基于神經(jīng)網(wǎng)絡(luò)和點的重要性度量的邊緣提取方法
THE METHOD OF EDGE DETECTION BASED ON NEURAL NETWORK AND THE MEASURE OF IMPORTANCE OF POINTS
-
摘要: 本文從邊緣點所在尺度和其鄰域的灰度分布狀況入手,提出了一個由四個分量組成的、對應(yīng)于點的、用于衡量該點重要性的邊緣重要性度量向量,為了考慮應(yīng)用背景,用人工分類好的樣本對一BP神經(jīng)網(wǎng)絡(luò)進(jìn)行訓(xùn)練,用訓(xùn)練好的網(wǎng)絡(luò)對圖像的邊緣點依重要性進(jìn)行分類,從而獲得圖像的重要邊緣。另外由于本文的方法無須對圖像進(jìn)行卷積,所以不會產(chǎn)生邊緣偏移。經(jīng)實驗驗證此方法取得了良好的效果。
-
關(guān)鍵詞:
- 邊緣檢測; 神經(jīng)網(wǎng)絡(luò); 重要性度量; 尺度
Abstract: Based on the scale and the state of intensity distribution in some neighborhoods of edge points, this paper proposes a measure vector of importance of point that consists of 4 components and corresponds to every point. For considering the background of application, this paper first trains a BP neural network using some samples that have classified by manual work, and then extracts more important edge points in a new image using the trained neural network. Because the image needs not be smoothed by some function in this algorithm, the edge deflection will not happen as usual, the location of gotten edge is in the accurate position. The effectiveness of this algorithm has been testified by some experiments. -
Mallat S. et al. Characterisitics of signals from multiscale edges. IEEE Trans. on PAMI, 1992,PAMI-14(7): 710-732.[2]Witkin A. Scale-space filtering, in Proc. Int. Joint Conf. Artifical Intell., Karlsrhue, Germany:1983, 1019-1022.[3]Bergholm F, Edge focusing, IEEE Trans. on PAMI, 1987, PAMI-9(6), 726-741.[4]楊烜,梁德群.基于方向信息的多尺度邊緣檢測方法,西安電子科技大學(xué)學(xué)報,1997,24(4),524-530[5]焦李成.神經(jīng)網(wǎng)絡(luò)理論.西安:西安電子科技大學(xué)出版社,1990,112-200. -
計量
- 文章訪問數(shù): 2177
- HTML全文瀏覽量: 98
- PDF下載量: 665
- 被引次數(shù): 0
下載:
