计算机工程与应用
計算機工程與應用
계산궤공정여응용
Computer Engineering and Applications
2015年
21期
177-184
,共8页
模板匹配%圆投影变换%高斯混合模型%聚类特征%光照鲁棒
模闆匹配%圓投影變換%高斯混閤模型%聚類特徵%光照魯棒
모판필배%원투영변환%고사혼합모형%취류특정%광조로봉
template matching%Radical Projection Transform(RPT)%Gaussian mixture model%clustering feature%illumi-nation robustness
针对圆投影模板匹配方法特征提取过程中损失大量图像信息的缺点，提出了结合聚类模型参数的线性光照鲁棒圆投影模板匹配方法。所提方法采用线性对比度拉伸来消除光照影响，并将模板图像各圆环内像素点的高斯混合模型聚类参数作为模板特征。匹配时通过一次迭代计算即可得到匹配误差，且该匹配过程可通过查找表来提高匹配速度。在目标搜索时使用了降采样搜索方法，并将降采样搜索匹配后各位置的误差均值作为自适应阈值，对匹配误差小于该阈值的降采样点邻域进行逐点匹配，匹配误差最小的位置作为最终匹配结果。试验及分析说明所提方法的定位误差及可靠度与基于归一化相关及均值的圆投影匹配算法相比有较大提高。
針對圓投影模闆匹配方法特徵提取過程中損失大量圖像信息的缺點，提齣瞭結閤聚類模型參數的線性光照魯棒圓投影模闆匹配方法。所提方法採用線性對比度拉伸來消除光照影響，併將模闆圖像各圓環內像素點的高斯混閤模型聚類參數作為模闆特徵。匹配時通過一次迭代計算即可得到匹配誤差，且該匹配過程可通過查找錶來提高匹配速度。在目標搜索時使用瞭降採樣搜索方法，併將降採樣搜索匹配後各位置的誤差均值作為自適應閾值，對匹配誤差小于該閾值的降採樣點鄰域進行逐點匹配，匹配誤差最小的位置作為最終匹配結果。試驗及分析說明所提方法的定位誤差及可靠度與基于歸一化相關及均值的圓投影匹配算法相比有較大提高。
침대원투영모판필배방법특정제취과정중손실대량도상신식적결점，제출료결합취류모형삼수적선성광조로봉원투영모판필배방법。소제방법채용선성대비도랍신래소제광조영향，병장모판도상각원배내상소점적고사혼합모형취류삼수작위모판특정。필배시통과일차질대계산즉가득도필배오차，차해필배과정가통과사조표래제고필배속도。재목표수색시사용료강채양수색방법，병장강채양수색필배후각위치적오차균치작위자괄응역치，대필배오차소우해역치적강채양점린역진행축점필배，필배오차최소적위치작위최종필배결과。시험급분석설명소제방법적정위오차급가고도여기우귀일화상관급균치적원투영필배산법상비유교대제고。
To overcome the information loss in radical-projection-transform template matching algorithm, the proposed method introduces the clustering model parameters robust to linear illumination. The method eliminates the influence of illumination by linear contrast stretch, and takes the Gaussian mixture model clustering result as the template image feature. The matching errors are obtained by once iterative, and the iterative calculation can be implemented by using a simple look-up table. In searching stage, down sampling matching strategy is used to reduce computation cost and the average error of this stage is set to an adaptive threshold for precise matching. Then, the pixel-wise matching is operated in the neighbor-hood of the down sampling point whose error is less than the threshold, and finally the point of minimum error is set to be the target position. The test shows that the proposed method has better positioning accuracy and reliability than the nor-malized correlation based radical-projection-transform template matching algorithm.
