工程學系
This paper presents an application of using a Cascade-CMAC (Cerebellar Model Articulation Controller) neural network to solve some color calibration problems, which include color differences induced from gamuts mis-match and the non-linear transformation characteristics between color scanning input devices and color printing output devices. For this purpose, we proposed a scalable learning architecture ''Cascade-CMAC'' to implement an adaptive color calibration system. By analyzing the preliminary learning situation, the scalable architecture can dynamically create a new learning unit to better represent a finer color resolution, so that the learning capacity as well as the color details of the system can be greatly improved. From the experimental results, the proposed Cascade-CMAC architecture can improve the rate of convergence and also can adjust the learning architecture effectively. The learning speed can be 2 similar to 4 times faster than the conventional CMAC. The effectiveness of this neural network has been tested by observing the differences between the calibrated and the un-calibrated output on a number of known samples. By using Macbeth Color-Checker which contains 24 color ptaches as benchmark, tile average color differences between the original and the calibrated print-out is improved from 15 Delta E-ab to 8 Delta E-ab under the 3 Delta E-ab convergent criterion for training. The calibration performance is somewhat significant.
Cluster-based support vector machines in text-independent speaker identification
(2004)
Sun, SY
;
Tseng, CL
;
Chen, YH
;
Chuang, SC
;
Fu, HC
Based on Statistical learning theory, Support Vector Machines(SVM) is a powerful tool for various classification problems, such as pattern recognition and speaker identification etc. However, Training SVM consumes large memory and long computing time. This paper proposes a cluster-based learning methodology to reduce training time and the memory size for SVM. By using k-means based clustering technique, training data at boundary of each cluster were selected for SVM learning. We also applied this technique to text-independent speaker identification problems. Without deteriorating recognition performance, the training data and time can be reduced up to 75% and 87.5% respectively.
Divide-and-conquer learning and modular perceptron networks
(2001-03-01)
Fu, HC
;
Lee, YP
;
Chiang, CC
;
Pao, HT
;
資訊工程學系
A novel modular perceptron network (MPN) and divide-and-conquer learning (DCL) schemes for the design of modular neural networks are proposed, When a training process in a multilayer perceptron fails into a local minimum or stalls in a flat region, the proposed DCL scheme is applied to divide the current training data region (e.g,, a hard to be learned training set) into two easier (hopely) to be learned regions. The learning process continues when a self-growing perceptron network and its initial weight estimation are constructed for one of the newly partitioned regions, Another partitioned region will resume the training process on the original perceptron network. Data region partitioning, weight estimating and learning are iteratively repeated until all the training data are completely learned by the MPN We have evaluated and compared the proposed MPN with several representative neural networks on the two-spirals problem and real-world dataset, The MPN achieves better weight learning performance by requiring much less data presentations (99.01% similar to 87.86% lesser) during the network training phases, and better generalization performance (4.0% better), and less processing time (2.0% similar to 81.3% lesser) during the retrieving phase, On learning the real-world data, the MPN's show less overfitting compared to single MLP. In addition, due to its self-growing and fast local learning characteristics, the modular network (MPN) can easily adapt to on-line and/or incremental Learning requirements for a rapid changing environment.
Face detection and eye localization by neural network based color segmentation
(2000)
Fu, HC
;
Lai, PS
;
Lou, RS
;
Pao, HT
;
資訊工程學系
This paper presents a neural network based scheme for human face detection and eye localization in color images under non-constrained scene. A Self-growing Probabilistic Decision-based Neural Network (SPDNN) is used to learn the conditional distribution for each color classes. Pixels of a color image are first classified into facial or non-facial regions, then pixels in the facial region are followed by eye region segmentation. The class of each pixel is determined by using the conditional distribution of the chrominance components of pixels belonging to each class. The paper demonstrates a successful application of SPDNN to face detection and eye localization on a database of 755 images from 151 persons. Regarding the performance, experimental results are elaborated in Section 3. As to the processing speed, the face detection and eye localization processes consume approximately 560 ms on a Pentium-II personal computer.
Forecasting electricity market prices: A neural network based approach
(2004)
Xu, YY
;
Hsieh, R
;
Lu, Y
;
Shen, YC
;
Chuang, SC
This paper presents a neural network approach to forecast the Phelix Base (PB) electricity market prices for European Energy Exchange (EEX). Up to now there has been little scientific work on forecasting the price development on the electricity markets. In this study, the Phelix Base moving average (PBMA), the moving difference (PBMD), and multilayer feedforward neural networks (MLNN) are used to predict various period for 7, 14, 21, 28, 63, 91, 182, and 273 days ahead of electric prices. The experimental results of forecasting by MLNNs and linear methods (autoregressive error model) are compared and discussed. The MLNNs outperform from 11.4% to 64.6% superior to the traditional linear regression method. It seems that the proposed MLNN can be very useful in predicting the electricity market prices of EEX.
Multi-linguistic handwritten character recognition by Bayesian decision-based neural networks
(1997)
Fu, HC
;
Xu, YY
;
交大名義發表
;
資訊工程學系
;
National Chiao Tung University
This paper proposes a multi-linguistic handwritten characters recognition system based on Bayesian decision-based neural networks (BDNN). The proposed system consists of two modules: First, a coarse classifier determines an input character to one of the pre-defined subclasses partitioned from a large character set, such as Chinese mixed with alphanumerics. Then a character recognizer determines the input image to its most matched reference character in the subclass. The proposed BDNN can be effectively applied to implement all these modules. It adopts a hierarchical network structures with nonlinear basis functions and a competitive credit-assignment scheme. Our prototype system demonstrates a successful utilization of BDNN to handwriting of Chinese and alphanumeric character recognition on both the public databases (HCCR/CCL for Chinese and CEDAR for the alphanumerics) and in house database (NCTU/NNL). Regarding the performance, experiments on three different databases all demonstrated high recognition (88 similar to 92%) accuracies as well as low rejection/acceptance (6.7%) rates, as elaborated in Section 3.2. As to the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27second/character on a Pentium-90 based personal computer, without using hardware accelerator or co-processor.
Multilinguistic handwritten character recognition by Bayesian decision-based neural networks
(1998-10-01)
Fu, HC
;
Xu, YY
;
資訊工程學系
;
Department of Computer Science
In this paper, we present a Bayesian decision-based neural network (BDNN) for multilinguistic handwritten character recognition, The proposed self-growing probabilistic decision-based neural network (SPDNN) adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme, Our prototype system demonstrates a successful utilization of SPDNN to the handwriting of Chinese and alphanumeric character recognition on both public databases (CCL/HCCR1 for Chinese and CEDAR for the alphanumerics) and in-house database (NCTU/NNL), Regarding the performance, experiments on three different databases all demonstrated high recognition (86-94%) accuracy as well as low rejection/acceptance (6.7%) rates. As for the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27 s/character on a Pentium-100 based personal computer, without using a hardware accelerator or coprocessor.
Multilinguistic handwritten character recognition by Bayesian decision-based neural networks
(1998-10-01)
Fu, HC
;
Xu, YY
;
資訊工程學系
;
Department of Computer Science
In this paper, we present a Bayesian decision-based neural network (BDNN) for multilinguistic handwritten character recognition, The proposed self-growing probabilistic decision-based neural network (SPDNN) adopts a hierarchical network structure with nonlinear basis functions and a competitive credit-assignment scheme, Our prototype system demonstrates a successful utilization of SPDNN to the handwriting of Chinese and alphanumeric character recognition on both public databases (CCL/HCCR1 for Chinese and CEDAR for the alphanumerics) and in-house database (NCTU/NNL), Regarding the performance, experiments on three different databases all demonstrated high recognition (86-94%) accuracy as well as low rejection/acceptance (6.7%) rates. As for the processing speed, the whole recognition process (including image preprocessing, feature extraction, and recognition) consumes approximately 0.27 s/character on a Pentium-100 based personal computer, without using a hardware accelerator or coprocessor.
Multimedia TV news browsing system
(2004)
Xu, YY
;
Chen, YH
;
Tseng, CL
;
Lai, PS
;
Fu, HC
In this demo, we present a system we have developed for automatic broadcast-quality video indexing that successfully combines results from the fields of speaker verification, acoustic analysis, very large vocabulary caption character recognition, content based sampling of video, information retrieval, dialogue systems, and ASF media delivery over IP. The prototype system of this demo is available at http://nn.csie.nctu.edu.tw/Project1-1/intruduction.htm.