研究者詳細 - 神谷　亨

論文 - 神谷　亨

分割表示757 件中 201 - 220 件目／全件表示 >>

YOLOｖ３を用いた全天球カメラ映像からの障害物認識

甲斐、陸、神谷

第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ( 第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ) 84 - 88 2020年10月

SVMによる胸部CT画像からのドライバー遺伝子情報変異の検出

吉福、寺澤、神谷、青木

第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ( 第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ) 80 - 83 2020年10月

２つの解像度スペクトルとTF-CRNNによる呼吸音の分類

浅谷、神谷、間普、木戸

第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ( 第33回バイオメディカル・ファジィ・システム学会年次大会講演論文集 ) 64 - 67 2020年10月

Symmetric plane detection and symmetry analysis from a 3D point cloud data of face 査読有り国際誌

Hosoki D., Kamiya T., Kimura-Nomoto N., Okawachi T., Nozoe E., Nakamura N.

International Conference on Control, Automation and Systems 2020-October 402 - 406 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. Cleft lip occurs in about 1 in 500 people and is a congenital anomaly that occurs when the lips are not completely formed in the process of fetal face fusion. The treatment of the cleft lip is performed for the purpose of forming bilaterally symmetrical lips and external nose. However, it is based on a criterion that depends on subjectivity, quantitatively determining the degree of symmetry of the surgical site is required. In this paper, we propose a method for detecting the face that serves as the symmetry basis of the face to analyze the symmetry of the surgical site, and an index that indicates the symmetry. In the proposed method, after detecting the facial organs as points in the 3D point cloud data of the subject's face, we align the mirror image inversion excluding the region from upper lip to the tip of the nose where the effect of shape change due to cleft lip is remarkable with the original point cloud. Next, the symmetric reference plane is set by finding a plane that bisects vertically between one point in the original point cloud and the corresponding point in the mirror image inversion. As a result, the target reference plane is detected with high accuracy. Furthermore, as a result of applying the symmetry analysis method based on the target reference plane, it was possible to visually represent the left-right asymmetric region.

DOI： 10.23919/ICCAS50221.2020.9268262

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098071444&origin=inward

An image registration method for spine region in CT images considering sagittal plane 査読有り国際誌

Yamashita Y., Kamiya T., Aoki T.

International Conference on Control, Automation and Systems 2020-October 407 - 410 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. In recent years, the computer-aided diagnosis (CAD) systems for supporting to the physician is attracting attention in medical research field. One of them is temporal subtraction technique. It is a technique to generate images emphasizing temporal changes in lesions by performing a differential operation between current and previous image of the same subject. However, there is a problem of mistakenly selecting current and previous slice of a spine region with similar geometry as the same slice because many of the spine regions in axial plane have similar geometries. In this paper, we propose an image registration method for the detection of bone metastases from the spine region by creating a temporal subtraction images from CT images. Especially, we develop an image registration system for spine region considering sagittal plane to accurately select the same slice for the current image and the previous image. In the experiment, we applied the proposed method to CT images of 27 cases with bone metastases and the results were compared with the markings of the lesions.

DOI： 10.23919/ICCAS50221.2020.9268246

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098087691&origin=inward

Automatic Classification of Respiratory Sounds Considering Time Series Information Based on VGG16 with LSTM 査読有り国際誌

Asatani N., Kamiya T., Mabu S., Kido S.

International Conference on Control, Automation and Systems 2020-October 423 - 426 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. According to the 2016 World Health Organization (WHO) survey, respiratory diseases are serious diseases that account for four of the top ten causes of death in the world, accounting for more than 8 million deaths worldwide. Currently, the diagnosis of respiratory disease is made by auscultation, but in order to make an accurate diagnosis, a number of abnormal patterns of respiratory sounds need to be memorized, and the results of the diagnosis are dependent on the proficiency of the physician. Therefore, a computer aided diagnosis (CAD) system is needed to quantitatively classify the respiratory sounds and output the results as a "second opinion". In this paper, a short-time Fourier transformed spectrogram, a Constant-Q transformed logarithmic frequency spectrogram, and a continuous wavelet transformed scalogram are simultaneously input to VGG16 which is one of the network models of CNN(Convolutional Neural Network) and classified by LSTM (Long short-term memory). The proposed method is applied to 26 respiratory sounds, and the 0.90 of accuracy, sensitivity of 0.97, and specificity of 0.90 is obtained.

DOI： 10.23919/ICCAS50221.2020.9268428

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098088561&origin=inward

Identification of normal and abnormal from ultrasound images of power devices using VGG16 査読有り国際誌

Ogawa T., Lu H., Watanabe A., Omura I., Kamiya T.

International Conference on Control, Automation and Systems 2020-October 415 - 418 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. Power devices are semiconductor devices that handle high voltages and large currents, which are used in electric vehicles, televisions, and trains. Therefore, high reliability and safety are required, and to ensure this, power cycle tests are performed to analyze the breakdown process. Conventional tests are often difficult to analyze due to the influence of sparks generated during the test. Therefore, new tests are being developed by adding ultrasound to conventional methods. The new technology is capable of continuously recording structural changes inside the device during testing, which is expected to make testing much easier than conventional testing. However, the new technology still has some challenges. The main problems are the lack of a method for analyzing large amounts of image data and the extraction of small changes in image features that are difficult to distinguish with the human eye, and the establishment of such a system is required. In this paper, we use deep learning for image classification of the obtained ultrasound images. We propose a new network model with the addition of Batch normalization and Global average pooling to VGG16, which is a pre-trained model. In the experiment, accuracy=98.29%, TPR=98.96% and FPR=7.43% classification accuracy was obtained.

DOI： 10.23919/ICCAS50221.2020.9268275

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098091061&origin=inward

Image registration method from LDCT image using FFD Algorithm 査読有り国際誌

Tanaka C., Kamiya T., Aoki T.

International Conference on Control, Automation and Systems 2020-October 411 - 414 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. In recent years, the number of lung cancer deaths has been increasing. In Japan, CT (Computed Tomography) equipment is used for its visual screening. However, there is a problem that seeing huge number of images taken by CT is a burden on the doctor. To overcome this problem, the CAD (Computer Aided Diagnosis) system is introduced on medical fields. In CT screening, LDCT (Low Dose Computed Tomography) screening is desirable considering radiation exposure. However, the image quality which is caused the lower the dose is another problem on the screening. A CAD system that enables accurate diagnosis even at low doses is needed. Therefore, in this paper, we propose a registration method for generating temporal subtraction images that can be applied to low-quality chest LDCT images. Our approach consists of two major components. Firstly, global matching based on the center of gravity is performed on the preprocessed images, and the region of interest (ROI) is set. Secondly, local matching by free-form deformation (FFD) based on B-Spline is performed on the ROI as final registration. In this paper, we apply our proposed method to LDCT images of 6 cases, and reduce 57.29% in the calculation time, 26.1% in the half value width, and 29.6% in the sum of histogram of temporal subtraction images comparing with the conventional method.

DOI： 10.23919/ICCAS50221.2020.9268267

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098056092&origin=inward

Object recognition from spherical camera images based on YOLOv3 査読有り国際誌

Kai T., Lu H., Kamiya T.

International Conference on Control, Automation and Systems 2020-October 419 - 422 2020年10月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 Institute of Control, Robotics, and Systems - ICROS. The aging of Japan is remarkable, and attention has been focused on the use and utilization of assistive devices. One of them is electric wheelchair, which enables physical disability people to easily operate it using a handle or a joystick. However, accidents are occurring frequently with increasing demand by using electric wheelchair. Therefore, developing an autonomous electric wheelchair is required to reduce accidents such as maneuvering mistakes, reduce the accident rate, improve convenience, and reduce the burden on caregivers. In this paper, we focus on the recognition of obstacles and use panoramic images obtained from a spherical camera that can easily handle information from all directions at low cost. A spherical camera is attached to an electric wheelchair, and images are cut out from the sequential images obtained by running. For image analysis, YOLOv3, which has been successful in the field of image recognition in recent years, is used. In the proposed method, considering the distortion of the image caused by using the spherical camera, the improvement of the model of YOLOv3 is examined, and the validity with the actual data is verified.

DOI： 10.23919/ICCAS50221.2020.9268308

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85098088521&origin=inward

Automatic Classification of Respiratory Sounds Based on Convolutional Neural Network with Multi Images 査読有り

Minami K., Lu H., Kamiya T., Mabu S., Kido S.

ACM International Conference Proceeding Series 17 - 21 2020年09月

U-Net特徴量による特発性肺線維疾患者の予後予測査読有り

植村、渡利、Janne、弘中、神谷、吉田

第１９回情報科学技術フォーラム第2分冊 ( 第１９回情報科学技術フォーラム第2分冊 ) 75 - 78 2020年09月

Deep Learning for Visual Segmentation: A Review 査読有り国際誌

Sun J., Li Y., Lu H., Kamiya T., Serikawa S.

Proceedings - 2020 IEEE 44th Annual Computers, Software, and Applications Conference, COMPSAC 2020 1256 - 1260 2020年07月

担当区分：責任著者記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

© 2020 IEEE. Big data-driven deep learning methods have been widely used in image or video segmentation. The main challenge is that a large amount of labeled data is required in training deep learning models, which is important in real-world applications. To the best of our knowledge, there exist few researches in the deep learning-based visual segmentation. To this end, this paper summarizes the algorithms and current situation of image or video segmentation technologies based on deep learning and point out the future trends. The characteristics of segmentation that based on semi-supervised or unsupervised learning, all of the recent novel methods are summarized in this paper. The principle, advantages and disadvantages of each algorithms are also compared and analyzed.

DOI： 10.1109/COMPSAC48688.2020.00-84

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85094163880&origin=inward

Automatic detection of lung nodules from temporal subtraction images based on residual 3D-CNN with linear multi-shortcut 査読有り国際誌

Yoshino, Lu, Kim, Aoki, Kido

International Journal of Computer Assisted Radiology and Surgery 15 ( 6 ) 2020年06月

U-radiomics combined with hyper-curvature features for predicting survival of patients with idiopathic pulmonary fibrosis 査読有り国際誌

Uemura, Watari, Nappi, Matsuhiro, Niki, Kim, Yoshida

International Journal of Computer Assisted Radiology and Surgery 15 ( 6 ) 2020年06月

Deep-Sea Organisms Tracking Using Dehazing and Deep Learning 査読有り国際誌

Lu H., Uemura T., Wang D., Zhu J., Huang Z., Kim H.

Mobile Networks and Applications 25 ( 3 ) 1008 - 1015 2020年06月

記述言語：英語掲載種別：研究論文（学術雑誌）

© 2018, Springer Science+Business Media, LLC, part of Springer Nature. Deep-sea organism automatic tracking has rarely been studied because of a lack of training data. However, it is extremely important for underwater robots to recognize and to predict the behavior of organisms. In this paper, we first develop a method for underwater real-time recognition and tracking of multi-objects, which we call “You Only Look Once: YOLO”. This method provides us with a very fast and accurate tracker. At first, we remove the haze, which is caused by the turbidity of the water from a captured image. After that, we apply YOLO to allow recognition and tracking of marine organisms, which include shrimp, squid, crab and shark. The experiments demonstrate that our developed system shows satisfactory performance.

DOI： 10.1007/s11036-018-1117-9

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85055349873&origin=inward

Detection of Circulating Tumor Cells in Fluorescence Microscopy Images Based on ANN Classifier 査読有り国際誌

Tsuji K., Lu H., Tan J.K., Kim H., Yoneda K., Tanaka F.

Mobile Networks and Applications 25 ( 3 ) 1042 - 1051 2020年06月

担当区分：責任著者記述言語：英語掲載種別：研究論文（学術雑誌）

© 2018, Springer Science+Business Media, LLC, part of Springer Nature. Circulating tumor cells (CTCs) is a clinical biomarker for cancer metastasis. CTCs are cells circulating in the body of patients by being separated from primary cancer and entering into blood vessel. CTCs spread every positions in the body, and this is one of the cause of cancer metastasis. To analyze them, pathologists get information about metastasis without invasive test. CTCs test is conducted by analyzing the blood sample from patient. The fluorescence microscope generates a large number of images per each sample, and images contain a lot of cells. There are only a few CTCs in images and cells often have blurry boundaries. So CTCs identification is not an easy work for pathologists. In this paper, we develop an automatic CTCs identification method in fluorescence microscopy images. This proposed method has three section. In the first approach, we conduct the cell segmentation in images by using filtering methods. Next, we compute feature values from each CTC candidate region. Finally, we identify CTCs using artificial neural network algorithm. We apply the proposed method to 5895 microscopy images (7 samplesas), and evaluate the effectiveness of our proposed method by using leave-one-out cross validation. We achieve the result of performance tests, a true positive rate is 92.57% and false positive rate is 9.156%.

DOI： 10.1007/s11036-018-1121-0

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85053481889&origin=inward

High-quality-guided artificial bee colony algorithm for designing loudspeaker 査読有り国際誌

Gao H., Li H., Liu Y., Lu H., Kim H., Pun C.M.

Neural Computing and Applications 32 ( 9 ) 4473 - 4480 2020年05月

記述言語：英語掲載種別：研究論文（学術雑誌）

© 2018, The Natural Computing Applications Forum. Designing the loudspeaker could be concerned as an optimization problem. Like most electromagnetic device design issues, it demonstrates multimodal, multidimensional and constrained. The traditional design method cannot achieve a satisfactory model within a certain period of time. In this paper, a high-quality-guided artificial bee colony algorithm is proposed to increase its convergence speed and search accuracy by gradually changing the number of updating dimensions and searching closer to better locations. The algorithm is first tested on some representative basic benchmark functions and then is applied to a loudspeaker design problem. By comparing with some classical algorithms, the performance of our algorithm is verified.

DOI： 10.1007/s00521-018-3568-0

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85048041015&origin=inward

An Automatic Design of Camouflage Patterns Based on CNNs 査読有り

Wei X., Wang K., Li G., Kim H.

ACM International Conference Proceeding Series 257 - 260 2020年04月

記述言語：英語掲載種別：研究論文（国際会議プロシーディングス）

In order to get with the environmental changes of battlefield quickly, the military camouflage should be changeable. If the camouflage patterns of the clothes and vehicles like tanks are different from the environment, it's very easy for cameras of enemies to find. As we all know that the same patterns is used in the most of current military all over the world. In this paper, we propose a novel feature-extraction method from an image using convolutional neural networks. Then the pattern will be combined with the environmental style pattern. The composite image is mapped onto the surface of the actual 3D clothes and vehicles finally. In this paper, the Eye-Movement equipment is applied to evaluate the results for better comparison. We can produce the proper pattern even the different and complicated environment.

DOI： 10.1145/3404555.3404637

Scopus

その他リンク： https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85092212124&origin=inward

SqueezeNetによる蛍光顕微鏡画像上のCTC自動検出査読有り

中道、陸、金、米田、田中

画像電子学会誌 49 ( 2 ) 136 - 143 2020年04月

CT 像からの骨転移検出のための画像位置合わせ法

佐藤、陸、金、青木

電子情報通信学会総合大会 108 2020年03月

　前のページ - 次のページ　

<神谷 亨>

論文 - 神谷 亨

<神谷　亨>

論文 - 神谷　亨