python 计算积分图和haar特征的实例代码
下面的代码通过积分图计算一张图片的一种haar特征的所有可能的值。初步学习图像处理并尝试写代码,如有错误,欢迎指出。
importcv2 importnumpyasnp importmatplotlib.pyplotasplt # #计算积分图 # defintegral(img): integ_graph=np.zeros((img.shape[0],img.shape[1]),dtype=np.int32) forxinrange(img.shape[0]): sum_clo=0 foryinrange(img.shape[1]): sum_clo=sum_clo+img[x][y] integ_graph[x][y]=integ_graph[x-1][y]+sum_clo; returninteg_graph #TypesofHaar-likerectanglefeatures #------ #||| #|-|+| #||| #------ # #就算所有需要计算haar特征的区域 # defgetHaarFeaturesArea(width,height): widthLimit=width-1 heightLimit=height/2-1 features=[] forwinrange(1,int(widthLimit)): forhinrange(1,int(heightLimit)): wMoveLimit=width-w hMoveLimit=height-2*h forxinrange(0,wMoveLimit): foryinrange(0,hMoveLimit): features.append([x,y,w,h]) returnfeatures # #通过积分图特征区域计算haar特征 # defcalHaarFeatures(integral_graph,features_graph): haarFeatures=[] fornuminrange(len(features_graph)): #计算左面的矩形区局的像素和 haar1=integral_graph[features_graph[num][0]][features_graph[num][1]]-\ integral_graph[features_graph[num][0]+features_graph[num][2]][features_graph[num][1]]-\ integral_graph[features_graph[num][0]][features_graph[num][1]+features_graph[num][3]]+\ integral_graph[features_graph[num][0]+features_graph[num][2]][features_graph[num][1]+features_graph[num][3]] #计算右面的矩形区域的像素和 haar2=integral_graph[features_graph[num][0]][features_graph[num][1]+features_graph[num][3]]-\ integral_graph[features_graph[num][0]+features_graph[num][2]][features_graph[num][1]+features_graph[num][3]]-\ integral_graph[features_graph[num][0]][features_graph[num][1]+2*features_graph[num][3]]+\ integral_graph[features_graph[num][0]+features_graph[num][2]][features_graph[num][1]+2*features_graph[num][3]] #右面的像素和减去左面的像素和 haarFeatures.append(haar2-haar1) returnhaarFeatures img=cv2.imread("faces/face00001.bmp",0) integeralGraph=integral(img) featureAreas=getHaarFeaturesArea(img.shape[0],img.shape[1]) haarFeatures=calHaarFeatures(integeralGraph,featureAreas) print(haarFeatures)
以上这篇python计算积分图和haar特征的实例代码就是小编分享给大家的全部内容了,希望能给大家一个参考,也希望大家多多支持毛票票。
声明:本文内容来源于网络,版权归原作者所有,内容由互联网用户自发贡献自行上传,本网站不拥有所有权,未作人工编辑处理,也不承担相关法律责任。如果您发现有涉嫌版权的内容,欢迎发送邮件至:czq8825#qq.com(发邮件时,请将#更换为@)进行举报,并提供相关证据,一经查实,本站将立刻删除涉嫌侵权内容。