基于CNN-PDE偏差異質擴散預處理的紅外圖像分水嶺分割

留言板

尊敬的讀者、作者、審稿人, 關于本刊的投稿、審稿、編輯和出版的任何問題, 您可以本頁添加留言。我們將盡快給您答復。謝謝您的支持!

姓名

郵箱

手機號碼

標題

留言內容

驗證碼

基金項目:

高等學校博士學科點專項科研基金資助項目(No.20020008004)

Infrared image watershed segmentation based on the preprocess by CNN-PDE bias-anisotropic diffusion filter

1. Information Engineering School, University of Science and Technology Beijing, Beijing 100083, China;
2. Department of Communications Engineering, Beijing Electronic Science Technology Institute, Beijing 150027, China;
3. Shandong Shengli Vocational College, Dongying 257062, China

摘要: 為了抑止采用分水嶺方法分割紅外圖像時的過分割現象,首先利用細胞神經網絡高效求解偏微分方程的能力,實現了可調偏差異質擴散濾波器并用其對圖像作預處理.為了消除噪聲殘留,引入了平滑系數與限制強度系數對梯度圖作閾值化處理.實際紅外圖像的分水嶺分割結果顯示,所提出的預處理方法能夠有效抑止過分割現象.
- 圖像分割 /
- 紅外圖像處理 /
- 細胞神經網絡 /
- 異質擴散 /
- 濾波器
Abstract: The watershed algorithm leads to over-segment when it was used to segment an infrared image. An adjustable bias-anisotropic diffusion filter based on CNN-PDE for smoothing an infrared image was studied. In order to remove the residual noise which can not be smoothed by filter, the smoothing coefficient and constrain coefficient were used to threshold the gradient image. The result of watershed segmentation of a practical infrared image shows the presented method can restrain over-segmentation effectively.
- image segmentation /
- infrared image processing /
- cellular neural networks /
- anisotropic diffusion /
- filter