OpenCV+Tesseract进行OCR学习（二）文字识别

OpenCV的Tesseract使用

Mac端的Tesseract使用

Tesseract的安装
Mac上的Tesseract安装很方便，直接利用brew来安装：

brew update
brew install tesseract

或者下载源码进行编译安装：
Github地址

Tesseract的使用

#include <tesseract/baseapi.h>

tesseract::TessBaseAPI tessearct_api;
    const char  *languagePath = "/usr/local/Cellar/tesseract/3.04.01_2/share/tessdata";
    const char *languageType = "chi_sim";
    int nRet = tessearct_api.Init(languagePath, languageType,tesseract::OEM_DEFAULT);
    if (nRet != 0) {
        printf("初始化字库失败！");
        return -1;
    }
    tessearct_api.SetPageSegMode(tesseract::PSM_SINGLE_BLOCK);
    tessearct_api.SetImage(seg_image.data, seg_image.cols, seg_image.rows, 1, seg_image.cols);
    string out = string(tessearct_api.GetUTF8Text());
    cout<<"the out result :"<<out<<endl;

iOS端的Tesseract使用

Tesseract的安装
利用CocoaPods来安装，命令如下：

brew update
pod search tesseractocrios

这时会出现如下：

继续键入命令：

touch Podfile
vi Podfile
这时，将上图中‘pod 'TesseractOCRiOS', '~> 4.0.0'’copy到Podfile中，保存退出，然后：
pod install

ok，这时打开项目目录下生成的后缀名为.xcworkspace的工程即可。

Tesseract的使用

#import "TesseractOCR/G8Tesseract.h"

//recognize image with tesseract
-(void)recognizeWithTesseract: (UIImage *)image{
    G8RecognitionOperation *operation = [[G8RecognitionOperation alloc] initWithLanguage:@"chi_sim"];
    operation.tesseract.engineMode = G8OCREngineModeTesseractOnly;
    operation.tesseract.pageSegmentationMode = G8PageSegmentationModeAutoOnly;
    operation.delegate = self;
    operation.recognitionCompleteBlock = ^(G8Tesseract *tesseract) {
        NSString *recognizedText = tesseract.recognizedText;
        NSLog(@"%@", recognizedText);
        self.text.text = recognizedText;

    };
//    self.imageView.image = operation.tesseract.thresholdedImage;
}

//print the progress infos
- (void)progressImageRecognitionForTesseract:(G8Tesseract *)tesseract {
    NSLog(@"progress: %lu", (unsigned long)tesseract.progress);
}