查詢結果分析
相關文獻
- 應用影像紋理分析及類神經網路辨識甘藍種苗之生長階段
- 利用三維形態分析方法診斷肺臟腫瘤
- 坡地利用影響山崩潛勢之評估模式建置--以寶來地區歷經莫拉克颱風為例
- Neural Network Procedures for Taguchi's Dynamic Problems
- A Fast and Efficient Competitive Learning Design Algorithm Based on Weight Vector Training in Transform Domain
- 專家系統振動訊號圖型判別之研究
- 反傳遞模糊類神經網路於流量推估之應用
- 類神經網路(Neural Networks)的種類及其在影像處理上的應用
- C++Fuzzy類神經網路物件導向發展系統之建立
- 臺灣汽保費率之估計--對數線性費率模式與類神經網路之比較
頁籤選單縮合
題 名 | 應用影像紋理分析及類神經網路辨識甘藍種苗之生長階段=Application of Image Texture Analysis and Neural Network on the Growth Stage Recognition for Head Cabbage Seedlings |
---|---|
作 者 | 謝清祿; 鄭聖夫; 林達德; | 書刊名 | 農業機械學刊 |
卷 期 | 6:2 1997.06[民86.06] |
頁 次 | 頁1-13 |
分類號 | 435.233 |
關鍵詞 | 紋理分析; 類神經網路; 甘藍種苗; Texture analysis; Neural network; Head cabbage seedlings; |
語 文 | 中文(Chinese) |
中文摘要 | 本研究應用影像紋理分析原理,計算甘藍穴盤種苗影像之均均度、熵、最大機率 對比、k 階反向差衡量、相關度、行長機率、同質度、及群聚傾向度等九項紋理特徵,並結 合倒傳遞類神經網路,發展辨識甘藍種苗不同生長階段之法則,以自動辨識甘藍種苗一片本 葉到五片本葉等五個不同生長階段。經分別試驗比較原始資料轉換方式、取樣影像大小與灰 階、共生矩陣計算方向及樣本平均等有關影像處理之因子,及隱藏層數、節點數及訓練次數 等類神經網路結構因子,獲知原始資料處理以經移位化處理可得較佳收斂值及辨識率,較佳 的影像取樣大小及樣本灰階在類神經網路訓練後之收斂值與較差者比較相差五倍以上,顯示 此二因子影響辨識率甚大。網路結構中以具二層隱藏層,節點數分別為 7、5 者較適用,同 時訓練次數不可太多以免造成過度訓練降低辨識度。辨識法則之最佳組合因子為採用 32 灰 階之 128x128 影像為紋理分析樣本,共生矩陣計算方向為對角線方向, 所求得之特徵值經 移位化做平均處理者,在網路訓練次數為 10 萬次,對於甘藍種苗生長階段之正確辨識率可 達 88.9%,而主要辨識誤差多發生在穴盤苗較茂密的第四葉與第五葉階段。 |
英文摘要 | Image texture analysis was employed in this study for automatic recognition of growth stage of head cabbage seedlings in a nursery tray. Nine textural features such as uniformity, entropy, maximum probability, inverse different moment of order k, correlation, probability of a run length, homogeneity, cluster tendency were determined and fed to back propagation neural network to predict seedling growth stage from one leaf to five leaves. Factors affecting the accuracy of the recognition algorithm were examined. They were input data transformation, sample image resolution and gray scale, coocurrence matrix direction operator, sample image averaging, neural network structure and training epochs. The tests revealed that data transformation with offsetting and averaging, higher sampled image resolution and gray scale yielded better network training convergence. Several network structures were also tested and compared. Among them, network structure with two hidden layers of 7-5 nodes showed better performance. However, over-training should be avoid to secure the recongnition accuracy. The best combination for the recogition algorithm was tested and selected. With sampled image resolution of 128x128, 32 gray-scale, diagonal position operator for the co-occurrence matrix, 100 thousand training epochs with two hiden layers of 7-5 nodes, 88.9% recognition rate was achieved in identifying the seedling growth stages when the nursery trays were densely covered with seedling leaves. |
本系統中英文摘要資訊取自各篇刊載內容。