A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack ...A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack algorithm. Then, feature propagation was conducted for feature enhancement, under the constraint of the layout relations. Next, candidate CCs were fed into classifiers with the enhanced feature vector. At last, a model-based hierarchical merging (MHM) procedure was presented to obtain understandable characters. The proposed merging algorithm utilized the constraint of text lines for specific languages and dynamically merges CCs into characters. The whole algorithm was evaluated at both pixel level and character level, experimental results showed that the proposed method is effective in detecting scene characters with significant geometric variations, uneven illumination, extremely low contrast and cluttered background.展开更多
目的借鉴欧洲基本健康模块(Minimum European Health Module,MEHM),设计合适的基本健康模块(Minimum Health Module,MHM),并验证其在人群健康综合测量中的可靠性。方法采用网格化分层抽样方法抽取调查对象后,随机抽取5%为此次方法验证...目的借鉴欧洲基本健康模块(Minimum European Health Module,MEHM),设计合适的基本健康模块(Minimum Health Module,MHM),并验证其在人群健康综合测量中的可靠性。方法采用网格化分层抽样方法抽取调查对象后,随机抽取5%为此次方法验证的试验对象,验证基本健康模块,选择自评健康、活动限制指标分别进行信度和效度评价,并计算分析居民自评健康和无活动限制健康状况。结果基本健康模块调查表总体自评健康、活动限制指标重测Kappa一致性系数分别为0.855、0.882,效标关联效度Gamma系数分别为0.899、0.974。现场调查质量控制指标符合要求。2016年宜昌市居民自评非健康率9.49%,长期活动限制3.08%。结论基本健康模块适合国内居民健康调查使用。建议全国统一地市级人群健康综合测量工具,明确健康综合测量指标类别,推荐采取类似欧盟的基本健康模块监测指标,并纳入中国居民健康核心指标体系。展开更多
文摘A new approach to extract and segment characters in natural scenes was proposed in this paper. First, a set of intrinsic features were calculated based on connected components (CCs) extracted by a non-linear Nilblack algorithm. Then, feature propagation was conducted for feature enhancement, under the constraint of the layout relations. Next, candidate CCs were fed into classifiers with the enhanced feature vector. At last, a model-based hierarchical merging (MHM) procedure was presented to obtain understandable characters. The proposed merging algorithm utilized the constraint of text lines for specific languages and dynamically merges CCs into characters. The whole algorithm was evaluated at both pixel level and character level, experimental results showed that the proposed method is effective in detecting scene characters with significant geometric variations, uneven illumination, extremely low contrast and cluttered background.
文摘目的借鉴欧洲基本健康模块(Minimum European Health Module,MEHM),设计合适的基本健康模块(Minimum Health Module,MHM),并验证其在人群健康综合测量中的可靠性。方法采用网格化分层抽样方法抽取调查对象后,随机抽取5%为此次方法验证的试验对象,验证基本健康模块,选择自评健康、活动限制指标分别进行信度和效度评价,并计算分析居民自评健康和无活动限制健康状况。结果基本健康模块调查表总体自评健康、活动限制指标重测Kappa一致性系数分别为0.855、0.882,效标关联效度Gamma系数分别为0.899、0.974。现场调查质量控制指标符合要求。2016年宜昌市居民自评非健康率9.49%,长期活动限制3.08%。结论基本健康模块适合国内居民健康调查使用。建议全国统一地市级人群健康综合测量工具,明确健康综合测量指标类别,推荐采取类似欧盟的基本健康模块监测指标,并纳入中国居民健康核心指标体系。
