Python 分割扫描文档中的文本行
我试图找到一种方法来打破分割扫描文档中已自适应阈值的文本行。现在,我将文档的像素值存储为0到255之间的无符号整数,并取每行中像素的平均值,然后根据像素值的平均值是否大于250将这些行划分为多个范围,然后取每个范围的行的中值。但是,这种方法有时会失败,因为图像上可能有黑色斑点Python 分割扫描文档中的文本行,python,opencv,ocr,scikit-image,Python,Opencv,Ocr,Scikit Image,我试图找到一种方法来打破分割扫描文档中已自适应阈值的文本行。现在,我将文档的像素值存储为0到255之间的无符号整数,并取每行中像素的平均值,然后根据像素值的平均值是否大于250将这些行划分为多个范围,然后取每个范围的行的中值。但是,这种方法有时会失败,因为图像上可能有黑色斑点 warped = threshold_adaptive(warped, 250, offset = 10) warped = warped.astype("uint8") * 255 # get areas where
warped = threshold_adaptive(warped, 250, offset = 10)
warped = warped.astype("uint8") * 255
# get areas where we can split image on whitespace to make OCR more accurate
color_level = np.array([np.sum(line) / len(line) for line in warped])
cuts = []
i = 0
while(i < len(color_level)):
if color_level[i] > 250:
begin = i
while(color_level[i] > 250):
i += 1
cuts.append((i + begin)/2) # middle of the whitespace region
else:
i += 1
有没有更能抵抗噪音的方法来完成这项任务
编辑:这里有一些代码。“warped”是原始图像的名称,“cuts”是我想要分割图像的地方
warped = threshold_adaptive(warped, 250, offset = 10)
warped = warped.astype("uint8") * 255
# get areas where we can split image on whitespace to make OCR more accurate
color_level = np.array([np.sum(line) / len(line) for line in warped])
cuts = []
i = 0
while(i < len(color_level)):
if color_level[i] > 250:
begin = i
while(color_level[i] > 250):
i += 1
cuts.append((i + begin)/2) # middle of the whitespace region
else:
i += 1
warped=threshold\u自适应(warped,250,偏移=10)
翘曲=翘曲。aType(“uint8”)*255
#获取可以在空白处分割图像的区域,以使OCR更加准确
color_level=np.数组([np.总和(线)/len(线)表示扭曲的线])
削减=[]
i=0
而(i250:
begin=i
而(颜色级别[i]>250):
i+=1
剪切。追加((i+begin)/2)#空白区域的中间
其他:
i+=1
编辑2:添加示例图像
从输入图像中,需要将文本设置为白色,背景设置为黑色 然后需要计算账单的旋转角度。一种简单的方法是找到所有白点的
minareact
(findNonZero
),然后得到:
然后可以旋转帐单,使文本水平:
现在您可以计算水平投影(reduce
)。可以取每行的平均值。在直方图上应用阈值th
,以解释图像中的一些噪声(这里我使用了0
,即无噪声)。只有背景的行将有一个值>0
,文本行在直方图中有一个值0
。然后取直方图中每个连续的白色箱子序列的平均箱子坐标。这将是您线路的y
坐标:
这是代码。它是C++的,但是由于大部分工作都是用OpenCV函数,所以它很容易转换为Python。至少,您可以将其用作参考:
#include <opencv2/opencv.hpp>
using namespace cv;
using namespace std;
int main()
{
// Read image
Mat3b img = imread("path_to_image");
// Binarize image. Text is white, background is black
Mat1b bin;
cvtColor(img, bin, COLOR_BGR2GRAY);
bin = bin < 200;
// Find all white pixels
vector<Point> pts;
findNonZero(bin, pts);
// Get rotated rect of white pixels
RotatedRect box = minAreaRect(pts);
if (box.size.width > box.size.height)
{
swap(box.size.width, box.size.height);
box.angle += 90.f;
}
Point2f vertices[4];
box.points(vertices);
for (int i = 0; i < 4; ++i)
{
line(img, vertices[i], vertices[(i + 1) % 4], Scalar(0, 255, 0));
}
// Rotate the image according to the found angle
Mat1b rotated;
Mat M = getRotationMatrix2D(box.center, box.angle, 1.0);
warpAffine(bin, rotated, M, bin.size());
// Compute horizontal projections
Mat1f horProj;
reduce(rotated, horProj, 1, CV_REDUCE_AVG);
// Remove noise in histogram. White bins identify space lines, black bins identify text lines
float th = 0;
Mat1b hist = horProj <= th;
// Get mean coordinate of white white pixels groups
vector<int> ycoords;
int y = 0;
int count = 0;
bool isSpace = false;
for (int i = 0; i < rotated.rows; ++i)
{
if (!isSpace)
{
if (hist(i))
{
isSpace = true;
count = 1;
y = i;
}
}
else
{
if (!hist(i))
{
isSpace = false;
ycoords.push_back(y / count);
}
else
{
y += i;
count++;
}
}
}
// Draw line as final result
Mat3b result;
cvtColor(rotated, result, COLOR_GRAY2BGR);
for (int i = 0; i < ycoords.size(); ++i)
{
line(result, Point(0, ycoords[i]), Point(result.cols, ycoords[i]), Scalar(0, 255, 0));
}
return 0;
}
#包括
使用名称空间cv;
使用名称空间std;
int main()
{
//读取图像
Mat3b img=imread(“路径到图像”);
//二值化图像。文本为白色,背景为黑色
马特宾;
CVT颜色(img、bin、颜色为灰色);
bin=bin<200;
//查找所有白色像素
向量pts;
findNonZero(bin,pts);
//获取白色像素的旋转矩形
RotatedRect box=MinareRect(pts);
如果(box.size.width>box.size.height)
{
交换(box.size.width,box.size.height);
箱角+=90.f;
}
点2f顶点[4];
点(顶点);
对于(int i=0;i<4;++i)
{
线(img,顶点[i],顶点[(i+1)%4],标量(0,255,0));
}
//根据找到的角度旋转图像
Mat1b旋转;
Mat M=getRotationMatrix2D(box.center,box.angle,1.0);
翘曲仿射(bin,旋转,M,bin.size());
//计算水平投影
Mat1f horProj;
减少(旋转、水平、1、CV\u减少\u平均值);
//去除直方图中的杂音。白色区域标识空格行,黑色区域标识文本行
浮点数th=0;
Mat1b hist=horProj基本步骤
阅读来源
脱粒
找到米纳雷卡特
旋转矩阵的扭曲
查找并绘制上界和下界
而Python中的代码:
#!/usr/bin/python3
# 2018.01.16 01:11:49 CST
# 2018.01.16 01:55:01 CST
import cv2
import numpy as np
## (1) read
img = cv2.imread("img02.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
## (2) threshold
th, threshed = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY_INV|cv2.THRESH_OTSU)
## (3) minAreaRect on the nozeros
pts = cv2.findNonZero(threshed)
ret = cv2.minAreaRect(pts)
(cx,cy), (w,h), ang = ret
if w>h:
w,h = h,w
ang += 90
## (4) Find rotated matrix, do rotation
M = cv2.getRotationMatrix2D((cx,cy), ang, 1.0)
rotated = cv2.warpAffine(threshed, M, (img.shape[1], img.shape[0]))
## (5) find and draw the upper and lower boundary of each lines
hist = cv2.reduce(rotated,1, cv2.REDUCE_AVG).reshape(-1)
th = 2
H,W = img.shape[:2]
uppers = [y for y in range(H-1) if hist[y]<=th and hist[y+1]>th]
lowers = [y for y in range(H-1) if hist[y]>th and hist[y+1]<=th]
rotated = cv2.cvtColor(rotated, cv2.COLOR_GRAY2BGR)
for y in uppers:
cv2.line(rotated, (0,y), (W, y), (255,0,0), 1)
for y in lowers:
cv2.line(rotated, (0,y), (W, y), (0,255,0), 1)
cv2.imwrite("result.png", rotated)
!/usr/bin/python3
#2018.01.16 01:11:49 CST
#2018.01.16 01:55:01 CST
进口cv2
将numpy作为np导入
##(1)阅读
img=cv2.imread(“img02.jpg”)
灰色=cv2.CVT颜色(img,cv2.COLOR\U BGR2GRAY)
##(2)门槛
th,threshed=cv2.阈值(灰色,127,255,cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
##(3)NOZERO上的MINAREACT
pts=cv2.findNonZero(脱粒)
ret=cv2.尖塔(pts)
(cx,cy),(w,h),ang=ret
如果w>h:
w、 h=h,w
ang+=90
##(4)找到旋转矩阵,进行旋转
M=cv2.getRotationMatrix2D((cx,cy),ang,1.0)
旋转=cv2.翘曲仿射(脱粒,M,(img.形状[1],img.形状[0]))
##(5)找到并绘制每条线的上下边界
hist=cv2.缩小(旋转,1,cv2.缩小平均值)。重塑(-1)
th=2
H、 W=图像形状[:2]
uppers=[y代表范围(H-1)内的y,如果hist[y]th]
如果hist[y]>th和hist[y+1],则降低范围(H-1)中y的值=[y]如何裁剪第一行中的第一个字符并将其保存为图像,依此类推以下行?