Publications/p2005nn
をテンプレートにして作成
[
トップ
] [
新規
|
一覧
|
検索
|
最終更新
|
ヘルプ
|
ログイン
]
開始行:
[[Publications]]
*''A robust classifier combined with an auto-associative ...
**Takashi TAKAHASHI and Takio KURITA [#od088bd4]
Neural Networks, vol.18, pp.958--966, 2005
**Abstract [#z866df50]
This paper describes an approach for constructing a class...
is unaffected by occlusions in images. We propose a meth...
integrating an auto-associative network into a simple cla...
the auto-associative network can recall the original imag...
partly occluded input image, we can employ it to detect o...
regions and complete the input image by replacing those r...
recalled pixels. By iterating this reconstruction proces...
integrated network is able to classify target objects wit...
robustly. To confirm the effectiveness of this method, w...
experiments involving face image classification. It is s...
classification performance is not decreased even if about...
the face image is occluded.
終了行:
[[Publications]]
*''A robust classifier combined with an auto-associative ...
**Takashi TAKAHASHI and Takio KURITA [#od088bd4]
Neural Networks, vol.18, pp.958--966, 2005
**Abstract [#z866df50]
This paper describes an approach for constructing a class...
is unaffected by occlusions in images. We propose a meth...
integrating an auto-associative network into a simple cla...
the auto-associative network can recall the original imag...
partly occluded input image, we can employ it to detect o...
regions and complete the input image by replacing those r...
recalled pixels. By iterating this reconstruction proces...
integrated network is able to classify target objects wit...
robustly. To confirm the effectiveness of this method, w...
experiments involving face image classification. It is s...
classification performance is not decreased even if about...
the face image is occluded.
ページ名: