CAJ | 학술논문

复杂背景是影响场景文字自动定位算法性能的重要因素。为消除背景干扰，本文首先根据谱残差理论获取显著性区域，然后利用基于笔画特征的点对梯度方向差比例图与基于傅里叶谱统计特征的后验概率图取得显著性区域的文字置信图，最后借助图模型融合视觉显著性图、文字置信图与HSI颜色特征最终达到抑制自然图像背景并突出前景文字的效果。在ICDAR2011场景文字定位竞赛数据库与实验室场景中文数据库中的实验结果表明，本算法可较好的抑制自然图像中复杂背景，并有效提升算法的性能。
복잡배경시영향장경문자자동정위산법성능적중요인소。위소제배경간우，본문수선근거보잔차이론획취현저성구역，연후이용기우필화특정적점대제도방향차비례도여기우부리협보통계특정적후험개솔도취득현저성구역적문자치신도，최후차조도모형융합시각현저성도、문자치신도여HSI안색특정최종체도억제자연도상배경병돌출전경문자적효과。재ICDAR2011장경문자정위경새수거고여실험실장경중문수거고중적실험결과표명，본산법가교호적억제자연도상중복잡배경，병유효제승산법적성능。
The complex background is an important inference factor of scene text automatic localization algorithm .To elimi-nate the impact of background ,this scheme firstly obtains the saliency region in saliency map according to the spectral residual theo-ry .Then it computes text confidence map in saliency region ,which is weighted sum of the fraction map of corresponding pairs based on stroke feature and the posterior probability map based on Fourier spectrum statistical feature .Finally ,it combines saliency map , text confidence map and HSI color feature with the graph model to suppress the background and highlight the foreground text .The experimental results on both the ICDAR2011 scene text localization competition test dataset and laboratory Chinese dataset show that the scheme can effectively suppress the complex background and improve the scene text localization algorithm .