OpenCV C++基于CNN模型的场景文本检测(OCR)

这个程序使用OpenCV text模块检测场景中的文本。输入图片程序运行后会显示用红色矩形框标注文本的图片代码int main() { Mat image imread(scenetext_segmented_word02.jpg); PtrTextDetectorCNN textSpotter TextDetectorCNN::create(textbox.prototxt,TextBoxes_icdar13.caffemodel); vectorRect bbox; vectorfloat outProbabillities; textSpotter-detect(image, bbox, outProbabillities); vectorint indexes; NMSBoxes(bbox, outProbabillities, 0.3f, 0.4f, indexes); for (int i 0; i indexes.size(); i) { rectangle(image, bbox[indexes[i]], Scalar(0, 0, 255), 3, 8); } imshow(TextBox,image); waitKey(); }