[转]Basic OCR in OpenCV

最新推荐文章于 2025-09-09 00:58:55 发布

转载最新推荐文章于 2025-09-09 00:58:55 发布 · 73 阅读

0 ·

CC 4.0 BY-SA版权

原文链接：http://www.cnblogs.com/FoundationSoft/archive/2013/01/01/2841718.html

文章标签：

#人工智能

本文提供了一个使用OpenCV实现的手写数字识别教程，详细介绍了图像预处理、特征提取和分类模块的工作流程。通过创建训练集和测试集，利用knn方法进行分类，最终展示了一个完整的手写数字识别系统的实现过程。

原文地址：http://blog.damiles.com/2008/11/basic-ocr-in-opencv/

代码下载：https://github.com/damiles/basicOCR

In this tutorial we go to create a basic number OCR. It consist to classify a handwrite number into his class.

To do it, we go to use all we learn in before tutorials, we go to use a simple basic painter and the basic pattern recognition and classification with openCV tutorial.

In a typical pattern recognition classifier consist in three modules:

Preprocessing: in this module we go to process our input image, for example size normalize, convert color to BN…

Feature extraction: in this module we convert our image processed to a characteristic vector of features to classify, it can be the pixels matrix convert to vector or get contour chain codes data representation

Classification module get the feature vectors and train our system or classify an input feature vector with a classify method as knn.

In this basic OCR we go to use this graph:

Where we get a train set and test set of image to train and test our classifier method (knn)

We have a 1000 handwrite images, 100 images of each number. We get 50 images of each number (class) to train and other 50 to test our system.

Then the first work we do is pre-process all train image, to do it we create a preprocessing function. In this function we get a image and a new width and height we want as result of preprocessing, then the function return a normalized size with bounding box image. You can see more clear the process in this graph:

Pre-processing code:

 
    01void findX(IplImage* imgSrc,int* min, int* max){

    02int i;

    03int minFound=0;

    04CvMat data;

    05CvScalar maxVal=cvRealScalar(imgSrc->width * 255);

    06CvScalar val=cvRealScalar(0);

    07//For each col sum, if sum < width*255 then we find the min

    08//then continue to end to search the max, if sum< width*255 then is new max

    09for (i=0; i< imgSrc->width; i++){

    10cvGetCol(imgSrc, &data, i);

    11val= cvSum(&data);

    12if(val.val[0] < maxVal.val[0]){

    13*max= i;

    14if(!minFound){

    15*min= i;

    16minFound= 1;

    17}

    18}

    19}

    20}

    21 

    22void findY(IplImage* imgSrc,int* min, int* max){

    23int i;

    24int minFound=0;

    25CvMat data;

    26CvScalar maxVal=cvRealScalar(imgSrc->width * 255);

    27CvScalar val=cvRealScalar(0);

    28//For each col sum, if sum < width*255 then we find the min

    29//then continue to end to search the max, if sum< width*255 then is new max

    30for (i=0; i< imgSrc->height; i++){

    31cvGetRow(imgSrc, &data, i);

    32val= cvSum(&data);

    33if(val.val[0] < maxVal.val[0]){

    34*max=i;

    35if(!minFound){

    36*min= i;

    37minFound= 1;

    38}

    39}

    40}

    41}

    42CvRect findBB(IplImage* imgSrc){

    43CvRect aux;

    44int xmin, xmax, ymin, ymax;

    45xmin=xmax=ymin=ymax=0;

    46 

    47findX(imgSrc, &xmin, &xmax);

    48findY(imgSrc, &ymin, &ymax);

    49 

    50aux=cvRect(xmin, ymin, xmax-xmin, ymax-ymin);

    51 

    52//printf("BB: %d,%d - %d,%d\n", aux.x, aux.y, aux.width, aux.height);

    53 

    54return aux;

    55 

    56}

    57 

    58IplImage preprocessing(IplImage* imgSrc,int new_width, int new_height){

    59IplImage* result;

    60IplImage* scaledResult;

    61 

    62CvMat data;

    63CvMat dataA;

    64CvRect bb;//bounding box

    65CvRect bba;//boundinb box maintain aspect ratio

    66 

    67//Find bounding box

    68bb=findBB(imgSrc);

    69 

    70//Get bounding box data and no with aspect ratio, the x and y can be corrupted

    71cvGetSubRect(imgSrc, &data, cvRect(bb.x, bb.y, bb.width, bb.height));

    72//Create image with this data with width and height with aspect ratio 1

    73//then we get highest size betwen width and height of our bounding box

    74int size=(bb.width>bb.height)?bb.width:bb.height;

    75result=cvCreateImage( cvSize( size, size ), 8, 1 );

    76cvSet(result,CV_RGB(255,255,255),NULL);

    77//Copy de data in center of image

    78int x=(int)floor((float)(size-bb.width)/2.0f);

    79int y=(int)floor((float)(size-bb.height)/2.0f);

    80cvGetSubRect(result, &dataA, cvRect(x,y,bb.width, bb.height));

    81cvCopy(&data, &dataA, NULL);

    82//Scale result

    83scaledResult=cvCreateImage( cvSize( new_width, new_height ), 8, 1 );

    84cvResize(result, scaledResult, CV_INTER_NN);

    85 

    86//Return processed data

    87return *scaledResult;

    88 

    89}

We use the function getData of basicOCR class to create the train data and train classes, this function get all images under OCR folder to create this train data, the OCR forlder is structured with 1 folder to each class and each file have are pbm files with this name cnn.pbm where c is the class {0..9} and nn is the number of image {00..99}

Each image we get is pre-processed and then convert the data in a feature vector we use.

basicOCR.cpp getData code:

 
    01void basicOCR::getData()

    02{

    03IplImage* src_image;

    04IplImage prs_image;

    05CvMat row,data;

    06char file[255];

    07int i,j;

    08for(i =0; i<classes; i++){

    09for( j = 0; j< train_samples; j++){

    10 

    11//Load file

    12if(j<10)

    13sprintf(file,"%s%d/%d0%d.pbm",file_path, i, i , j);

    14else

    15sprintf(file,"%s%d/%d%d.pbm",file_path, i, i , j);

    16src_image = cvLoadImage(file,0);

    17if(!src_image){

    18printf("Error: Cant load image %s\n", file);

    19//exit(-1);

    20}

    21//process file

    22prs_image = preprocessing(src_image, size, size);

    23 

    24//Set class label

    25cvGetRow(trainClasses, &row, i*train_samples + j);

    26cvSet(&row, cvRealScalar(i));

    27//Set data

    28cvGetRow(trainData, &row, i*train_samples + j);

    29 

    30IplImage* img = cvCreateImage( cvSize( size, size ), IPL_DEPTH_32F, 1 );

    31//convert 8 bits image to 32 float image

    32cvConvertScale(&prs_image, img, 0.0039215, 0);

    33 

    34cvGetSubRect(img, &data, cvRect(0,0, size,size));

    35 

    36CvMat row_header, *row1;

    37//convert data matrix sizexsize to vecor

    38row1 = cvReshape( &data, &row_header, 0, 1 );

    39cvCopy(row1, &row, NULL);

    40}

    41}

    42}

After processed and get train data and classes whe then train our model with this data, in our sample we use knn method then:

`1`	`knn=new` `CvKNearest( trainData, trainClasses, 0,` `false, K );`

Then we now can test our model, and we can use the test result to compare to another methods we can use, or if we reduce the image scale or similar. There are a function to create the test in our basicOCR class, test function.

This function get the other 500 samples and classify this in our selected method and check the obtained result.

 
    01void basicOCR::test(){

    02IplImage* src_image;

    03IplImage prs_image;

    04CvMat row,data;

    05char file[255];

    06int i,j;

    07int error=0;

    08int testCount=0;

    09for(i =0; i<classes; i++){

    10for( j = 50; j< 50+train_samples; j++){

    11 

    12sprintf(file,"%s%d/%d%d.pbm",file_path, i, i , j);

    13src_image = cvLoadImage(file,0);

    14if(!src_image){

    15printf("Error: Cant load image %s\n", file);

    16//exit(-1);

    17}

    18//process file

    19prs_image = preprocessing(src_image, size, size);

    20float r=classify(&prs_image,0);

    21if((int)r!=i)

    22error++;

    23 

    24testCount++;

    25}

    26}

    27float totalerror=100*(float)error/(float)testCount;

    28printf("System Error: %.2f%%\n", totalerror);

    29 

    30}

Test use the classify function that get image to classify, process image, get feature vector and classify it with a find_nearest of knn class. This function we use to classify the input user images:

 
    01float basicOCR::classify(IplImage* img, int showResult)

    02{

    03IplImage prs_image;

    04CvMat data;

    05CvMat* nearest=cvCreateMat(1,K,CV_32FC1);

    06float result;

    07//process file

    08prs_image = preprocessing(img, size, size);

    09 

    10//Set data

    11IplImage* img32 = cvCreateImage( cvSize( size, size ), IPL_DEPTH_32F, 1 );

    12cvConvertScale(&prs_image, img32, 0.0039215, 0);

    13cvGetSubRect(img32, &data, cvRect(0,0, size,size));

    14CvMat row_header, *row1;

    15row1 = cvReshape( &data, &row_header, 0, 1 );

    16 

    17result=knn->find_nearest(row1,K,0,0,nearest,0);

    18 

    19int accuracy=0;

    20for(int i=0;i<K;i++){

    21if( nearest->data.fl[i] == result)

    22accuracy++;

    23}

    24float pre=100*((float)accuracy/(float)K);

    25if(showResult==1){

    26printf("|\t%.0f\t| \t%.2f%%  \t| \t%d of %d \t| \n",result,pre,accuracy,K);

    27printf(" ---------------------------------------------------------------\n");

    28}

    29 

    30return result;

    31 

    32}

All work or training and test is in basicOCR class, when we create a basicOCR instance then only we need call to classify function to classify our input image. Then we go to use basic Painter we create before in other tutorial to user interactivity to draw a image and classify it.

转载于:https://www.cnblogs.com/FoundationSoft/archive/2013/01/01/2841718.html