一、开源框架OpenCV和TesseractOCRiOS
OpenCV（完成图像处理技术）
OpenCV是一个开源的跨平台计算机视觉和机器学习库，通俗点的说，就是他给计算机提供了一双眼睛，一双可以从图片中获取信息的眼镜，从而完成人脸识别、身份证识别、去红眼、追踪移动物体等等的图像相关的功能。opencv官网
TesseractOCRiOS（完成文字识别技术）
Tesseract是目前可用的最准确的开源OCR引擎，可以读取各种格式的图片并将他们转换成各种语言文本。而TesseractOCRiOS则是针对iOS平台封装的Tesseract引擎库。
二、代码实现：使用OpenCV对图片进行处理，取出需要识别的文字区域，使用TesseractOCRiOS对图片文字进行识别，识别的速度与准确率跟图片预处理有关系，难点也是图片处理这一块。
//扫描身份证图片，并进行预处理，定位号码区域图片并返回
- (UIImage*)opencvScanCard:(UIImage*)image {
//将UIImage转换成Mat
cv::MatresultImage;
UIImageToMat(image, resultImage);
//转为灰度图
cvtColor(resultImage, resultImage,cv::COLOR_BGR2GRAY);
//利用阈值二值化
cv::threshold(resultImage, resultImage,100,255,CV_THRESH_BINARY);
//腐蚀，填充（腐蚀是让黑色点变大）
cv::MaterodeElement =getStructuringElement(cv::MORPH_RECT,cv::Size(26,26));
cv::erode(resultImage, resultImage, erodeElement);
//轮廊检测
std::vector> contours;//定义一个容器来存储所有检测到的轮廊
cv::findContours(resultImage, contours,CV_RETR_TREE,CV_CHAIN_APPROX_SIMPLE,cvPoint(0,0));
//cv::drawContours(resultImage, contours, -1, cv::Scalar(255),4);
//取出身份证号码区域
std::vector rects;
cv::RectnumberRect =cv::Rect(0,0,0,0);
std::vector>::const_iteratoritContours = contours.begin();
for( ; itContours != contours.end(); ++itContours) {
cv::Rectrect =cv::boundingRect(*itContours);
rects.push_back(rect);
//算法原理
if(rect.width> numberRect.width&& rect.width> rect.height*5) {
numberRect = rect;
}
}
//身份证号码定位失败
if(numberRect.width==0|| numberRect.height==0) {
returnnil;
}
//定位成功成功，去原图截取身份证号码区域，并转换成灰度图、进行二值化处理
cv::MatmatImage;
UIImageToMat(image, matImage);
resultImage = matImage(numberRect);
cvtColor(resultImage, resultImage,cv::COLOR_BGR2GRAY);
cv::threshold(resultImage, resultImage,80,255,CV_THRESH_BINARY);
//将Mat转换成UIImage
UIImage*numberImage =MatToUIImage(resultImage);
returnnumberImage;
}
//利用TesseractOCR识别文字
- (void)tesseractRecognizeImage:(UIImage*)image compleate:(CompleateBlock)compleate {
G8RecognitionOperation*operation = [[G8RecognitionOperationalloc]initWithLanguage:@"eng"];
operation.tesseract.engineMode=G8OCREngineModeTesseractOnly;
operation.tesseract.pageSegmentationMode=G8PageSegmentationModeAutoOnly;
operation.delegate=self;
//设置image
operation.tesseract.image= image;
//读取
operation.recognitionCompleteBlock= ^(G8Tesseract*tesseract) {
//执行回调
compleate(tesseract.recognizedText);
};
[self.operationQueueaddOperation:operation];
//dispatch_async(dispatch_get_global_queue(DISPATCH_QUEUE_PRIORITY_BACKGROUND, 0), ^{
//G8Tesseract *tesseract = [[G8Tesseract alloc] initWithLanguage:@"eng"];
//tesseract.image = [image g8_blackAndWhite];
//tesseract.image = image;
//tesseract.engineMode = G8OCREngineModeTesseractOnly;
//tesseract.pageSegmentationMode = G8PageSegmentationModeAutoOnly;
//// Start the recognition
//[tesseract recognize];
////执行回调
//compleate(tesseract.recognizedText);
//});
}
