We adopt two different characteristic extracting methods and recognition algorithms accordingly . thirdly , we researched the neutral network algorithm and its improvement algorithm , designed a bp neutral network , which could apply in chinese handwritten recognition 汉字识别的分类算法包括对汉字进行粗分类和细分类,在不同的分类方法中各采用两种互补的特征抽取算法,并相应地在识别上采用不同的策略。
The model made rough classification to the human ears first according to their geometric features , then ica was used to extract the algebra features and support vector machine ( svm ) was for detailed classification , finally the results were achieved , which was in accordance with human natural recognition process 该模型首先根据人耳的几何特征对人耳进行粗分类;然后应用独立分量分析的方法提取代数特征,支持向量机进行细分类,最后给出分类结果。
A algorithm of shot coarse classification is proposed , firstly , key frames are extracted in equal interval in a shot ; then for a frame , dominant colors are obtained by hue , furthermore , the variance of dominant colors and ratio of clustered colors are computed , by which the corresponding frame could be classified into playing or non - playing frame , finally , a shot could be classified by the percentage of playing frames 2 .在镜头粗分类中,首先在每个镜头内等间隔地提取关键帧,随后得出主颜色序列,并对主颜色序列进行方差统计和聚类颜色比率的计算,最后依据比赛帧比率来进行镜头分类。
There are three steps in the combined . firstly , the template matching method is used to classify roughly in the first step ; secondly , the fuzzy pattern recognition method which are connected paralled is used to classify finely ; at last , the third classifier , which input is the output of the second classifiers , raise one ’ s hand as its decision rules 第一级分类器采用模板匹配法进行粗分类;第二级分类器由并行的模糊模式识别分类器组成,进行细分类;第三级分类器是综合分类器,它将第二级的输出作为输入,根据举手表决规则得到最后的输出结果。