著者
Takashi TOMITA Shigeki HAGIHARA Masaya SHIMAKAWA Naoki YONEZAKI
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.10, pp.1665-1677, 2022-10-01

This paper focuses on verification for reactive system specifications. A reactive system is an open system that continuously interacts with an uncontrollable external environment, and it must often be highly safe and reliable. However, realizability checking for a given specification is very costly, so we need effective methods to detect and analyze defects in unrealizable specifications to refine them efficiently. We introduce a systematic characterization on necessary conditions of realizability. This characterization is based on quantifications for inputs and outputs in early and late behaviors and reveals four essential aspects of realizability: exhaustivity, strategizability, preservability and stability. Additionally, the characterization derives new necessary conditions, which enable us to classify unrealizable specifications systematically and hierarchically.
著者
Seung-Tak NOH Hiroki HARADA Xi YANG Tsukasa FUKUSATO Takeo IGARASHI
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105.D, no.10, pp.1704-1711, 2022-10-01 (Released:2022-10-01)
参考文献数
17
被引用文献数
1

It is important to consider curvature properties around the control points to produce natural-looking results in the vector illustration. C2 interpolating splines satisfy point interpolation with local support. Unfortunately, they cannot control the sharpness of the segment because it utilizes trigonometric function as blending function that has no degree of freedom. In this paper, we alternate the definition of C2 interpolating splines in both interpolation curve and blending function. For the interpolation curve, we adopt a rational Bézier curve that enables the user to tune the shape of curve around the control point. For the blending function, we generalize the weighting scheme of C2 interpolating splines and replace the trigonometric weight to our novel hyperbolic blending function. By extending this basic definition, we can also handle exact non-C2 features, such as cusps and fillets, without losing generality. In our experiment, we provide both quantitative and qualitative comparisons to existing parametric curve models and discuss the difference among them.
著者
Yuichiro TATEIWA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.9, pp.1557-1567, 2022-09-01

We consider network security exercises where students construct virtual networks with User-mode Linux (UML) virtual machines and then execute attack and defense activities on these networks. In an older version of the exercise system, the students accessed the desktop screens of the remote servers running UMLs with Windows applications and then built networks by executing UML commands. However, performing the exercises remotely (e.g., due to the COVID-19 pandemic) resulted in difficulties due to factors such as the dependency of the work environment on specific operating systems, narrow-band networks, as well as issues in providing support for configuring UMLs. In this paper, a novel web-based hands-on system with intuitive and seamless operability and lightweight responsiveness is proposed in order to allow performing the considered exercises while avoiding the mentioned shortcomings. The system provides web pages for editing device layouts and cable connections by mouse operations intuitively, web pages connecting to UML terminals, and web pages for operating X clients running on UMLs. We carried out experiments for evaluating the proposed system on the usability, system performance, and quality of experience. The subjects offered positive assessments on the operability and no negative assessments on the responsiveness. As for command inputs in terminals, the response time was shorter and the traffic was much smaller in comparison with the older system. Furthermore, the exercises using nano required at least 16 kbps bandwidth and ones using wireshark required at least 2048 kbps bandwidth.
著者
Kento MATSUMOTO Sunao HARA Masanobu ABE
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.9, pp.1581-1589, 2022-09-01
被引用文献数
1

In this paper, we propose a new algorithm to generate Speech-like Emotional Sound (SES). Emotional expressions may be the most important factor in human communication, and speech is one of the most useful means of expressing emotions. Although speech generally conveys both emotional and linguistic information, we have undertaken the challenge of generating sounds that convey emotional information alone. We call the generated sounds “speech-like,” because the sounds do not contain any linguistic information. SES can provide another way to generate emotional response in human-computer interaction systems. To generate “speech-like” sound, we propose employing WaveNet as a sound generator conditioned only by emotional IDs. This concept is quite different from the WaveNet Vocoder, which synthesizes speech using spectrum information as an auxiliary feature. The biggest advantage of our approach is that it reduces the amount of emotional speech data necessary for training by focusing on non-linguistic information. The proposed algorithm consists of two steps. In the first step, to generate a variety of spectrum patterns that resemble human speech as closely as possible, WaveNet is trained with auxiliary mel-spectrum parameters and Emotion ID using a large amount of neutral speech. In the second step, to generate emotional expressions, WaveNet is retrained with auxiliary Emotion ID only using a small amount of emotional speech. Experimental results reveal the following: (1) the two-step training is necessary to generate the SES with high quality, and (2) it is important that the training use a large neutral speech database and spectrum information in the first step to improve the emotional expression and naturalness of SES.
著者
Rui YANG Raphael SHU Hideki NAKAYAMA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.9, pp.1537-1545, 2022-09-01

Generative Adversarial Networks (GANs) are one of the most successful learning principles of generative models and were wildly applied to many generation tasks. In the beginning, the gradient penalty (GP) was applied to enforce the discriminator in GANs to satisfy Lipschitz continuity in Wasserstein GAN. Although the vanilla version of the gradient penalty was further modified for different purposes, seeking a better equilibrium and higher generation quality in adversarial learning remains challenging. Recently, DRAGAN was proposed to achieve the local linearity in a surrounding data manifold by applying the noised gradient penalty to promote the local convexity in model optimization. However, we show that their approach will impose a burden on satisfying Lipschitz continuity for the discriminator. Such conflict between Lipschitz continuity and local linearity in DRAGAN will result in poor equilibrium, and thus the generation quality is far from ideal. To this end, we propose a novel approach to benefit both local linearity and Lipschitz continuity for reaching a better equilibrium without conflict. In detail, we apply our synchronized activation function in the discriminator to receive a particular form of noised gradient penalty for achieving local linearity without losing the property of Lipschitz continuity in the discriminator. Experimental results show that our method can reach the superior quality of images and outperforms WGAN-GP, DiracGAN, and DRAGAN in terms of Inception Score and Fréchet Inception Distance on real-world datasets.
著者
Eiji KONAKA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E102.D, no.6, pp.1145-1153, 2019-06-01 (Released:2019-06-01)
参考文献数
24
被引用文献数
1

This study tries to construct an accurate ranking method for five team ball games at the Olympic Games. First, the study uses a statistical rating method for team ball games. A single parameter, called a rating, shows the strength and skill of each team. We assume that the difference between the rating values explains the scoring ratio in a match based on a logistic regression model. The rating values are estimated from the scores of major international competitions that are held before the Rio Olympic Games. The predictions at the Rio Olympic Games demonstrate that the proposed method can more accurately predict the match results than the official world rankings or world ranking points. The proposed method enabled 262 correct predictions out of 370 matches, whereas using the official world rankings resulted in only 238 correct predictions. This result shows a significant difference between the two criteria.
著者
Weina ZHOU Xinxin HUANG Xiaoyang ZENG
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.8, pp.1393-1400, 2022-08-01
被引用文献数
4

As a kind of marine vehicles, Unmanned Surface Vehicles (USV) are widely used in military and civilian fields because of their low cost, good concealment, strong mobility and high speed. High-precision detection of obstacles plays an important role in USV autonomous navigation, which ensures its subsequent path planning. In order to further improve obstacle detection performance, we propose an encoder-decoder architecture named Fusion Refinement Network (FRN). The encoder part with a deeper network structure enables it to extract more rich visual features. In particular, a dilated convolution layer is used in the encoder for obtaining a large range of obstacle features in complex marine environment. The decoder part achieves the multiple path feature fusion. Attention Refinement Modules (ARM) are added to optimize features, and a learnable fusion algorithm called Feature Fusion Module (FFM) is used to fuse visual information. Experimental validation results on three different datasets with real marine images show that FRN is superior to state-of-the-art semantic segmentation networks in performance evaluation. And the MIoU and MPA of the FRN can peak at 97.01% and 98.37% respectively. Moreover, FRN could maintain a high accuracy with only 27.67M parameters, which is much smaller than the latest obstacle detection network (WaSR) for USV.
著者
Dehua LIANG Jun SHIOMI Noriyuki MIURA Masanori HASHIMOTO Hiromitsu AWANO
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.7, pp.1273-1282, 2022-07-01

Reservoir computing (RC) is an attractive alternative to machine learning models owing to its computationally inexpensive training process and simplicity. In this work, we propose EnsembleBloomCA, which utilizes cellular automata (CA) and an ensemble Bloom filter to organize an RC system. In contrast to most existing RC systems, EnsembleBloomCA eliminates all floating-point calculation and integer multiplication. EnsembleBloomCA adopts CA as the reservoir in the RC system because it can be implemented using only binary operations and is thus energy efficient. The rich pattern dynamics created by CA can map the original input into a high-dimensional space and provide more features for the classifier. Utilizing an ensemble Bloom filter as the classifier, the features provided by the reservoir can be effectively memorized. Our experiment revealed that applying the ensemble mechanism to the Bloom filter resulted in a significant reduction in memory cost during the inference phase. In comparison with Bloom WiSARD, one of the state-of-the-art reference work, the EnsembleBloomCA model achieves a 43× reduction in memory cost while maintaining the same accuracy. Our hardware implementation also demonstrated that EnsembleBloomCA achieved over 23× and 8.5× reductions in area and power, respectively.
著者
Ding LI Chunxiang GU Yuefei ZHU
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.6, pp.1172-1184, 2022-06-01
被引用文献数
2

Website Fingerprinting (WF) enables a passive attacker to identify which website a user is visiting over an encrypted tunnel. Current WF attacks have two strong assumptions: (i) specific tunnel, i.e., the attacker can train on traffic samples collected in a simulated tunnel with the same tunnel settings as the user, and (ii) pseudo-open-world, where the attacker has access to training samples of unmonitored sites and treats them as a separate class. These assumptions, while experimentally feasible, render WF attacks less usable in practice. In this paper, we present Gene Fingerprinting (GF), a new WF attack that achieves cross-tunnel transferability by generating fingerprints that reflect the intrinsic profile of a website. The attack leverages Zero-shot Learning — a machine learning technique not requiring training samples to identify a given class — to reduce the effort to collect data from different tunnels and achieve a real open-world. We demonstrate the attack performance using three popular tunneling tools: OpenSSH, Shadowsocks, and OpenVPN. The GF attack attains over 94% accuracy on each tunnel, far better than existing CUMUL, DF, and DDTW attacks. In the more realistic open-world scenario, the attack still obtains 88% TPR and 9% FPR, outperforming the state-of-the-art attacks. These results highlight the danger of our attack in various scenarios where gathering and training on a tunnel-specific dataset would be impractical.
著者
Hitoshi SUDA Gaku KOTANI Daisuke SAITO
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.6, pp.1196-1210, 2022-06-01
被引用文献数
1

In this paper, we propose a new training framework named the INmfCA algorithm for nonparallel voice conversion (VC) systems. To train conversion models, traditional VC frameworks require parallel corpora, in which source and target speakers utter the same linguistic contents. Although the frameworks have achieved high-quality VC, they are not applicable in situations where parallel corpora are unavailable. To acquire conversion models without parallel corpora, nonparallel methods are widely studied. Although the frameworks achieve VC under nonparallel conditions, they tend to require huge background knowledge or many training utterances. This is because of difficulty in disentangling linguistic and speaker information without a large amount of data. In this work, we tackle this problem by exploiting NMF, which can factorize acoustic features into time-variant and time-invariant components in an unsupervised manner. The method acquires alignment between the acoustic features of a source speaker's utterances and a target dictionary and uses the obtained alignment as activation of NMF to train the source speaker's dictionary without parallel corpora. The acquisition method is based on the INCA algorithm, which obtains the alignment of nonparallel corpora. In contrast to the INCA algorithm, the alignment is not restricted to observed samples, and thus the proposed method can efficiently utilize small nonparallel corpora. The results of subjective experiments show that the combination of the proposed algorithm and the INCA algorithm outperformed not only an INCA-based nonparallel framework but also CycleGAN-VC, which performs nonparallel VC without any additional training data. The results also indicate that a one-shot VC framework, which does not need to train source speakers, can be constructed on the basis of the proposed method.
著者
Xin XIA Xiaozhen ZHOU David LO Xiaoqiong ZHAO Ye WANG
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E97.D, no.7, pp.1769-1780, 2014 (Released:2014-07-01)
参考文献数
42
被引用文献数
1

A build system converts source code, libraries and other data into executable programs by orchestrating the execution of compilers and other tools. The whole building process is managed by a software build system, such as Make, Ant, CMake, Maven, Scons, and QMake. Many studies have investigated bugs and fixes in several systems, but to our best knowledge, none focused on bugs in build systems. One significant feature of software build systems is that they should work on various platforms, i.e., various operating systems (e.g., Windows, Linux), various development environments (e.g., Eclipse, Visual Studio), and various programming languages (e.g., C, C++, Java, C#), so the study of software build systems deserves special consideration. In this paper, we perform an empirical study on bugs in software build systems. We analyze four software build systems, Ant, Maven, CMake and QMake, which are four typical and widely-used software build systems, and can be used to build Java, C, C++ systems. We investigate their bug database and code repositories, randomly sample a set of bug reports and their fixes (800 bugs reports totally, and 199, 250, 200, and 151 bug reports for Ant, Maven, CMake and QMake, respectively), and manually assign them into various categories. We find that 21.35% of the bugs belong to the external interface category, 18.23% of the bugs belong to the logic category, and 12.86% of the bugs belong to the configuration category. We also investigate the relationship between bug categories and bug severities, bug fixing time, and number of bug comments.
著者
Elsayed A. ELSAYED Kenji KISE
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E103.D, no.12, pp.2504-2517, 2020-12-01 (Released:2020-12-01)
参考文献数
14
被引用文献数
2

Data sorting is an important operation in computer science. It is extensively used in several applications such as database and searching. While high-performance sorting accelerators are in demand, it is very important to pay attention to the hardware resources for such kind of high-performance sorters. In this paper, we propose three FPGA based architectures to accelerate sorting operation based on the merge sorting algorithm. We call our proposals as WMS: Wide Merge Sorter, EHMS: Efficient Hardware Merge Sorter, and EHMSP: Efficient Hardware Merge Sorter Plus. We target the Virtex UltraScale FPGA device. Evaluation results show that our proposed merge sorters maintain both the high-performance and cost-effective properties. While using much fewer hardware resources, our proposed merge sorters achieve higher performance compared to the state-of-the-art. For instance, with 256 sorted records are produced per cycle, implementation results of proposed EHMS show a significant reduction in the required number of Flip Flops (FFs) and Look-Up Tables (LUTs) to about 66% and 79%, respectively over the state-of-the-art merge sorter. Moreover, while requiring fewer hardware resources, EHMS achieves about 1.4x higher throughput than the state-of-the-art merge sorter. For the same number of produced records, proposed WMS also achieves about 1.6x throughput improvement over the state-of-the-art while requiring about 81% of FFs and 76% of LUTs needed by the state-of-the-art sorter.
著者
Shunji FUNASAKA Koji NAKANO Yasuaki ITO
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E99.D, no.12, pp.2986-2994, 2016-12-01 (Released:2016-12-01)
参考文献数
22
被引用文献数
2 8

The main contribution of this paper is to present a work-optimal parallel algorithm for LZW decompression and to implement it in a CUDA-enabled GPU. Since sequential LZW decompression creates a dictionary table by reading codes in a compressed file one by one, it is not easy to parallelize it. We first present a work-optimal parallel LZW decompression algorithm on the CREW-PRAM (Concurrent-Read Exclusive-Write Parallel Random Access Machine), which is a standard theoretical parallel computing model with a shared memory. We then go on to present an efficient implementation of this parallel algorithm on a GPU. The experimental results show that our GPU implementation performs LZW decompression in 1.15 milliseconds for a gray scale TIFF image with 4096×3072 pixels stored in the global memory of GeForce GTX 980. On the other hand, sequential LZW decompression for the same image stored in the main memory of Intel Core i7 CPU takes 50.1 milliseconds. Thus, our parallel LZW decompression on the global memory of the GPU is 43.6 times faster than a sequential LZW decompression on the main memory of the CPU for this image. To show the applicability of our GPU implementation for LZW decompression, we evaluated the SSD-GPU data loading time for three scenarios. The experimental results show that the scenario using our LZW decompression on the GPU is faster than the others.
著者
Masatoshi YAMADA Masaki OHATA Daisuke KAKOI
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105.D, no.3, pp.565-577, 2022-03-01 (Released:2022-03-01)
参考文献数
35

In ball games, acquiring skills to change the direction becomes necessary. For revealing the mechanism of skill acquisition in terms of the relevant field, it would be necessary to take an approach regarding players' cognition as well as body movements measurable from outside. In the phase of change-of-direction performance that this study focuses on, cognitive factors including the prediction of opposite players' movements and judgements of the situation have significance. The purpose of this study was to reveal cognitive transformation in the skill acquisition process for change-of-direction performance. The survey was conducted for three months from August 29 to November 28, 2020, and those surveyed were seven university freshmen belonging to women's basketball club of M University. The way to analyze verbal reports collected in order to explore the changes in the players' cognition is described in Sect.2. In Sect.3, we made a plot graph showing temporal changes in respective factors based on coding outcomes for verbal reports. Consequently, as cognitive transformation in the skill acquisition process for change-of-direction performance, four items such as (1) goal setting for skill acquisition, (2) experience of change in running direction, (3) experience of speed and acceleration, and (4) experience of the movement of lower extremities such as legs and hip joints were suggested as common cognitive transformation. In addition, cognitive transformation varied by the degree of skill acquisition for change-of-direction performance. It was indicated that paying too much attention to body feelings including the position of and shift in the center of gravity in the body posed an obstacle to the skill acquisition for change-of-direction performance.
著者
Ki-Woong PARK Sung Hoon BAEK
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E100.D, no.10, pp.2348-2356, 2017-10-01 (Released:2017-10-01)
参考文献数
24
被引用文献数
1

Emerging digital payment services, also known as FinTech, have enabled various types of advanced payment transactions (such as Google Wallet, Apple Pay, Samsung Pay, etc.). However, offline peer-to-peer cash transactions still make up about 25.6% of the overall financial transactions in everyday life. By investigating existing online and offline payment systems, we identify three key challenges for building a digital cash transaction system with core features of the offline cash transactions: self-verifiability of digital cash; user anonymity; atomic cash transfer for double spending/depositing protection. In this paper, we propose OPERA, an offline peer-to-peer digital cash transaction system that addresses the three challenges. It newly introduces a concept of ‘one-time-readable memory(ORM)’ and ‘digital token’ which is a unit of self-verifiable digital cash. The one-time readability from ORM and three-stage token exchange protocol enable OPERA to provide uniqueness to digital cash and to allow a complete offline digital payment. OPERA devices are enhanced with TCPA technology to ensure the integrity of the physical device package. To evaluate the feasibility and resilience of the OPERA design, we built a prototype on a customized embedded board.
著者
Ryo HARAGUCHI Naozo SUGIMOTO Shigeru EIHO Yoshio ISHIDA
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E85-D, no.1, pp.69-76, 2002-01-01

This paper deals with a method of registration and superimposition of a coronary arterial tree on a myocardial SPECT (Single Photon Emission Computed Tomography) image. We can grasp the myocardial function more easily in connection with the shape of the coronary arterial tree. The superimposed image is easily obtainable through some manual pointing on coronary angiograms (CAG) followed by an automatic matching method: First, a rough shape model of left ventricle is estimated by using SPECT data. This 3-D left ventricular model is projected on a pair of bi-plane CAG images. We can obtain two 2-D coronary images on bull's eye map by scanning the left ventricular surface projected on CAG. By maximizing a matching degree between two 2-D coronary images, registration between CAG and SPECT is performed. Finally the superimposed image is obtained by integrating two 2-D coronary images and bull's eye image of SPECT. We validated our method by numerical experiments with artificial data set and also applied it to two clinical data sets.
著者
ZHAO Yu GAO Sheng GALLINARI Patrick GUO Jun
出版者
一般社団法人 電子情報通信学会
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.100, no.6, pp.1242-1250, 2017
被引用文献数
1

<p>It inevitably comes out information overload problem with the increasing available data on e-commence websites. Most existing approaches have been proposed to recommend the users personal significant and interesting items on e-commence websites, by estimating unknown rating which the user may rate the unrated item, i.e., rating prediction. However, the existing approaches are unable to perform user prediction and item prediction, since they just treat the ratings as real numbers and learn nothing about the ratings' embeddings in the training process. In this paper, motivated by relation prediction in multi-relational graph, we propose a novel embedding model, namely RPEM, to solve the problem including the tasks of rating prediction, user prediction and item prediction simultaneously for recommendation systems, by learning the latent semantic representation of the users, items and ratings. In addition, we apply the proposed model to cross-domain recommendation, which is able to realize recommendation generation in multiple domains. Empirical comparison on several real datasets validates the effectiveness of the proposed model. The data is available at https://github.com/yuzhaour/da.</p>
著者
Takahide ITO Yuichi NAKAMURA Kazuaki KONDO Espen KNOOP Jonathan ROSSITER
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E103.D, no.11, pp.2314-2322, 2020-11-01 (Released:2020-11-01)
参考文献数
15
被引用文献数
1

This paper introduces a novel skin-stretcher device for gently urging head rotation. The device pulls and/or pushes the skin on the user's neck by using servo motors. The user is induced to rotate his/her head based on the sensation caused by the local stretching of skin. This mechanism informs the user when and how much the head rotation is requested; however it does not force head rotation, i.e., it allows the user to ignore the stimuli and to maintain voluntary movements. We implemented a prototype device and analyzed the performance of the skin stretcher as a human-in-the-loop system. Experimental results define its fundamental characteristics, such as input-output gain, settling time, and other dynamic behaviors. Features are analyzed, for example, input-output gain is stable within the same installation condition, but various between users.
著者
Isana FUNAHASHI Taichi YOSHIDA Xi ZHANG Masahiro IWAHASHI
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE TRANSACTIONS on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105-D, no.1, pp.123-133, 2022-01-01

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 by conventional fusion methods, which tackle the artifact. To avoid this problem, the proposed method estimates the information of lacking areas via adaptive inpainting. The proposed CNN consists of three networks, warp and refinement, detection, and inpainting networks. The second and third networks detect lacking areas and estimate their pixel values, respectively. In the experiments, it is observed that a simple fusion method with the proposed method outperforms state-of-the-art fusion methods in the peak signal-to-noise ratio. Moreover, the proposed method is applied for various fusion methods as pre-processing, and results show obviously reducing artifacts.
著者
Keigo TAGA Junjun ZHENG Koichi MOURI Shoichi SAITO Eiji TAKIMOTO
出版者
The Institute of Electronics, Information and Communication Engineers
雑誌
IEICE Transactions on Information and Systems (ISSN:09168532)
巻号頁・発行日
vol.E105.D, no.1, pp.105-115, 2022-01-01 (Released:2022-01-01)
参考文献数
26

A wide range of communication protocols has recently been developed to address service diversification. At the same time, firewalls (FWs) are installed at the boundaries between internal networks, such as those owned by companies and homes, and the Internet. In general, FWs are configured as whitelists and release only the port corresponding to the service to be used and block communication from other ports. In a previous study, we proposed a method for traversing a FW and enabling communication by inserting a pseudo-transmission control protocol (TCP) header imitating HTTPS into a packet, which normally would be blocked by the FW. In that study, we confirmed the efficiency of the proposed method via its implementation and experiments. Even though common encapsulating techniques work on end-nodes, the previous implementation worked on the relay node assuming a router. Further, middleboxes, which overwrite L3 and L4 headers on the Internet, need to be taken into consideration. Accordingly, we re-implemented the proposed method into an end-node and added a feature countering a typical middlebox, i.e., NAPT, into our implementation. In this paper, we describe the functional confirmation and performance evaluations of both versions of the proposed method.