基于OpenCV(python)的实现文本分割之垂直投影法

import numpy as np 
import cv2 

def get_vvList(list_data):
    #取出list中像素存在的区间
    vv_list=list()
    v_list=list()
    for index,i in enumerate(list_data):
        if i>0:
            v_list.append(index)
        else:
            if v_list:
                vv_list.append(v_list)
                #list的clear与[]有区别
                v_list=[]
    return vv_list

if __name__=='__main__':
    img_bgr=cv2.imread('./testImg/2.png',1)
    if not img_bgr is None:
        img=img_bgr.copy()
        img_gray=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
        #二值化
        t,binary=cv2.threshold(img_gray,0,255,cv2.THRESH_OTSU+cv2.THRESH_BINARY)
        '''
        垂直投影为从上往下投射，统计每一列的黑色像素总数
        '''
        rows,cols=binary.shape
        ver_list=[0]*cols
        for j in range(cols):
            for i in range(rows):
                if binary.item(i,j)==0:
                    ver_list[j]=ver_list[j]+1
        '''
        对ver_list中的元素进行筛选，可以去除一些噪点
        '''
        ver_arr=np.array(ver_list)
        ver_arr[np.where(ver_arr<1)]=0
        ver_list=ver_arr.tolist()

        #绘制垂直投影
        img_white=np.ones(shape=(rows,cols),dtype=np.uint8)*255
        for j in range(cols):
            pt1=(j,rows-1)
            pt2=(j,rows-1-ver_list[j])
            cv2.line(img_white,pt1,pt2,(0,),1)
        cv2.imshow('垂直投影',img_white)
        cv2.waitKey(0)

        #切割单一字符
        vv_list=get_vvList(ver_list)
        for i in vv_list:
            img_ver=img_bgr[:,i[0]:i[-1]]
            cv2.imshow('单一字符',img_ver)
            cv2.waitKey(0)