Faculty Profiles - AMANO Toshiyuki

Published Papers - AMANO Toshiyuki

Division display161 - 180 of about 182／ All the affair displays >>

Appearance Enhancement Using a Projector-Camera Feedback System

Toshiyuki Amano, Hirokazu Kato

19TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOLS 1-6 ( IEEE ) 1154 - 1157 2008 [Refereed]

DOI

Real world dynamic appearance enhancement with procam feedback

Toshiyuki Amano, Hirokazu Kato

PROCAMS 2008 - ACM/IEEE 5th International Workshop on Projector Camera Systems 2008

DOI

3D head model generation using full-face head shape measurement system

Takehiko Koyasu, Toshiyuki Amano, Yukio Sato

Systems and Computers in Japan 38 ( 13 ) 82 - 91 2007.11

Recently, the application of human facial shapes has been attracting interest in such fields as authentication, amusement, and medical care. However, the systems now used in practice heavily burden the person undergoing measurement, because a long time is required for measurement and the user must maintain his or her facial expression. The paper considers the measurement of the human face and proposes a fast method for head shape measurement in which the number of projected patterns is decreased by utilizing the continuity of the facial shape and the uniformity of its reflectivity. Specifically, based on the assumption of continuity of the facial shape, the pattern projection of the upper bits is omitted in the spatial coding, and the spatial code is restored by utilizing the continuity of the facial shape. By applying this method, shape measurement with 8-bit spatial resolution in the depth direction is achieved by five pattern light projection operations. Based on the fact that the reflectivity of the face is almost uniform, binarization is performed without complementary pattern projection, by using average image comparison and local threshold setting. With these measures, the head model can be acquired by the proposed method in 14 pattern imaging operations, compared with 36 pattern imaging operations required in the conventional measurement system based on spatial coding using complementary pattern light projection. © 2007 Wiley Periodicals, Inc.

DOI

A Fast Linear Pose Estimation Method of 3D Object Using EbC Image Pair

AMANO Toshiyuki, TAMAKI Toru

The IEICE transactions on information and systems ( The Institute of Electronics, Information and Communication Engineers ) 90 ( 8 ) 2060 - 2069 2007.08 [Refereed]

本論文では三次元物体の姿勢パラメータを二次元画像から高速に推定する方法として、EbC(Estimation-by-Completion)法を提案する。EbC法は、アピアランスベース姿勢推定を、画像に埋め込まれた情報トラックの復元という問題としてとらえ、固有空間法による学習結果をもとにBPLP法で画像補完することで情報トラックを復元し、パラメータ推定を実現する。また、画像補完とパラメータ推定の計算を2枚の画像(EbC画像対)に集約し、各パラメータの推定を画像の内積演算と簡単な三角関数のみで実現するため、パラメータ推定を高速に行うことができる。実験では、鉛直軸周りの回転と画像面での並進の3自由度の姿勢パラメータ推定結果を示し、EbC法の精度と計算コストについて述べる。

Image interpolation using BPLP method on the eigenspace

Toshiyuki Amano, Yukio Sato

Systems and Computers in Japan 38 ( 1 ) 87 - 96 2007.01

In this paper the authors propose a method to use interpolation to eliminate characters in only one image with telops or other text through an image interpolation method that uses the eigenspace method. Background scenes and other images have a fractal character, and often the self-correlation in the image can be assumed to be high. The authors focus on this point and represent rules for describing the image based on an eigenspace consisting of only one image that has defects. The eigenspace generated in this manner reflects the features of the image, and by using this eigenspace, image interpolation can be achieved. Although this interpolation method does not restore the original image, the authors confirmed through experimental results that it can provide interpolation without a feeling of oddness for images which have a high level of self-correlation. © 2006 Wiley Periodicals, Inc.

DOI

Image interpolation using BPLP method on the eigenspace

Toshiyuki Amano, Yukio Sato

Systems and Computers in Japan 38 ( 1 ) 87 - 96 2007.01 [Refereed]

DOI

Virtual recovery of the deteriorated art object based on AR technology

Toshiyuki Amano, Ryo Suzuki

2007 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, VOLS 1-8 ( IEEE ) 3600 - + 2007 [Refereed]

In this paper, the virtual restoration method of the art piece in the real world is proposed. The correction pattern for restoration is generated from non damaged object's image scanned in advance. As the method to recover the beauty, the marker tracking is used to detect art piece position and the correction image is projected from calibrated LCD projector In the experiment, the color restoration by a sample image was performed. From the experimental results, the ability of restoration of the discoloring was confirmed in the real world imaginary by the correction image projection.

DOI

Virtual Recovery of the Depleted Art Object based on AR Technology

SUZUKI Ryo, AMANO Toshiyuki

The Journal of the Society for Art and Science 6 ( 1 ) 11 - 20 2007 [Refereed]

In positioning of the present art pieces, the irreversible restoration for beauties recovery is not allowed in many cases. In this research, we applied augmented reality technology to this problem, and the virtual restoration method of the art piece in the real world is proposed. In this proposed method, the correction image for restoration is generated from a non-damage image scanned in advance. As the method to recover the beauty, the marker tracking is used to detect art piece position and the correction image is projected from calibrated LCD projector. Moreover, the pose of art piece is detected and luster restoration is performed based on the phong model. In the experiment, the color restoration and luster restoration by a sample image were performed. From the experimental results, the ability of restoration of the discoloring and luster was confirmed in the real world imaginary by the correction image projection.

DOI

Virtual Recovery of the Depleted Art Object based on AR Technology

SUZUKI Ryo, AMANO Toshiyuki

The Journal of the Society for Art and Science ( 芸術科学会 ) 6 ( 1 ) 11 - 20 2007 [Refereed]

DOI

Correlation based image defect detection

Toshiyuki Amano

18TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 1, PROCEEDINGS ( IEEE COMPUTER SOC ) 163 - 166 2006 [Refereed]

The defect inspection that used image sensing such as automated pattern inspection is a useful solution to automatize the visual check, not limit to factory automation field. Mostly such defect inspection is using the models of defect that described by primitive features. This paper proposes a new defect detection method that is the non-model based approach. In this approach, the method extracts the image description rule from local regions. It is useful for the defect inspection problems that cannot prepare a defect model such as scratch or superimpose detection, texture image analysis, etc. In the experiment, I tiled the defect detection to the landscape picture which several types of superimpose were added. From these results, it was confirmed that the proposed method has high ability to detect the defected regions independently with the texture type. Furthermore, I attempted the application to a scene image. Therefrom, the possibility to apply the figure-ground separation of the image understanding basic problem was confirmed.

DOI

3‐D Head Model Generation Using Full Face Head Shape Measurement System

子安健彦, 天野敏之, 佐藤幸男

電子情報通信学会論文誌 D-2 ( The Institute of Electronics, Information and Communication Engineers ) J87-D-2 ( 9 ) 1796 - 1804 2004.09 [Refereed]

近年,認証やアミューズメント,医療分野などにおいて人物の顔画像のみならず顔形状の応用が注目されている.しかし,現在実用化されているシステムでは計測時間が長く,表情を意識的に固定する必要があるなど被計測者に対する負担が大きい.そこで,本論文では人間の顔計測を前提とし,顔形状の連続性や反射率の一様性から投影パターン数を削減することで高速な頭部形状計測手法を提案する.具体的には,顔形状の連続性の仮定より空間コード化法における上位ビットのパターン投影を省略し,顔形状の連続性から空間コードの復元を行う.この手法を用いることにより奥行方向の空間分解能が8 bitの形状計測を5回のパターン光投影より実現した.また,顔の反射率がほぼ一様であることから,平均画像比較法と局所的にしきい値を決定することにより相補パターン投影法を用いない2値化を実現した.以上より,従来の相補パターン光投影を用いた空間コード化法を用いた計測システムでは36回のパターン撮影が必要であったのに対し,本システムでは14回のパターン撮影で頭部モデルの取得が可能となった.

Curved document imaging with eye scanner

Toshiyuki Amano, Tsutomu Abe, Osamu Nishikawa, Tetsuo Iyoda, Yukio Sato

Systems and Computers in Japan 35 ( 9 ) 20 - 29 2004.08

In conventional document imaging by a copying machine, the item to be copied must be held flat at a specified position. In addition, distortion or blurring can be produced when an object with three-dimensional undulations is imaged. Consequently, we developed a next-generation document imaging device (Eye Scanner) which can image characters or photographs on a curved sheet from an arbitrary viewpoint, without contact and without distortion, by utilizing shape information. This paper gives an outline of the Eye Scanner device and proposes a method of eliminating texture distortion of a curved object imaged from an arbitrary viewpoint. A divided imaging and connection method by using a pan-tilt stage is presented. © 2004 Wiley Periodicals, Inc.

DOI

Image interpolation by high dimensional projection based on subspace method

T Amano

PROCEEDINGS OF THE 17TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION, VOL 4 ( IEEE COMPUTER SOC ) 665 - 668 2004 [Refereed]

This paper presents a new image interpolation technique for image cracking such as telop character occlusion or picture deterioration. The landscape picture and texture pattern or other natural scenes contain the behavior of the autocorrelation pattern, and a method of image interpolation based on the autocorrelation pattern has been established. This method extracts many local regions from a piece of image and generates a subspace by the image vectors. The subspace limits the freedom of the image description at the local region by the hyperplane restriction in the image vector space. This paper explains for an image interpolation method based on eigen-space and explains the expansion using kernel non-linear projection.

DOI

Image Interpolation by the High Dimensional Nonlinear Projection Using kBPLP Method.

天野敏之, 佐藤幸男

電子情報通信学会論文誌 D-2 ( 一般社団法人電子情報通信学会 ) J86-D-2 ( 4 ) 525 - 534 2003.04 [Refereed]

近年カーネル主成分分析やSupport Vector Machineなどで代表される非線形部分空間法が注目を浴びている.これらの非線形部分空間法は特徴空間上のクラス境界が非線形関数によって表現できる問題について,適切なカーネル関数を用いることによりその分布に適した非線形の部分空間を生成することが可能であり,線形の部分空間よりも低い次元の部分空間でより精度の高いパターン認識を可能とする有効な手法である.本論文ではこの非線形部分空間射影の手法を筆者らが先に提案した固有ベクトル列により張られる超平面を知識とする欠落データの補間手法(BPLP法)に組み込むことにより,高次元の非線形射影を求めるカーネルBPLP法(kBPLP法)を提案する.また,テロップ文字などにより情報の欠落が生じた画像の補間問題にkBPLP法を適用し,BPLP法や他手法の補間結果との比較により本手法の有効性を評価する.

Cured Document Imagine with Eye Scanner

AMANO Toshiyuki, ABE Tsutomu, NISHIKAWA Osamu, IYODA Tetsuo, SATO Yukio

The Transactions of the Institute of Electronics,Information and Communication Engineers. ( 一般社団法人電子情報通信学会 ) 86 ( 3 ) 409 - 417 2003.03 [Refereed]

従来の複写機などによる紙面撮影は,あらかじめ決められた位置に紙面を引き伸ばした状態で配置する必要がある上,立体的な凹凸などがある物体の撮影ではひずみやぼけが生じる問題があった.そこで,我々は次世代のドキュメント撮影装置として,形状情報を用いることにより湾曲した紙面上の文字や写真を,自由視点から非接触でひずみなく撮影する撮影装置(アイスキャナ)を開発した.本論文では,アイスキャナの概要を説明し,自由視点から撮影された湾曲物体上のテクスチャのひずみを取り除く手法を提案する.また,パン・チルトステージによる分割撮影・接合手法について説明する.

Image Interpolation Using BPLP Method on the Eigenspace.

天野敏之, 佐藤幸男

電子情報通信学会論文誌 D-2 ( 一般社団法人電子情報通信学会 ) J85-D-2 ( 3 ) 457 - 465 2002.03 [Refereed]

本論文では,固有空間法を用いた画像補間法により,文字などのテロップを含む1枚の画像のみを用いて文字を補間により消去する手法を提案する.風景画などの画像はフラクタル的な性質があり,画像の自己相関性が仮定できる場合が多い.筆者らはこの点に着目し,欠損を含む1枚の画像のみから固有空間により画像を記述するルールを表現した.このように生成された固有空間は,画像の特徴を反映しており,この固有空間を用いることにより画像補間を実現した.本補間手法はオリジナル画像を復元するものではないが,実験の結果画像の自己相関性が成立する画像については違和感なく補間できることが確認された.

Development of the next generation document reader - Eye scanner

Toshiyuki Amano, Tsutomu Abe, Tetsuo Iyoda, Osamu Nishikawa, Yukio Sato

Proceedings of SPIE - The International Society for Optical Engineering 4669 250 - 258 2002

Up to now a copying machine requires setting the document to the copy glass of the designated position. In addition to that, the copying machine of the present cannot copy the non-flat shape document (e.g. books, cylindrical objects, etc.) clearly. Besides, it cannot copy without distortion. So, we propose a next generation's document reader "Eye Scanner". The Eye Scanner is composed of the range finder, digital camera and pan-tilt stage system. Due to these devices the Eye Scanner is possible shape information and high-density texture image acquisition. Therefore the Eye Scanner is able to read the document by the free viewpoint and able to generate the image which is not distorted by the geometric conversion. Moreover, the Eye Scanner has the ability for high-resolution image generation by the digital camera, which placed on the optical coaxial position by the half-mirror. In this paper, we explain about the detail of the system. At the explanation of the methodology we explain the methodology about distortion correction by the free form transformation with shape information and explain about the technique of image merging. At the experiment, we show some result of distortion correction and show the result of image merging. © 2002 SPIE · 0277-786X/02/$15.00.

DOI

Development of the Next Generation Document Reader : Eye Scanner

AMANO Toshiyuki, MATSUMOTO Motoki, ABE Tsutomu, IYODA Tetsuo, NISHIKAWA Osamu, SATO Yukio

ITE Technical Report ( The Institute of Image Information and Television Engineers ) 26 31 - 36 2002

Up to now a copying machine requires setting the document to the copy glass of the designated position. In addition to that, the copying machine cannot copy the non-flat shape document without distortion. So, we propose a next generation's document reader "Eye Scanner". The Eye Scanner is composed of the range finder, digital camera and pan-tilt stage system. Due to these devices, the Eye Scanner is able to read the document by the free viewpoint and able to generate the image which is not distorted by the geometric conversion. In this paper, we explain about the detail of the system. At the experiment, we show some result of distortion correction and show the result of image merging at divide capture.

DOI

Eigenspace approach for object recognition and its pose detection

Toshiyuki Amano, Akashi Yamaguchi, Seiji Inokuchi

Systems and Computers in Japan 31 ( 11 ) 60 - 69 2000.10

Range images are useful data in object recognition and pose detection. Most object recognition and pose detection techniques utilizing range images compare the geometrical features extracted from the range images to geometrical models. However, because of the difficulty in stabilizing feature extraction and the explosion in the matching combinations as the geometric models become complex, the subjects were restricted to geometrically simple objects. Previously, we proposed adapting eigenspace matching to object recognition and pose detection using range images and described eigenspace matching for range images with missing pixels. Since range images directly represent shape, by preparing the shape model of the target recognition object beforehand, virtual range images can be generated on a computer, and the eigenspace can be generated. If multiple range images are combined as the shape model, the cost of acquiring the learning samples, which is a problem in eigenspace matching, can be greatly reduced. In this paper, we focus on reducing the costs of acquiring learning samples for eigenspace matching and apply the eigenspace obtained by virtual learning to an actual range finder to demonstrate its effectiveness.

DOI

Object Search Using Range Images by the Eigenspace Approach.

天野敏之, 井口征士

電子情報通信学会論文誌 D-2 ( The Institute of Electronics, Information and Communication Engineers ) J83-D-2 ( 2 ) 584 - 592 2000.02 [Refereed]

距離画像は, 物体認識・姿勢検出を行う有効なデータである.距離画像を用いた物体認識・姿勢検出手法の多くは, 距離画像から抽出した幾何学的特徴量と幾何モデルとの照合を行っている.しかし, 特徴量の抽出を安定に行うことは困難であることや, 幾何モデルが複雑になると照合の組合せが膨大となることにより, 対象物体は幾何学的に単純な形状の物体に限られていた.我々は先に, 距離画像を用いた物体認識・姿勢検出において固有空間照合を適応することを提案し, 画素欠損を含む距離画像の固有空間照合法を示した.また, 固有空間照合の学習サンプル獲得コストの削減に的を絞って, 仮想的な学習で得られた固有空間を実際のレンジファインダへ応用してその有効性を調べた.本論文では, 仮想平行光学系とターンテーブルにより回転するレンジファインダを組み合せ, 平面上に配置された対象物体の物体認識・位置・姿勢検出への拡張を説明する.

　 PREV - NEXT 　

<AMANO Toshiyuki>

Published Papers - AMANO Toshiyuki