Faculty Profiles - KAMIYA Tohru

Papers - KAMIYA Tohru

Division display441 - 460 of about 751／ All the affair displays >>

Detection of underwater objects based on machine learning Reviewed

2104 - 2109 2013.12

Detecting foreground objects by sequential background inference in a video captured by a moving camera Reviewed

1699 - 1702 2013.12

Classifying 2D and 3D objects on a road employing the road plane Reviewed

1689 - 1692 2013.12

Abnormal motion detection in an occlusive environment Reviewed

1398 - 1402 2013.12

A novel pedestrian detector on low-resolution images: Gradient LBP using patterns of oriented edges Reviewed

IEICE Transactions on Information and Systems E96-D ( 12 ) 2882 - 2887 2013.12

A global-local approach to saliency detection Reviewed

8048 LNCS ( PART 2 ) 332 - 337 2013.09

Cerebrovascular Segmentation from CTA and MRA Image

MAEDA Shinya, YAMAMURA Yutaro, KIM Hyoungseop, TAN Joo Kooi, ISHIKAWA Seiji, YAMAMOTO Akiyoshi

IEICE technical report. Image engineering ( The Institute of Electronics, Information and Communication Engineers ) 113 ( 211 ) 81 - 84 2013.09

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

Radiation therapy is one of treatment technique for tumor. In the treatment, tumor parts are exposed by radiation beams from several angles. To avoid radiation exposure to normal tissues in the treatment, radiation beams are aimed accurately to tumor. Consequently, to comprehend tumor parts from CT and/or MR images is important in treatment planning. The tumor parts are displayed effectively by applying the image registration between CT and MR images. Feature based image registration technique is one of typical approaches for image registration. In this study, to develop assistance system of radiation therapy for brain tumor, cerebrovascular segmentation method which is utilized as feature position detection of image registration technique for head CTA and MRA images has been proposed. Availability of proposed method has been investigated by applying to head CTA and MRA images.

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009817858

Cerebrovascular Segmentation from CTA and MRA Image

MAEDA Shinya, YAMAMURA Yutaro, KIM Hyoungseop, TAN Joo Kooi, ISHIKAWA Seiji, YAMAMOTO Akiyoshi

IEICE technical report. Life intelligence and office information systems ( The Institute of Electronics, Information and Communication Engineers ) 113 ( 210 ) 81 - 84 2013.09

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009784523

Cerebrovascular Segmentation from CTA and MRA Image

MAEDA Shinya, YAMAMURA Yutaro, KIM Hyoungseop, TAN Joo Kooi, ISHIKAWA Seiji, YAMAMOTO Akiyoshi

( The Institute of Electronics, Information and Communication Engineers ) 113 ( 212 ) 81 - 84 2013.09

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009783192

Road region estimation and obstacles extraction using a monocular camera Reviewed

9 ( 9 ) 3561 - 3572 2013.07

Detection of Lung nodules on temporal subtraction based on non-rigid image registration and development of software for image viewer

IKEDA Yuriko, TOKISA Takumi, MAEDA Shinya, KIM Hyoungseop, TAN Joo KOOI, ISHIKAWA Seiji

Technical report of IEICE. PRMU ( The Institute of Electronics, Information and Communication Engineers ) 113 ( 75 ) 1 - 4 2013.06

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

A temporal subtraction technique that is subtracted from previous image to current one is introduced as powerful tools in medical fields to diagnose abnormalities and temporal changes. It provided a computer aided diagnosis (CAD) tools on visual screening. Radiologist can easily detect lesions on images by compare of images. It is because the subtraction image can enhance the temporal changes, such as shaped of new lesions and/or the temporal changes in existing abnormalities by removing most of the normal background structures by subtraction of a previous image from a current one. In this paper, we develop a CAD system to detect lung nodules on temporal subtraction based on non-rigid image registration and its application for 3D image viewer. In this CAD system, final abnormal areas are detected based on artificial neural networks and displayed on current images.

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009779161

Temporal Subtraction Method for Thoracic MDCT Image by Using Intensity Gradient Information Reviewed

MAEDA Shinya, MIYAKE Noriaki, KIM Hyoungseop, TAN Joo Kooi, ISHIKAWA Seiji, MURAKAMI Seiichi, AOKI Takatoshi

Transactions of the Society of Instrument and Control Engineers ( The Society of Instrument and Control Engineers ) 49 ( 4 ) 461 - 468 2013.04

Authorship：Corresponding author Language：Japanese Publishing type：Research paper (scientific journal)

Recently, CAD system has been introduced as a visual screening method in medical field. Also, temporal subtraction method, which enhances temporal changes such as the abnormalities on the image, is implemented as one of technique for CAD by subtracting previous image from current one. Image registration techniques are required for the temporal subtraction method. If the accuracy of image registration is insufficiently, normal structure elements which should be removed are remained on subtraction image. In this study, a novel image registration method for temporal subtraction technique on thoracic MDCT images has been developed to reduce the subtraction artifacts by using intensity gradient information. The proposed method has been applied to thoracic MDCT images, and its efficiency has been indicated.

DOI： 10.9746/sicetr.49.461

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/10031166608

Detection of artery regions in lower extremity arteries from non-enhanced MR imaging based on particle filter algorithms Reviewed

17 ( 2 ) 318 - 323 2013.03

Nonrigid Registration Method for Thoracic CT Images by Using Vessel Structure Information Reviewed

MAEDA Shinya, KIM Hyoungseop, TAN Joo Kooi, ISHIKAWA Seiji, MURAKAMI Seiichi, AOKI Takatoshi

The IEICE transactions on information and systems (Japanese edetion) ( The Institute of Electronics, Information and Communication Engineers ) 96 ( 3 ) 733 - 742 2013.03

Recognizing human actions using histogram of local binary patterns Reviewed

54 - 59 2013.01

Automatic classification of seabed sediments based on HLAC Reviewed

653 - 658 2013.01

A parameterization based correspondence method for PDM building Reviewed

17 ( 1 ) 18 - 26 2013.01

Detection of Underwater Objects Based on Machine Learning Reviewed

Tan Ysuhiro, Tan Joo Kooi, Kim Hyoungseop, Ishikawa Seiji

Journal of the Japan Society of Naval Architects and Ocean Engineers ( The Japan Society of Naval Architects and Ocean Engineers ) 18 ( 0 ) 115 - 121 2013.01

Language：Japanese Publishing type：Research paper (scientific journal)

Side-scan and forward looking sonars are some of the most widely used imaging systems for obtaining large scale images of a seafloor, and their use continues to expand rapidly with their increasing deployment on Autonomous Underwater Vehicles. However,it is difficult to extract quantitative information from the images generated from these processes, in particular, for the detection and extraction of information on the objects within these images. We propose in this paper an algorithm for automatic detection of underwater objects in side-scan images based on machine learning employing adaptive boosting. Experimental results show that the method produces consistent maps of a seafloor.

DOI： 10.2534/jjasnaoe.18.115

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/130003393937

C-1-1 Automatic Detection of Blood Vessels in Legs from Fresh Blood Imaging Based on Particle Filter Algorithms

Kim Hyoungseop, Koga Yuiko, Tan Joo Kooi, Ishikawa Seiji, Yamamoto Akiyoshi

Proceedings of the Annual Conference of Biomedical Fuzzy Systems Association ( Biomedical Fuzzy Systems Association ) 26 ( 0 ) 29 - 32 2013.01

Authorship：Lead author Language：Japanese Publishing type：Research paper (conference, symposium, etc.)

Recently, the Arterio sclerosis obliterans (ASO) caused by chronic ischemia of limbs increases. As one of the diagnosis methods to detect the ASO, MR image which is obtained fresh blood imaging (FBI) is used for visual screening in medical fields. In this paper, we propose a method to detect blood vessel regions in legs from the FBI images. Especially, we developed for preventing the spread outside of the region and the segment accuracy in peripheral artery areas that is improved by using particle filter algorithms. We performed our proposed method on to real MR images which is obtained by FBI method and satisfactory detection results of artery regions are achieved.

DOI： 10.24466/pacbfsa.26.0_29

CiNii Article

Other Link： https://ci.nii.ac.jp/naid/110009830344

Temporal subtraction method for abdominal contrast and non-contrast image based on image matching techniques Reviewed

1805 - 1808 2012.12

　 PREV - NEXT 　

<KAMIYA Tohru>

Papers - KAMIYA Tohru