西安工业大学学报
西安工業大學學報
서안공업대학학보
JOURNAL OF XI'AN TECHNOLOGICAL UNIVERSITY
2015年
7期
546-549
,共4页
背景模型%目标检测%背景先验信息%颜色特征
揹景模型%目標檢測%揹景先驗信息%顏色特徵
배경모형%목표검측%배경선험신식%안색특정
background model%object detection%background priors%color feature
针对传统感兴趣目标检测算法未利用图像自身的先验信息，提出了一种结合图像背景先验信息及颜色特征的感兴趣算法。依据图像边缘区域为一般图像背景的特点，建立了图像背景模型，基于该模型考虑背景区域的差异性，有效避免了目标在图像边缘时造成的漏检现象。通过融合两种显著性特征，得到了最终感兴趣目标。实验结果表明：该算法检测感兴趣目标时，检测准确性较其他主流检测算法提高了10％。
針對傳統感興趣目標檢測算法未利用圖像自身的先驗信息，提齣瞭一種結閤圖像揹景先驗信息及顏色特徵的感興趣算法。依據圖像邊緣區域為一般圖像揹景的特點，建立瞭圖像揹景模型，基于該模型攷慮揹景區域的差異性，有效避免瞭目標在圖像邊緣時造成的漏檢現象。通過融閤兩種顯著性特徵，得到瞭最終感興趣目標。實驗結果錶明：該算法檢測感興趣目標時，檢測準確性較其他主流檢測算法提高瞭10％。
침대전통감흥취목표검측산법미이용도상자신적선험신식，제출료일충결합도상배경선험신식급안색특정적감흥취산법。의거도상변연구역위일반도상배경적특점，건립료도상배경모형，기우해모형고필배경구역적차이성，유효피면료목표재도상변연시조성적루검현상。통과융합량충현저성특정，득도료최종감흥취목표。실험결과표명：해산법검측감흥취목표시，검측준학성교기타주류검측산법제고료10％。
Since the image’s ow n prior information is not used by the traditional salient object detection algorithm ,an algorithm is proposed w hich combines the prior information on the image background with the color features .Based on the features of image edge region being the general image background ,an image background model is built .Because the regional differences in the background are considered in the model ,missing the objects in the edges of the image can be avoided .Then the two significant features are fused to obtain the final goal .Experimental results show that this algorithm increases the detection accuracy by 10% compared with other popular detection algorithms .
