我正在尝试在OpenCV-Python(cv2)中实现“数字识别OCR”。它仅用于学习目的。我想在OpenCV中学习KNearest和SVM功能。
我有每个数字的100个样本(即图像)。我想和他们一起训练。
OpenCV示例附带了一个示例letter_recog.py
。但我仍然无法弄清楚如何使用它。我不明白什么是样本,响应等。另外,它首先加载一个txt文件,我首先不明白。
稍后搜索一下,我可以在cpp示例中找到letter_recognition.data。我使用它并在letter_recog.py模型中为cv2.KNearest创建了一个代码(仅用于测试):
import numpy as np
import cv2
fn = 'letter-recognition.data'
a = np.loadtxt(fn, np.float32, delimiter=',', converters={ 0 : lambda ch : ord(ch)-ord('A') })
samples, responses = a[:,1:], a[:,0]
model = cv2.KNearest()
retval = model.train(samples,responses)
retval, results, neigh_resp, dists = model.find_nearest(samples, k = 10)
print results.ravel()
它给了我一个20000的数组,我不明白它是什么。
问题:
1)letter_recognition.data文件是什么?如何从我自己的数据集构建该文件?
2)results.reval()
表示什么?
3)我们如何使用letter_recognition.data文件(KNearest或SVM)编写简单的数字识别工具?
答案 0 :(得分:484)
好吧,我决定在我的问题上自己解决以解决上述问题。我想要的是在OpenCV中使用KNearest或SVM功能实现简化的OCR。下面是我做了什么以及如何做。 (它仅用于学习如何将KNearest用于简单的OCR目的)。
1)我的第一个问题是关于OpenCV样本附带的letter_recognition.data文件。我想知道那个文件里面有什么。
它包含一个字母,以及该字母的16个特征。
this SOF
帮我找到了它。这些16个特征在论文Letter Recognition Using Holland-Style Adaptive Classifiers
中有解释。
(虽然我最后还不了解其中的一些功能)
2)因为我知道,如果不了解所有这些功能,就很难做到这一点。我试了一些其他的论文,但对初学者来说都有点困难。
So I just decided to take all the pixel values as my features.
(我并不担心准确性或性能,我只是希望它起作用,至少准确度最低)
我在下面拍摄了我的训练数据:
(我知道训练数据的数量较少。但是,由于所有字母都是相同的字体和大小,我决定试试这个。)
为了准备培训数据,我在OpenCV中编写了一个小代码。它做了以下事情:
key press manually
。这次我们自己按数字键对应于框中的字母。在手动数字分类结束时,列车数据(train.png)中的所有数字都由我们自己手动标记,图像如下所示:
以下是我用于上述目的的代码(当然,不是那么干净):
import sys
import numpy as np
import cv2
im = cv2.imread('pitrain.png')
im3 = im.copy()
gray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),0)
thresh = cv2.adaptiveThreshold(blur,255,1,1,11,2)
################# Now finding Contours ###################
contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
samples = np.empty((0,100))
responses = []
keys = [i for i in range(48,58)]
for cnt in contours:
if cv2.contourArea(cnt)>50:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>28:
cv2.rectangle(im,(x,y),(x+w,y+h),(0,0,255),2)
roi = thresh[y:y+h,x:x+w]
roismall = cv2.resize(roi,(10,10))
cv2.imshow('norm',im)
key = cv2.waitKey(0)
if key == 27: # (escape to quit)
sys.exit()
elif key in keys:
responses.append(int(chr(key)))
sample = roismall.reshape((1,100))
samples = np.append(samples,sample,0)
responses = np.array(responses,np.float32)
responses = responses.reshape((responses.size,1))
print "training complete"
np.savetxt('generalsamples.data',samples)
np.savetxt('generalresponses.data',responses)
现在我们进入培训和测试部分。
对于测试我在下面使用的部分,我用来训练的字母类型相同。
我们按照以下方式进行培训:
出于测试目的,我们执行以下操作:
我在下面的单个代码中包含了最后两个步骤(培训和测试):
import cv2
import numpy as np
####### training part ###############
samples = np.loadtxt('generalsamples.data',np.float32)
responses = np.loadtxt('generalresponses.data',np.float32)
responses = responses.reshape((responses.size,1))
model = cv2.KNearest()
model.train(samples,responses)
############################# testing part #########################
im = cv2.imread('pi.png')
out = np.zeros(im.shape,np.uint8)
gray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
thresh = cv2.adaptiveThreshold(gray,255,1,1,11,2)
contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
for cnt in contours:
if cv2.contourArea(cnt)>50:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>28:
cv2.rectangle(im,(x,y),(x+w,y+h),(0,255,0),2)
roi = thresh[y:y+h,x:x+w]
roismall = cv2.resize(roi,(10,10))
roismall = roismall.reshape((1,100))
roismall = np.float32(roismall)
retval, results, neigh_resp, dists = model.find_nearest(roismall, k = 1)
string = str(int((results[0][0])))
cv2.putText(out,string,(x,y+h),0,1,(0,255,0))
cv2.imshow('im',im)
cv2.imshow('out',out)
cv2.waitKey(0)
它有效,下面是我得到的结果:
这里它以100%的准确度工作。我认为这是因为所有数字都是相同种类和相同的大小。
但无论如何,这对初学者来说是个好开始(我希望如此)。
答案 1 :(得分:47)
对于那些对C ++代码感兴趣的人可以参考下面的代码。 感谢 Abid Rahman 提供了很好的解释。
程序与上述相同,但轮廓查找仅使用第一层级轮廓,因此算法仅对每个数字使用外轮廓。
//Process image to extract contour
Mat thr,gray,con;
Mat src=imread("digit.png",1);
cvtColor(src,gray,CV_BGR2GRAY);
threshold(gray,thr,200,255,THRESH_BINARY_INV); //Threshold to find contour
thr.copyTo(con);
// Create sample and label data
vector< vector <Point> > contours; // Vector for storing contour
vector< Vec4i > hierarchy;
Mat sample;
Mat response_array;
findContours( con, contours, hierarchy,CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE ); //Find contour
for( int i = 0; i< contours.size(); i=hierarchy[i][0] ) // iterate through first hierarchy level contours
{
Rect r= boundingRect(contours[i]); //Find bounding rect for each contour
rectangle(src,Point(r.x,r.y), Point(r.x+r.width,r.y+r.height), Scalar(0,0,255),2,8,0);
Mat ROI = thr(r); //Crop the image
Mat tmp1, tmp2;
resize(ROI,tmp1, Size(10,10), 0,0,INTER_LINEAR ); //resize to 10X10
tmp1.convertTo(tmp2,CV_32FC1); //convert to float
sample.push_back(tmp2.reshape(1,1)); // Store sample data
imshow("src",src);
int c=waitKey(0); // Read corresponding label for contour from keyoard
c-=0x30; // Convert ascii to intiger value
response_array.push_back(c); // Store label to a mat
rectangle(src,Point(r.x,r.y), Point(r.x+r.width,r.y+r.height), Scalar(0,255,0),2,8,0);
}
// Store the data to file
Mat response,tmp;
tmp=response_array.reshape(1,1); //make continuous
tmp.convertTo(response,CV_32FC1); // Convert to float
FileStorage Data("TrainingData.yml",FileStorage::WRITE); // Store the sample data in a file
Data << "data" << sample;
Data.release();
FileStorage Label("LabelData.yml",FileStorage::WRITE); // Store the label data in a file
Label << "label" << response;
Label.release();
cout<<"Training and Label data created successfully....!! "<<endl;
imshow("src",src);
waitKey();
Mat thr,gray,con;
Mat src=imread("dig.png",1);
cvtColor(src,gray,CV_BGR2GRAY);
threshold(gray,thr,200,255,THRESH_BINARY_INV); // Threshold to create input
thr.copyTo(con);
// Read stored sample and label for training
Mat sample;
Mat response,tmp;
FileStorage Data("TrainingData.yml",FileStorage::READ); // Read traing data to a Mat
Data["data"] >> sample;
Data.release();
FileStorage Label("LabelData.yml",FileStorage::READ); // Read label data to a Mat
Label["label"] >> response;
Label.release();
KNearest knn;
knn.train(sample,response); // Train with sample and responses
cout<<"Training compleated.....!!"<<endl;
vector< vector <Point> > contours; // Vector for storing contour
vector< Vec4i > hierarchy;
//Create input sample by contour finding and cropping
findContours( con, contours, hierarchy,CV_RETR_CCOMP, CV_CHAIN_APPROX_SIMPLE );
Mat dst(src.rows,src.cols,CV_8UC3,Scalar::all(0));
for( int i = 0; i< contours.size(); i=hierarchy[i][0] ) // iterate through each contour for first hierarchy level .
{
Rect r= boundingRect(contours[i]);
Mat ROI = thr(r);
Mat tmp1, tmp2;
resize(ROI,tmp1, Size(10,10), 0,0,INTER_LINEAR );
tmp1.convertTo(tmp2,CV_32FC1);
float p=knn.find_nearest(tmp2.reshape(1,1), 1);
char name[4];
sprintf(name,"%d",(int)p);
putText( dst,name,Point(r.x,r.y+r.height) ,0,1, Scalar(0, 255, 0), 2, 8 );
}
imshow("src",src);
imshow("dst",dst);
imwrite("dest.jpg",dst);
waitKey();
在结果中,第一行中的点被检测为8,并且我们没有训练过点。此外,我正在考虑第一层次级别中的每个轮廓作为样本输入,用户可以通过计算区域来避免它。
答案 2 :(得分:11)
如果您对机器学习的最新技术感兴趣,您应该研究深度学习。您应该拥有支持GPU的CUDA,或者在Amazon Web Services上使用GPU。
Google Udacity使用Tensor Flow提供了一个很好的教程。本教程将教您如何在手写数字上训练自己的分类器。使用Convolutional Networks,我在测试集上获得了超过97%的准确度。
答案 3 :(得分:1)
我在生成训练数据时遇到了一些问题,因为有时很难识别最后一个选定的字母,所以我将图像旋转了 1.5 度。现在每个字符都是按顺序选择的,训练后测试仍然显示 100% 的准确率。代码如下:
import numpy as np
import cv2
def rotate_image(image, angle):
image_center = tuple(np.array(image.shape[1::-1]) / 2)
rot_mat = cv2.getRotationMatrix2D(image_center, angle, 1.0)
result = cv2.warpAffine(image, rot_mat, image.shape[1::-1], flags=cv2.INTER_LINEAR)
return result
img = cv2.imread('training_image.png')
cv2.imshow('orig image', img)
whiteBorder = [255,255,255]
# extend the image border
image1 = cv2.copyMakeBorder(img, 80, 80, 80, 80, cv2.BORDER_CONSTANT, None, whiteBorder)
# rotate the image 1.5 degrees clockwise for ease of data entry
image_rot = rotate_image(image1, -1.5)
#crop_img = image_rot[y:y+h, x:x+w]
cropped = image_rot[70:350, 70:710]
cv2.imwrite('rotated.png', cropped)
cv2.imshow('rotated image', cropped)
cv2.waitKey(0)
对于示例数据,我对脚本进行了一些更改,如下所示:
import sys
import numpy as np
import cv2
def sort_contours(contours, x_axis_sort='LEFT_TO_RIGHT', y_axis_sort='TOP_TO_BOTTOM'):
# initialize the reverse flag
x_reverse = False
y_reverse = False
if x_axis_sort == 'RIGHT_TO_LEFT':
x_reverse = True
if y_axis_sort == 'BOTTOM_TO_TOP':
y_reverse = True
boundingBoxes = [cv2.boundingRect(c) for c in contours]
# sorting on x-axis
sortedByX = zip(*sorted(zip(contours, boundingBoxes),
key=lambda b:b[1][0], reverse=x_reverse))
# sorting on y-axis
(contours, boundingBoxes) = zip(*sorted(zip(*sortedByX),
key=lambda b:b[1][1], reverse=y_reverse))
# return the list of sorted contours and bounding boxes
return (contours, boundingBoxes)
im = cv2.imread('rotated.png')
im3 = im.copy()
gray = cv2.cvtColor(im,cv2.COLOR_BGR2GRAY)
blur = cv2.GaussianBlur(gray,(5,5),0)
thresh = cv2.adaptiveThreshold(blur,255,1,1,11,2)
contours,hierarchy = cv2.findContours(thresh,cv2.RETR_LIST,cv2.CHAIN_APPROX_SIMPLE)
contours, boundingBoxes = sort_contours(contours, x_axis_sort='LEFT_TO_RIGHT', y_axis_sort='TOP_TO_BOTTOM')
samples = np.empty((0,100))
responses = []
keys = [i for i in range(48,58)]
for cnt in contours:
if cv2.contourArea(cnt)>50:
[x,y,w,h] = cv2.boundingRect(cnt)
if h>28 and h < 40:
cv2.rectangle(im,(x,y),(x+w,y+h),(0,0,255),2)
roi = thresh[y:y+h,x:x+w]
roismall = cv2.resize(roi,(10,10))
cv2.imshow('norm',im)
key = cv2.waitKey(0)
if key == 27: # (escape to quit)
sys.exit()
elif key in keys:
responses.append(int(chr(key)))
sample = roismall.reshape((1,100))
samples = np.append(samples,sample,0)
responses = np.array(responses,np.ubyte)
responses = responses.reshape((responses.size,1))
print("training complete")
np.savetxt('generalsamples.data',samples,fmt='%i')
np.savetxt('generalresponses.data',responses,fmt='%i')