文档图像的智能版面分析（SAC）技术研究

import numpy as np
import cv2
import sys
import matplotlib.pyplot as plt

img = cv2.imread(sys.argv[1],0)
h,w = img.shape[:2]
img = cv2.resize(img,(h//5,w//5),interpolation=cv2.INTER_CUBIC)
_,bin = cv2.threshold(img,128,255,cv2.THRESH_BINARY)
horizontal_sum = np.sum(bin, axis=1)
 
plt.plot(horizontal_sum, range(horizontal_sum.shape[0]))
plt.gca().invert_yaxis()
plt.show()

源码如下：

#coding:utf-8
'''
表格生成线条坐标
'''
import cv2
import numpy as np
from matplotlib import pyplot as plt
import json
import sys
import subprocess
import os
class detectTable(object):
    def __init__(self, src_img):
        self.src_img = src_img

    def run(self):
        if len(self.src_img.shape) == 2:  # 灰度图
            gray_img = self.src_img
        elif len(self.src_img.shape) ==3:
            gray_img = cv2.cvtColor(self.src_img, cv2.COLOR_BGR2GRAY)

        thresh_img = cv2.adaptiveThreshold(~gray_img,255,cv2.ADAPTIVE_THRESH_MEAN_C,cv2.THRESH_BINARY,15,-2)
        h_img = thresh_img.copy()
        v_img = thresh_img.copy()
        scale = 15
        h_size = int(h_img.shape[1]/scale)

        h_structure = cv2.getStructuringElement(cv2.MORPH_RECT,(h_size,1)) # 形态学因子
        h_erode_img = cv2.erode(h_img,h_structure,1)

        h_dilate_img = cv2.dilate(h_erode_img,h_structure,1)
        # cv2.imshow("h_erode",h_dilate_img)
        v_size = int(v_img.shape[0] / scale)

        v_structure = cv2.getStructuringElement(cv2.MORPH_RECT, (1, v_size))  # 形态学因子
        v_erode_img = cv2.erode(v_img, v_structure, 1)
        v_dilate_img = cv2.dilate(v_erode_img, v_structure, 1)

        mask_img = h_dilate_img+v_dilate_img
        joints_img = cv2.bitwise_and(h_dilate_img,v_dilate_img)
        joints_img = cv2.dilate(joints_img,None,iterations=3)
        cv2.imwrite("joints.png",~joints_img)
        cv2.imwrite("mask.png",~mask_img)

if __name__=='__main__':
    img = cv2.imread(sys.argv[1])
    detectTable(img).run()

基于惯性大水滴滴水算法和支持向量机的粘连字符验证码识别

代码地址：https://download.csdn.net/download/yinchuandong2/8062831
论文地址：https://download.csdn.net/download/yinchuandong2/8062837
博客地址：https://blog.csdn.net/yinchuandong2/article/details/40340735