<address id="fnnj5"><dfn id="fnnj5"></dfn></address>

<address id="fnnj5"><dfn id="fnnj5"></dfn></address>
<sub id="fnnj5"><dfn id="fnnj5"></dfn></sub>
<address id="fnnj5"><dfn id="fnnj5"></dfn></address>

<address id="fnnj5"><listing id="fnnj5"></listing></address>

    云南民族大學學報(自然科學版)

    2020, v.29;No.124(06) 601-606

    [打印本頁] [關閉]
    本期目錄(Current Issue) | 過刊瀏覽(Past Issue) | 高級檢索(Advanced Search)

    基于深度森林的視網膜血管分割算法
    Retinal vessel segmentation based on deep forest

    李志強;楊欣;吳臣桓;
    LI Zhi-qiang;YANG Xin;WU Chen-huan;College of Automation Engineering, Nanjing University of Aeronautics and Astronautics;

    摘要(Abstract):

    為提高診斷視網膜血管相關疾病的效率,提出了1種基于深度森林的視網膜血管分割算法.首先通過CLAHE算法對彩色眼底視網膜圖像進行增強處理;然后隨機選取部分圖像塊,并以圖像塊中心位置對應的標簽作為圖像塊的標簽對深度森林模型進行訓練;最后從測試圖像提取圖像塊送入訓練好的深度森林模型對圖像塊中心像素的標簽進行預測,從而完成視網膜血管分割.在DRIVE和STARE數據集上進行了性能驗證,平均準確率分別達到了0.937 5和0.946 1,實現了有效的視網膜血管分割.
    To improve the efficiency of diagnosing retinal vessel diseases, we propose a retinal vessel segmentation algorithm based on deep forest. First, we perform the augmentation on the color fundus retinal image through the CLAHE. Then we randomly select some image blocks, and adopt the label corresponding to the center of the image block as its label. On this basis, we train our deep-forest model. Finally, we distill the image blocks from the test image. They are sent to the trained model to predict the label of the central pixel, thus completing the retinal blood vessel segmentation. We validate our algorithm on the datasets DRIVE and STARE. The average accuracy is 0.937 5 and 0.946 1 respectively, realizing effective retinal vessel segmentation.

    關鍵詞(KeyWords): 視網膜血管分割;深度森林;集成學習
    retinal vessel segmentation;deep forest;ensemble learning

    Abstract:

    Keywords:

    基金項目(Foundation): 國家自然科學基金(61573182);; 中央高;究蒲袠I務費專項資金(NS2020025)

    作者(Author): 李志強;楊欣;吳臣桓;
    LI Zhi-qiang;YANG Xin;WU Chen-huan;College of Automation Engineering, Nanjing University of Aeronautics and Astronautics;

    Email:

    DOI:

    參考文獻(References):

    擴展功能
    本文信息
    服務與反饋
    本文關鍵詞相關文章
    本文作者相關文章
    中國知網
    分享
    新浪爱彩