台灣省糧食局每年採用航照遙測技術調查稻作,並以人工辨識航照方法,估算水稻田面積與產量。若發展適當的客觀分類辨識方法,將可減少時間、人力與物力之投入,且避免人為判釋上的主觀差異。本研究採用類神經網路,其模仿人類神經元記憶思考的處理模式與容錯性的特點,適合分類工具的發展。研究中,選用監督式理論較具代表的倒傳遞類神經網路,與混合監督式與非監督式的學習向量量化類神經網路,並採用兩種不同資料編碼輸入網路模式,分別針對彰化地區多時段SPOT衛星影像與多時段正規化差分植生指數影像作水稻田分類工作。分類成果與傳統高斯最大概似法相比較,最後並加入紋理影像輔助分類。研究結果就整體而言,類神經網路確實比傳統高斯最大概似分類法為佳,尤其以倒傳遞類神經網路最為有效,學習向量量化類神經網路改之。
Taiwan Provincial Food Department utilizes aerial photo interpretation for rice crop inventory each year to calculate the areas. If an automated classification method can be developed, the amount of time, manpower, and resources needed in the current work can be reduced . Meanwhi le, the errors caused by human subjective interpretation can be avoided . This research uses artificial neural network , which simulates human neuron and fault-tolerance for classification. In this study, error back-propagation (BP) and learning vector quantization (LVQ) neural network algorithms are selected. Meanwhile, two data coding techniques are applied for data representation to input network model. The data used in the experimen t are multi-temporal SPOT images and multi-temporal NDVI images of Changhua area. All the classification results are compared with those produced by Gaussian maximum likelihood algorithm . Finally, the contribution of texture images for classification are studied . In general, the experiments reveal that neural network approach es are better than maximum likelihood classification. Especially BP, and LVQ is thesecond best.