// Copyright (c) 2020 PaddlePaddle Authors. All Rights Reserved. // // 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. #include "opencv2/core.hpp" #include "opencv2/imgcodecs.hpp" #include "opencv2/imgproc.hpp" #include "paddle_api.h" #include "paddle_inference_api.h" #include #include #include #include #include #include #include #include #include namespace PaddleOCR { void Permute::Run(const cv::Mat *im, float *data) { int rh = im->rows; int rw = im->cols; int rc = im->channels(); for (int i = 0; i < rc; ++i) { cv::extractChannel(*im, cv::Mat(rh, rw, CV_32FC1, data + i * rh * rw), i); } } void Normalize::Run(cv::Mat *im, const std::vector &mean, const std::vector &scale, const bool is_scale) { double e = 1.0; if (is_scale) { e /= 255.0; } (*im).convertTo(*im, CV_32FC3, e); for (int h = 0; h < im->rows; h++) { for (int w = 0; w < im->cols; w++) { im->at(h, w)[0] = (im->at(h, w)[0] - mean[0]) * scale[0]; im->at(h, w)[1] = (im->at(h, w)[1] - mean[1]) * scale[1]; im->at(h, w)[2] = (im->at(h, w)[2] - mean[2]) * scale[2]; } } } void ResizeImgType0::Run(const cv::Mat &img, cv::Mat &resize_img, int max_size_len, float &ratio_h, float &ratio_w) { int w = img.cols; int h = img.rows; float ratio = 1.f; int max_wh = w >= h ? w : h; if (max_wh > max_size_len) { if (h > w) { ratio = float(max_size_len) / float(h); } else { ratio = float(max_size_len) / float(w); } } int resize_h = int(float(h) * ratio); int resize_w = int(float(w) * ratio); if (resize_h % 32 == 0) resize_h = resize_h; else if (resize_h / 32 < 1 + 1e-5) resize_h = 32; else resize_h = resize_h / 32 * 32; if (resize_w % 32 == 0) resize_w = resize_w; else if (resize_w / 32 < 1 + 1e-5) resize_w = 32; else resize_w = resize_w / 32 * 32; cv::resize(img, resize_img, cv::Size(resize_w, resize_h)); ratio_h = float(resize_h) / float(h); ratio_w = float(resize_w) / float(w); } void CrnnResizeImg::Run(const cv::Mat &img, cv::Mat &pad_resize_img, float max_wh_ratio, const std::vector &rec_image_shape) { int imgC, imgH, imgW; imgC = rec_image_shape[0]; imgH = rec_image_shape[1]; imgW = rec_image_shape[2]; float wh_ratio = 1.0 * imgW / imgH; wh_ratio = std::max(max_wh_ratio, wh_ratio); imgW = int(32 * wh_ratio); float ratio = float(img.cols) / float(img.rows); int resize_w, resize_h; if (ceilf(imgH * ratio) > imgW) resize_w = imgW; else resize_w = int(ceilf(imgH * ratio)); cv::Mat resize_img; cv::resize(img, resize_img, cv::Size(resize_w, imgH), 0.f, 0.f, cv::INTER_LINEAR); cv::copyMakeBorder(resize_img, pad_resize_img, 0, 0, 0, int(imgW - resize_img.cols), cv::BORDER_CONSTANT, {127, 127, 127}); } void ClsResizeImg::Run(const cv::Mat &img, cv::Mat &resize_img, const std::vector &rec_image_shape) { int imgC, imgH, imgW; imgC = rec_image_shape[0]; imgH = rec_image_shape[1]; imgW = rec_image_shape[2]; float ratio = float(img.cols) / float(img.rows); int resize_w, resize_h; if (ceilf(imgH * ratio) > imgW) resize_w = imgW; else resize_w = int(ceilf(imgH * ratio)); cv::resize(img, resize_img, cv::Size(resize_w, imgH), 0.f, 0.f, cv::INTER_LINEAR); if (resize_w < imgW) { cv::copyMakeBorder(resize_img, resize_img, 0, 0, 0, imgW - resize_w, cv::BORDER_CONSTANT, cv::Scalar(0, 0, 0)); } } } // namespace PaddleOCR