投影法多用于圖像的閾值分割。閑話不多說，現用Python實現。

上代碼。

import cv2import numpyimg = cv2.imread('D:/0.jpg', cv2.COLOR_BGR2GRAY)height, width = img.shape[:2]#resized = cv2.resize(img, (3*width,3*height), interpolation=cv2.INTER_CUBIC)#二值化(_, thresh) = cv2.threshold(img, 150, 255, cv2.THRESH_BINARY) #cv2.imshow('thresh', thresh)#擴大黑色面積，使效果更明顯kernel = cv2.getStructuringElement(cv2.MORPH_RECT, (10, 10))#形態學處理，定義矩形結構closed = cv2.erode(thresh, None, iterations = 5)cv2.imshow('erode',closed)height, width = closed.shape[:2]v = [0]*widthz = [0]*heighta = 0#垂直投影#統計并存儲每一列的黑點數for x in range(0, width):     for y in range(0, height):  if closed[y,x][0] == 0:   a = a + 1  else :   continue v[x] = a a = 0l = len(v)#print l#print width#創建空白圖片，繪制垂直投影圖emptyImage = numpy.zeros((height, width, 3), numpy.uint8) for x in range(0,width): for y in range(0, v[x]):  b = (255,255,255)  emptyImage[y,x] = bcv2.imshow('chuizhi', emptyImage)#水平投影#統計每一行的黑點數a = 0emptyImage1 = numpy.zeros((height, width, 3), numpy.uint8) for y in range(0, height): for x in range(0, width):  if closed[y,x][0] == 0:   a = a + 1  else :   continue z[y] = a a = 0l = len(z)#print l#print height#繪制水平投影圖for y in range(0,height): for x in range(0, z[y]):  b = (255,255,255)  emptyImage1[y,x] = bcv2.imshow('shuipin', emptyImage1)cv2.waitKey(0)

原圖

垂直投影圖

水平投影圖

由這兩圖可以確定我們所需的分割點，從而可以進行下一步的文本分割。這將在下一篇博客中實現。

以上這篇Python實現投影法分割圖像示例就是小編分享給大家的全部內容了，希望能給大家一個參考，也希望大家多多支持武林網之家。