计算机科学
計算機科學
계산궤과학
COMPUTER SCIENCE
2009年
12期
248-250,262
,共4页
吴定雪%龚俊彬%徐宏波%田金文
吳定雪%龔俊彬%徐宏波%田金文
오정설%공준빈%서굉파%전금문
图像匹配%点特征%角点%旋转不变性
圖像匹配%點特徵%角點%鏇轉不變性
도상필배%점특정%각점%선전불변성
Image matching%Point-feature%Corner point%Rotation invariance
图像匹配在模式识别、图像分析和计算机视觉中有着广泛的应用.图像匹配是将模板在参考图中逐像素移动,计算它们的灰度相似性,搜索相似性最大的位置.这种逐像素的搜索方法计算复杂度高.如果模板和参考图之间存在旋转,传统的匹配方法很难实时实现.提出了一种基于点特征的旋转图像的匹配方法,首先采用Harris角点检测算子提取图像的特征点,然后利用小面模型对特征点邻域进行拟合,提取特征点的旋转不变特征,最后利用特征点的旋转不变特征进行点集的匹配,获取图像的平移和旋转参数.该方法匹配结果准确,与传统的相关匹配方法相比计算复杂度很小,易于实时实现.
圖像匹配在模式識彆、圖像分析和計算機視覺中有著廣汎的應用.圖像匹配是將模闆在參攷圖中逐像素移動,計算它們的灰度相似性,搜索相似性最大的位置.這種逐像素的搜索方法計算複雜度高.如果模闆和參攷圖之間存在鏇轉,傳統的匹配方法很難實時實現.提齣瞭一種基于點特徵的鏇轉圖像的匹配方法,首先採用Harris角點檢測算子提取圖像的特徵點,然後利用小麵模型對特徵點鄰域進行擬閤,提取特徵點的鏇轉不變特徵,最後利用特徵點的鏇轉不變特徵進行點集的匹配,穫取圖像的平移和鏇轉參數.該方法匹配結果準確,與傳統的相關匹配方法相比計算複雜度很小,易于實時實現.
도상필배재모식식별、도상분석화계산궤시각중유착엄범적응용.도상필배시장모판재삼고도중축상소이동,계산타문적회도상사성,수색상사성최대적위치.저충축상소적수색방법계산복잡도고.여과모판화삼고도지간존재선전,전통적필배방법흔난실시실현.제출료일충기우점특정적선전도상적필배방법,수선채용Harris각점검측산자제취도상적특정점,연후이용소면모형대특정점린역진행의합,제취특정점적선전불변특정,최후이용특정점적선전불변특정진행점집적필배,획취도상적평이화선전삼수.해방법필배결과준학,여전통적상관필배방법상비계산복잡도흔소,역우실시실현.
Template matching has many applications in signal processing, image processing, pattern recognition,and video compressing.It fund a desired template in the large reference image by sliding the template window in a pixel-by-pixel basis,computing the degree of similarity between them,and searching position with the largest similarity measurement.It is computationally expensive to search for every possible position of the template window within the larger reference image.When having a rotation between the template and the reference image, the conventional template matching algorithm described above is not practical for real-time processing.In this paper, a point-matching algorithm was proposed to match the rotated template, which included:firstly, the feature points were detected by Harris detector, then the facet model was used to approximate locally the image intensity function,and the rotation-invariability of the feature point was extracted,finally, the transformation(translation and rotation) was obtained by matching feature points.Results have shown the efficacy of the proposed method.