一般大眾學習認識鳥類多半從圖鑑書籍閱讀開始,到實地觀察比對而逐漸熟悉,但此種學習方式需要長時間的經驗與知識累積,難免讓初學者失去興趣。為克服此障礙,本論文嘗試發展自動辨識鳥類的方法,期望能透過手機捕捉鳥類影像而辨識出其所屬種類,藉以提供初學者的學習輔助。我們首先提出一種基於輪廓的鳥類辨識方法,從影像中取出鳥類的輪廓,透過主成分分析來降低複雜度,最後利用線性判斷分析來決定所屬鳥種。接著又提出另一種根據顏色和紋理的鳥類辨識方法,取出圖像中鳥類的顏色和紋理特徵,並利用k-近鄰演算法和k-means分群法來決定影像所屬鳥類。本論文從網路收集了大台北地區常見的 10種鳥類共 220張影像樣本,經測試後約可獲得70% 的辨識精確度。
A majority of people learn to recognize bird species by reading the illustrated Handbooks first and then doing field investigation again and again to become more and more familiar. However, such a learning procedure takes time and energy, which is usually an obstacle for a beginner. To alleviate this obstacle, this study attempts to develop automated methods for recognizing bird species from the captured images. The methods can be applied in mobile smart devices to help beginners learn the bird species efficiently. At first we proposed an algorithm to recognize bird species based on the feature of images’ edge, which uses Principle Component Analysis and Linear Discriminant Analysis to reduce the feature dimensionality and thereby classify the images. Then we proposed an alternative algorithm which captures the images’ features of color and texture and uses k-NN and k-means to classify the images. Experiments conducted using 220 images from 10 different bird species show that the highest recognition accuracy is 70%.