方挺 張亞萍
摘要:針對礦石圖像中鐵礦石相互粘連、大小不同、形態(tài)不規(guī)則等特點(diǎn),提出基于雙窗的局部均值閾值化算法,較好地將粘連的各礦石目標(biāo)相互分離。結(jié)合孔洞填充、距離變換等算法獲取礦石種子標(biāo)記圖像,利用基于標(biāo)記改進(jìn)的分水嶺算法完成礦石圖像分割。實(shí)驗(yàn)結(jié)果表明,該算法能有效分割粘連礦石,分割效果良好。
關(guān)鍵詞:礦石圖像分割;局部均值閾值化;孔洞填充;距離變換;分水嶺算法
DOIDOI:10.11907/rjdk.161258
中圖分類號(hào):TP317.4文獻(xiàn)標(biāo)識(shí)碼:A文章編號(hào):1672-7800(2016)006-0215-03
參考文獻(xiàn):
[1]TESSIER J,DUCHESNE C,BARTOLACCI G.A machine vision approach to on-line estimation of run-of-mine ore composition on conveyor belts[J].Minerals Engineering,2007,20(12): 1129-1144.
[2]PEREZ C A,ESTVEZ P A,VERA P A,et al.Ore grade estimation by feature selection and voting using boundary detection in digital image analysis[J].International Journal of Mineral Processing,2011,101(1-4): 28-36.
[3]SALINAS R,RAFF U,F(xiàn)ARFAN C.Automated estimation of rock fragment distributions using computer vision and its application in mining[J].IEE Proceedings-Vision,Image and Signal Processing,2005,152(1): 1-8.
[4]ZHANG G Y,LIU G Z,ZHU H.Segmentation algorithm of complex ore images based on templates transformation and reconstruction[J].International Journal of Minerals,Metallurgy,and Materials,2011,18(4): 385-389.
[5]王鳳娥.改進(jìn)后的分水嶺算法在圖像分割中的應(yīng)用研究[D].濟(jì)南:山東大學(xué),2008.
[6]CHATTERJEE S,BHATTACHERJEE A.Genetic algorithms for feature selection of image analysis-based quality monitoring model:an application to an iron mine[J].Engineering applications of artificial intelligence,2011,24(5): 786-795.
[7]朱聰.光學(xué)鏡片表面疵病檢測算法研究[D].成都:西南交通大學(xué),2014.
[8]BAILEY D G.An efficient euclidean distance transform[M].Combinatorial Image Analysis.Springer.2005: 394-408.