Masahiro Iwahashi

Masahiro Iwahashi
Nagaoka University of Technology · Department of Electrical, Electronics and Information Engineering

PhD

About

236
Publications
24,025
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
1,524
Citations
Introduction
Skills and Expertise
Additional affiliations
April 1993 - present
Nagaoka University of Technology
Position
  • Professor (Full)

Publications

Publications (236)
Article
Full-text available
There are three primary objectives of this work; first: to establish a gas concentration map; second: to estimate the point of emission of the gas; and third: to generate a path from any location to the point of emission for UAVs or UGVs. A mountable array of MOX sensors was developed so that the angles and distances among the sensors, alongside se...
Article
Full-text available
Conventional methods for the early fusion of multi-modal features cannot recognize the relevant modality corresponding to the demand of each user in sequential recommendation. In this paper, we propose the adaptive multi-modal bidirectional long short-term memory network (AM-Bi-LSTM) to recognize the relevant modality for sequential recommendation....
Article
Full-text available
UAVs have been contributing substantially to multi-disciplinary research and around 70% of the articles have been published in just about the last five years, with an exponential increase. Primarily, while exploring the literature from the scientific databases for various aspects within the autonomous UAV path planning, such as type and configurati...
Article
Cross-modal retrieval with noisy labels has attracted much attention. This state-of-the-art method trains a network to increase weights for clean labels in the loss. However, we have found that the network is eventually overfitted to the remaining noisy labels as training progresses. Motivated by this finding, this paper proposes a method called La...
Article
Full-text available
Background Monitoring jar fermenter–cultured microorganisms in real time is important for controlling productivity of bioproducts in large-scale cultivation settings. Morphological data is used to understand the growth and fermentation states of these microorganisms during monitoring. Oleaginous yeasts are used for their high productivity of single...
Article
Full-text available
This article presents a method for trend clustering from tweets about coronavirus disease (COVID-19) to help us objectively review the past and make decisions about future countermeasures. We aim to avoid detecting usual trends based on seasonal events while detecting essential trends caused by the influence of COVID-19. To this aim, we regard dail...
Article
Full-text available
Tumblr is one of the most popular micro-blogging services worldwide on which users can share posts consisting of texts and images. This paper proposes a user-centric method of multimodal feature extraction for the personalized retrieval of Tumblr posts. To implement personalized retrieval, we formulate each user’s preferences as a triplet loss by u...
Article
Full-text available
In this paper, we propose an image adjustment method for multi-exposure images based on convolutional neural networks (CNNs). We call image regions without information due to saturation and object moving in multi-exposure images lacking areas in this paper. Lacking areas cause the ghosting artifact in fused images from sets of multi-exposure images...
Article
Full-text available
Abstract Electroencephalography (EEG) is a method for recording electrical activities arising from the cortical surface of the brain, which has found wide applications not just in clinical medicine, but also in neuroscience research and studies of Brain‐Computer Interface (BCI). However, EEG recordings often suffer from distortions due to artefactu...
Article
This article presents a method that detects tweet communities with similar topics and ranks the communities by importance measures . By identifying the tweet communities that have high importance measures, it is possible for users to easily find important information about the coronavirus disease (COVID-19). Specifically, we first construct a com...
Article
Full-text available
An image after tone mapping (TM) has noise bias, i.e., noise values with a non-zero mean, because of the non-linearity of the TM function. Therefore, noise reduction filters based on the zero-mean assumption do not work well for such images. To overcome this limitation, noise bias compensation (NBC) divides pixels into subsets depending on their va...
Article
Full-text available
Tumblr is a popular micro-blogging service on which users can share posts comprising text and images. This paper presents a method for personalizing post recommendations for each user from a large number of posts. Specifically, we develop a supervised multi-variational auto encoder considering user preference (SMVAE-UP). SMVAE-UP can extract relati...
Article
This paper develops a system to visually inspect cutlery based on a simple machine learning algorithm using image features that are robust against overexposure. First, we develop an image acquisition apparatus comprising a laser and a screen that produces speckle images of unique shapes depending on the degree to which the photographed cutlery has...
Article
Full-text available
This paper proposes a method for classifying the river state (a flood risk exists or not) from river surveillance camera images by combining patch-based processing and a convolutional neural network (CNN). Although CNN needs much training data, the number of river surveillance camera images is limited because flood does not frequently occur. Also,...
Article
We evaluated the reconstruction quality from a conventional compressed ultrafast photography (CUP) system and demonstrated a multi-directional high-speed imaging system based on the CUP system. We evaluated the defect rate as a function of the reconstruction quality. The results showed that the dependence of the defect rate on the reconstruction qu...
Article
Full-text available
In this paper, we introduce salient object detection with importance degree (SOD-ID), which is a generalized technique for salient object detection (SOD), and propose an SOD-ID method. We define SOD-ID as a technique that detects salient objects and estimates their importance degree values. Hence, it is more effective for some image applications th...
Article
The compressed ultrafast photography (CUP) method is used to observe ultrafast light emission phenomena by restoring multiple images from a single observed image via a compressed sensing algorithm. However, because its regularization function is only suitable for ultrafast light emissions with lattice contours, the CUP method frequently produces ar...
Article
Many measurement methods have been proposed for use in automated production. Existing methods for measuring three-dimensional surface height data operate by projecting fringe patterns onto a target object and capturing images of them. However, these methods do not work well for cutlery, such as table forks and spoons, because specular reflection ca...
Article
Full-text available
Recent studies have reported the success of linear prediction analysis (LPA)-related features, which are extracted as a short-term spectral feature for replay attack detection due to the advantage of the imperfection in the LPA-based signal produced by recording and playback devices. However, exploiting LPA-based signals is focused on only magnitud...
Article
We propose a two-layer coding method for HDR images with noise bias compensation (NBC). Although the mean of image noise is assumed to be zero originally, it becomes nonzero (that is, noise bias is present) after tone mapping, because of the nonlinearity of tone mapping. In the conventional two-layer coding, the reconstructed LDR image is decoded u...
Article
Full-text available
Although Twitter has become an important source of information, the number of accessible tweets is too large for users to easily find their desired information. To overcome this difficulty, a method for tweet clustering is proposed in this paper. Inspired by the reports that network representation is useful for multimedia content analysis including...
Article
Full-text available
There are many studies on detecting human speech from artificially generated speech and automatic speaker verification (ASV) that aim to detect and identify whether the given speech belongs to a given speaker. Recent studies demonstrate the success of the relative phase (RP) feature in speaker recognition/verification and the detection of synthesiz...
Conference Paper
Since the emergence of the Shor’s factoring algorithm, the research over Quantum Fourier Transform (QFT) has motivated the broad attention in the dilemma of the efficient quantum computation. For the purpose of exploring the sizable extent for their exponential growth and the massive computational steps, this paper confers the Field Programmable Ga...
Article
Full-text available
This paper introduces a zero-skip quantization (ZS.Q) scheme for the near lossless coding of sparse histogram images. Increases in the range of pixel values and various tone mapping operations on those pixel values mean that the histogram bins often contain no pixels. Recently, this sparseness of the histogram was used to increase the lossless codi...
Article
Full-text available
A large number of studies have been made on denoising of a digital noisy image. In regression filters, a convolution kernel was determined based on the spatial distance or the photometric distance. In non-local mean (NLM) filters, pixel-wise calculation of the distance was replaced with patch-wise one. Later on, NLM filters have been developed to b...
Article
Full-text available
Enhancing reverberant speech with Deep Neural Networks (DNNs) is an interesting yet challenging topic. The performance of speech enhancement degrades significantly when test and training conditions are mismatched. In this paper we propose a Static Reverberation Aware Training (SRAT)-based dereverberation through which the reverberation estimate is...
Article
In this paper, we propose a method of salient object detection based on distributed seeds and a co-propagation of seed information. Salient object detection is a technique which estimates important objects for human by calculating saliency values of pixels. Previous salient object detection methods often produce incorrect saliency values near salie...
Article
Full-text available
The wavelet transform (WT)-based JPEG 2000 is a standard for the compression of digital images that uses a separable lifting structure in which a multidimensional image signal is transformed separately along its horizontal and vertical dimensions. A non-separable three-dimensional (3D) structure is used to minimize the number of lifting steps in ex...
Article
Full-text available
Various somatic stem cells divide asymmetrically; however, it is not known whether embryonic stem cells (ESCs) divide symmetrically or asymmetrically, not only while maintaining an undifferentiated state, but also at the onset of differentiation. Here, we observed single ESCs using time-lapse imaging, and compared sister cell pairs derived from the...
Article
In this paper, we propose a 2-layer lossless coding method for high dynamic range (HDR) images based on range compression and adaptive inverse tone-mapping. Recently, HDR images, which have a wider range of luminance than conventional low dynamic range (LDR) ones, have been frequently used in various fields. Since commonly used devices cannot yet d...
Article
Full-text available
Recently, deep neural network (DNN)-based feature enhancement has been proposed for many speech applications. DNN-enhanced features have achieved higher performance than raw features. However, phase information is discarded during most conventional DNN training. In this paper, we propose a DNN-based joint phase- and magnitude -based feature (JPMF)...
Article
Brain electrical activity recordings by electroencephalography (EEG) are often contaminated with signal artifacts. Procedures for automated removal of EEG artifacts are frequently sought for clinical diagnostics and brain computer interface (BCI) applications. In recent years, a combination of independent component analysis (ICA) and discrete wavel...
Article
Since few decades ago, Discrete Cosine Transform (DCT) based digital image signal compression had been adopted as the JPEG international standard. Later, Wavelet Transform (WT) has replaced the DCT and its being applied in medical image compression. JPEG 2000, the international standardization of WT is using separable lifting structure where the mu...
Conference Paper
We propose a fusion method for high dynamic range (HDR) imaging based on the estimated camera response function (CRF) and fused gradients from input multi-exposure images. We introduce an objective function consisting of data fidelity and gradient-based constraint functions, and HDR images are produced via minimizing it. These functions are respect...
Conference Paper
We propose an estimation method of initial labels based on scale-invariant feature transform (SIFT), high dimensional color transform (HDCT), and machine learning for propagation-based saliency detection. The label propagation strategy is efficient for saliency detection, but its accuracy depends on the distribution of initial labels. In this paper...
Article
A number of successful tone mapping operators (TMOs) for contrast compression have been proposed due to the need to visualize high dynamic range (HDR) images on low dynamic range devices. This paper proposes a novel inverse tone mapping (TM) operation and a new remapping framework with the operation. Existing inverse TM operations require either th...
Article
Ever since the international standard JPEG 2000 based on the lifting wavelet transform was adopted as a core technology of the digital cinema applications, its implementation issues have been discussed from various respects such as memory band width, low latency, high throughput, parallel processing and so on. Unlike the separable two-dimensional (...
Conference Paper
This paper proposes a fixed-point local tone mapping operation (TMO) for high dynamic range (HDR) images. A TMO is classified in two types: local and global. Although a local TMO offers better results than global one, it requires more resources such as a computational cost and memory space. The proposed method uses fixed-point arithmetic with short...
Thesis
Full-text available
群論の手芸への展開
Thesis
Full-text available
手芸で壁紙群を実現する ~群論の手芸への展開(全53ページ) 放送大学卒業論文, 2016
Article
The lifting wavelet transform (WT) has been widely applied to image coding. Recently, the total number of lifting steps has been minimized introducing a non-separable 2D structure so that delay from input to output can be reduced in parallel processing. However the minimum lifting WT has a problem that its upper bound of the rate-distortion curve i...
Article
As three dimensional (3D) discrete wavelet transform (DWT) is widely used for high resolution volumetric data compression, and to further improve the performance of lossless coding, the adaptive directional lifting (ADL) structure based on non-separable 3D DWT with a (5,3) filter is proposed in this paper. The proposed 3D DWT has less lifting steps...
Article
Full-text available
This paper is focused on a practice that has been widely noted in South Asia, i.e. employing extra-local methods to assess community resilience with no or minimal attempts on localising. The objective of this paper is to assess the consistency/inconsistency and concordance/discordance of resilience levels computed by different extra-local assessmen...
Article
This letter considers a unified tone mapping operation (TMO) for HDR images. The unified TMO can perform tone mapping for various HDR image formats with a single common operation. The integer TMO which can realize unified tone mapping by converting an input HDR image into an intermediate format is proposed. This method can be executed efficiently w...
Conference Paper
Full-text available
This paper introduces a noise bias compensation (NBC) to a two layer backward compatible high dynamic range (HDR) image coding to decrease data volume of the compressed data. In this system, dynamic range of the input HDR image is reduced with tone mapping (TM) to generate a low dynamic range (LDR) image. It is encoded to generate a bit stream in t...
Conference Paper
Full-text available
This paper introduces a noise bias compensation to a tone mapped noisy image so that the variance of the noise is reduced. Although the noise bias is assumed to be zero before tone mapping (TM), it becomes non-zero value after TM. The reason includes some factors such as the non-linearity of TM and the asymmetry of the probability density function...
Conference Paper
Full-text available
An integer transform is used in lossless-lossy coding since it can reconstruct an input signal without any loss at output of the backward transform. Recently, its number of lifting steps is reduced as well as delay from input to output introducing multi-dimensional memory accessing. However it has a problem that quality of the reconstructed signal...
Article
Full-text available
In this paper, we propose a bit-depth scalable lossless coding method for high dynamic range (HDR) images based on a reversible logarithmic mapping. HDR images are generally expressed as floating-point data, such as in the OpenEXR or RGBE formats. Our bit-depth scalable coding approach outputs base layer data and enhancement layer data. It can reco...
Article
Full-text available
Deep neural network (DNN)-based approaches have been shown to be effective in many automatic speech recognition systems. However, few works have focused on DNNs for distant-talking speaker recognition. In this study, a bottleneck feature derived from a DNN and a cepstral domain denoising autoencoder (DAE)-based dereverberation are presented for dis...
Conference Paper
This paper proposes a new class of near-lossless (NL) coding, which enables to estimate the l∞ bound specified in the first coding. This estimation is needed when a new l∞ bound is specified again in the second coding. However, so far, the conventional studies on NL coding have not taken account of this issue for re-encoding, but they have focused...
Conference Paper
This paper considers a unified tone mapping operation (TMO) for HDR images. This paper includes not only floating-point data but also long-integer (i.e. longer than 8-bit) data as HDR image expression. A TMO generates a low dynamic range (LDR) image from a high dynamic range (HDR) image by compressing its dynamic range. A unified TMO can perform to...
Article
Recently, automatic accent recognition has been paid more and more attentions. However, there are few researches focusing on accent recognition in distant-talking environment which is very important for improving distant-talking speech recognition performance with non-native accents. In this paper, we apply Gaussian Mixture Models (GMM) and Deep Ne...