Underwater images are actively utilized for ocean observation and various applications related to marine science. They, however, suffer from image quality degradation due to underwater imaging which impedes in-depth image analysis. While deep models are effectively applied to correct degraded images, underwater image enhancement (UIE) specifically poses two issues regarding severe color distortion and scarce training data. To cope with those two issues, we propose a novel framework of multi-channel enhanced Glow, dubbed as MC-Glow, which effectively harnesses a deep model to enhance underwater images. Our deep model built upon invertible Glow structure is equipped with a multi-channel processing for resolving severe color degradation. In contrast to standard processing of full colors, the multi-channel branch encodes RGB colors separately to suppress interference among distorted color channels. Besides, we explore the possibility of leveraging the white balance dataset for pre-training the deep model. The pre-training dataset is composed of easy-to-access photos unlike underwater images and endows the model with effective image enhancement by mitigating scarcity of underwater images. Experimental results on UIE tasks using two benchmark datasets demonstrate that the proposed MC-Glow produces competitive performance with the other UIE approaches. Code is available at https://github.com/tkswalk/2025_Signal-Processing/tree/main .

A non-negative matrix factorization (NMF) is effectively applied to analyze data in an unsupervised way. Though non-negative factors are endowed with favorable interpretability, such as part-based representation, NMF lacks flexibility, being only applicable to data composed of non-negative values. In this paper, we propose a novel approach to enhance both flexibility and interpretability of matrix factorization. While NMF approximates a matrix in an additive form of non-negative factors, the proposed method disentangles the matrix into additive and subtractive parts by exploiting non-negative factors with a center factor akin to the average of data. Thereby, the disentanglement flexibly deals with any real-valued data beyond non-negative ones while rendering clear functionality to the factors. In the experiments on several factorization tasks using real-world data, the proposed method provides effective factorization to embed well interpretability especially into factors for analyzing intrinsic characteristics of the data.

Non-negative matrix factorization (NMF) is widely applied to analyze pattern data in an unsupervised manner. It imposes hard non-negativity constraints on factors to extract intrinsic characteristics from an input matrix, though demanding complicated optimization techniques which hinder the general applicability. Toward flexible formulation, we propose weakly non-negative factorization. In contrast to the strict non-negative approach, our method permits factors to contain small amount of negative values. The relaxation theoretically leads to an efficient factorization formulation which can be implemented by means of off-the-shelf techniques used in a deep learning literature. Thus, the method is flexibly applicable to versatile factorization tasks, such as deep NMF and structured NMF. In the experiments on the NMF-related tasks, we demonstrate that the weak non-negativity produces effective factors similarly to NMF and the method exhibits favorable performance in comparison to the other approaches.

Semantic segmentation is an object classification such as a perceptual grouping in image analysis tasks. And semantic segmentation methods have been proposed to improve the pixel-wise classification accuracies in the research field of computer vision. Recently, the methods achieve high accuracies by using convolutional neural networks (CNN). These CNN-based methods generally need large number and variety of training images to assure a generalization performance without fine tuning. However, it is difficult to prepare the large-scale image datasets which were given reliable semantic labels. In order to overcome this problem, we propose an efficient method for feature transformation to improve the generalization performance in semantic segmentation. Our method is formulated as a variant of neighborhood preserving embedding (NPE) incorporating the within-class coherency and showed best generalization performances compared with other feature transformation methods.

Object re-identification techniques are essential to improve the identification performance in video surveillance tasks. The re-identification problem is equal to a multi-view problem that an unknown individual is identified across spatially disjoint data. For the re-identification techniques, several multi-view feature transformation methods have been proposed. These methods are formulated by the supervised learning framework and show the better performances in multi-view classification tasks in which the training data are observed by the different sensors. However, in the reidentification tasks, these methods may not be required because the simple feature transformation method such as linear discriminant analysis (LDA) shows the reasonable identification rates. In this paper, we propose a novel semi supervised feature transformation method, which is formulated as a natural coupling with PCA and LDA modeled by the graph embedding framework. Our method showed best re-identification performances compared with other feature transformation methods.

We have developed a real-time vital signs monitoring system for two years in 2012 and 2013. Just by putting a single vital sensor node to the back waist position of each player and placing four data collection nodes around a field, the system can monitor at a note PC heart rate (HR), energy expenditure (EE) and body temperature (BT) for all players during a football game in real-time, periodically and reliably. The system is based on novel vital sensing technique and wireless data transmission technique. This paper introduces the two techniques in the system, presents some problems encountered in the system development and discusses solutions for them.

Discriminating feature extraction is important to achieve high recognition rate in a classification problem. Fisher's linear discriminant analysis (LDA) is one of the well-known discriminating feature extraction methods and is closely related to the Mahalanobis distance metric learning. Neighborhood component analysis (NCA) is one of the Mahalanobis distance metric learning methods based on stochastic nearest neighbor assignment. The objective function of NCA can be expressed as a within-class coherency by a simple formula, and NCA extracts discriminating features by minimizing the objective function. Unfortunately, the computational cost of NCA significantly increases as the number of input data increases. For reducing the computational cost, we propose a fast distance metric learning method by taking the between-class distinguish ability into account of nearest mean classification. According to the experimental results using standard repository datasets, the computational time of our method is evaluated as 27 times shorter than that of NCA while keeping or improving the accuracy.

In order to plan effective training menus and avoid injuries and diseases, vital signs monitoring for athletes during training and game is essential, where a key issue is how to collect vital data reliably and in real-time from many people spread in a large field. To realize such a real-time vital data monitoring system, we developed prototype wireless vital sensor nodes, and conducted twice field experiments to evaluate the packet success rate (PSR), where we put the sensor nodes to the waists of 22 players and collected packets from all of them during a football game. In this paper, we present the detail of the real-time vital data collection system composed of the prototype sensor nodes and data collection nodes, and discuss the experimental results in terms of PSR and diversity gain.

Linear discriminant analysis (LDA) is a well-known method to extract efficient features for multi-class classification. Otsu derived the optimal (ultimate) non-linear discriminant analysis (ONDA) by supposing underlying probabilities and showed that ONDA was closely related to Bayesian decision theory (posterior probabilities). Also Otsu pointed out that the usual LDA could be regarded as the linear approximation of this ultimate ONDA through the linear approximations of the Bayesian posterior probabilities. This theory of ONDA suggests that we can construct a novel nonlinear discriminant mapping by utilizing the estimates of the posterior probabilities. Based on this theory, logistic discriminant analysis (LgDA) was proposed by one of the authors as the approximation of ONDA. In LgDA, the posterior probabilities are estimated by logistic regression. In this paper, we propose the sparse logistic discriminant analysis in which the posterior probabilities are estimated by the sparse logistic regression with L2-or L1-regularizer to improve the generalization performance of LgDA further. Experiments using the standard datasets for classification reveal that the discriminant spaces by our proposed method (LgDA-L2 and LgDA-L1) are better than those by LDA and LgDA in terms of the recognition rates for test samples.

In biology, peptide ion detection from mass spectra is important for identifying proteins. Many methods have been proposed for detecting peptide ion peaks, some of which use wavelet transform. In these methods, however, the co-occurrence pattern of peptide ions and those isotopes is not directly considered. In this paper, we propose a novel method for detecting peptide ion peaks from a mass spectrum by using a weighted auto-correlation. The weight functions derived from Maxwell-Boltzmann distribution and the sine function are introduced to the proposed auto correlations to effectively represent the peptide ion co-occurrence patterns. The multi-scaled auto-correlation features extracted with those weight functions are compressed by using principal component analysis. Experiments on raw mass spectra show that the proposed method achieves the favorable performances and is capable of automatically detecting peptide ion peaks.

In the cancer detection from stained biopsy images, it is important to extract histologically discriminative characteristics. For this purpose, we propose a novel method to extract statistical and morphological features. At the first stage, we estimate cell component memberships at each pixel by applying an expectation maximization (EM) algorithm to the color information. Next we calculate the local co-occurrence of the memberships as image features. And then, linear discriminant analysis (LDA) is applied to those features for final decision of whether cancer or not, with enhancing the discrimination. In the experiments on real biopsy images of cancers, the resulting detection accuracy is superior to the other methods.

Linear discriminant analysis (LDA) is one of the well known methods to extract the best features for the multi-class discrimination. Otsu derived the optimal nonlinear discriminant analysis (ONDA) by assuming the underlying probabilities and showed that the ONDA was closely related to Bayesian decision theory (the posterior probabilities). Also Otsu pointed out that LDA could be regarded as a linear approximation of the ONDA through the linear approximations of the Bayesian posterior probabilities. Based on this theory, we propose a novel nonlinear discriminant analysis named logistic discriminant analysis (LgDA) in which the posterior probabilities are estimated by multi-nominal logistic regression (MLR). The experimental results are shown by comparing the discriminant spaces constructed by LgDA and LDA for the standard repository datasets.

In this paper, we propose a novel algorithm of multi-nominal logistic regression in which the locality regularization term is introduced. The locality is defined by the neighborhood information of the data set and is preserved in the mapped feature space. By using the standard benchmark datasets, it was shown that the proposed algorithm gave higher recognition rates than the linear SVM in binary classification problems. The recognition rates for multi-class classification problem were also better than the general multi-nominal logistic regression.

Support Vector Machines (SVMs), though accurate, are still difficult to solve large-scale applications, due to the computational and storage requirement. To relieve this problem, we propose RANSAC-SVM method, which trains a number of small SVMs for randomly selected subsets of training set, while tuning their parameters to fit SVMs to whole training set. RANSAC-SVM achieves good generalization performance, which close to the Bayesian estimation, with small subset of the training samples, and outperforms the full SVM solution in some condition.

We propose an automatic factorization method for time series signals that follow Boltzmann distribution. Generally time series signals are fitted by using a model function for each sample. To analyze many samples automatically, we have to apply a factorization method. When the energy dynamics are measured in thermal equilibrium, the energy distribution can be modeled by Boltzmann distribution law. The measured signals are factorized as the non-negative sum of the probability density function of Boltzmann distribution. If these signals are composed from several components, then they can be decomposed by using the idea of non-negative matrix factorization (NMF). In this paper, we modify the original NMF to introduce the probability density function modeled by Boltzmann distribution. Also the number of components in samples is estimated by using model selection method. We applied our proposed method to actual data that was measured by fluorescence correlation spectroscopy (FCS). The experimental results show that our method can automatically factorize the signals into the correct components.

The purpose of this study was to investigate the effects of international virtual learning classes. For the purpose, the class implemented using multipoint communication system which was constructed high quality video transfer systems on a cross-border infrastructure (gigabit bandwidth) between Japan to South Korea. In order to reveal the effects of the class, a questionnaire was composed of five categories; consciousness to foreign countries, nationality, acquisition of view point, motivation, recognition to the partner country. The results of 2 /spl times/ 2 mixed two-way ANOVA showed differences of characteristics of two countries and changes of student's attitude. The results revealed that an international virtual learning class has a possibility to develop and enhance student's awareness of humanity and the world. Future implementation will depend on growth and sustenance of the international relationship for a prolonged period.

This paper reports on an image processing algorithm and hardware for fast, precise inspection of LSI wafer patterns. In order to detect deep sub-micron defects such as 0.2 /spl mu/m at high speed by grayscale image comparison, we must overcome the sampling errors that inevitably occur between two images during detection. For this purpose, we have developed a subpixel image alignment algorithm that infers the correct sampling position and creates the two resampled images with subpixel accuracy. We have also developed an 8-channel pipelined processor with gate arrays. It has 8/spl times/19,000 gates and can operate at 8/spl times/15 MHz. Evaluation of the system confirmed that the accuracy of the subpixel image alignment was 0.16 pixels or less and that the inspection system could detect 0.18 /spl mu/m defects at a pixel size of 0.25 /spl mu/m for half-micron LSI wafer patterns with an inspection speed of 25 s/cm/sup 2/.>