平成１７年１月４日
　会　 員 　各 　位

                                        計測自動制御学会北海道支部


　　　計測自動制御学会北海道支部後援講演会のお知らせ

　下記により本支部が後援する講演会が開催されます。多数ご参加くださいま
すようご案内申し上げます。

                                記

講演題目：「Biologically Inspired Active Vision System Based on 
　　        Selective Attention」

講師：Prof. Minho Lee, Kyungpook National University

日時：平成１７年１月１４日（金）１３：００〜１４：１５

場所：北海道大学大学院情報科学研究科棟　A-13教室
    　(JR札幌駅北口よりタクシーで10分）
　　　〒060-1408　札幌市北区北14条西9丁目
　　　http://www.ist.hokudai.ac.jp/map/

主催：IEEE Computational Intelligence Society Japan Chapter(CIS-Japan)
　　　および IEEE 札幌支部

参加費：無料（参加資格を問いません）
事前申込の有無：なし

概要：
In this talk, I explain a biologically motivated active system 
based on human-like bottom-up saliency map model together with 
top-down attention through human interaction.  The proposed 
model uses a trainable selective attention model that can 
inhibit an unwanted salient area and only focus on an 
interesting area in a static natural scene.  The proposed 
model was implemented by the bottom-up saliency map model in 
conjunction with the fuzzy adaptive resonance theory (ART) 
network.  The bottom-up saliency map model generates a salient 
area based on intensity, edge, color and symmetry feature maps, 
and human supervisor decides whether the selected salient area 
is important.  If the selected area is not interesting, the ART 
network trains and memorizes that area, and also generates an 
inhibit signal so that the bottom-up saliency map model does 
not have attention to an area with similar characteristic in 
subsequent visual search process. Also, we applied the proposed 
selective attention model to various image processing problems 
such as image compression, image watermarking, vergence control, 
tracking a pedestrian and detect or localize faces in nature 
input scene.  Moreover, I explain the application of the 
proposed system for autonomous mental development system.  
Computer experimental results show that the proposed model 
outperforms the conventional approaches. 

問合せ先：北海道大学大学院情報科学研究科
　　　　　複雑系工学講座
　　　　　大森隆司
          E-mail: omori@complex.eng.hokudai.ac.jp