// -*- C++ -*- // Copyright 2006-2008 Deutsches Forschungszentrum fuer Kuenstliche Intelligenz // or its licensors, as applicable. // // You may not use this file except under the terms of the accompanying license. // // Licensed under the Apache License, Version 2.0 (the "License"); you // may not use this file except in compliance with the License. You may // obtain a copy of the License at http://www.apache.org/licenses/LICENSE-2.0 // // Unless required by applicable law or agreed to in writing, software // distributed under the License is distributed on an "AS IS" BASIS, // WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. // See the License for the specific language governing permissions and // limitations under the License. // // Project: OCRopus // File: main-ocr-text-image-seg.cc // Purpose: Document zone classification using run-lengths and // connected components based features and logistic regression // classifier. // Responsible: Faisal Shafait (faisal.shafait@dfki.de) // Reviewer: // Primary Repository: // Web Sites: www.iupr.org, www.dfki.de #include "ocr-text-image-seg.h" using namespace ocropus; using namespace iulib; using namespace colib; int main(int argc, char **argv){ try { if(!(argc==3 || argc==2)) { fprintf(stderr, "Usage: ... input.png output.png\n"); exit(1); } const char *outimage="out.png"; if(argc==3){ outimage=argv[2]; } bytearray in,out; read_image_gray(in,stdio(argv[1],"r")); bytearray in_binary; if(!contains_only(in,byte(0),byte(255))){ autodel binarize(make_BinarizeByOtsu()); makelike(in_binary,in); binarize->binarize(in_binary,in); }else{ copy(in_binary,in); } // get text/image probability map intarray tiseg_image; autodel tiseg(make_TextImageSegByLogReg()); tiseg->textImageProbabilities(tiseg_image,in_binary); // Cleanup rectarray bboxes; get_nontext_boxes(bboxes,tiseg_image); copy(out,in); for(int i=0; i