merge shared files
This commit is contained in:
MissPenguin
parent
39b7263e22
commit
874a32625f
|
|
@ -13,6 +13,7 @@
|
|||
// limitations under the License.
|
||||
|
||||
#include <include/postprocess_op.h>
|
||||
#include <include/clipper.cpp>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
|
|
@ -30,6 +30,7 @@
|
|||
#include "include/clipper.h"
|
||||
#include "include/utility.h"
|
||||
|
||||
|
||||
using namespace std;
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
|
|
|||
|
|
@ -20,6 +20,8 @@
|
|||
#include <ostream>
|
||||
#include <stdlib.h>
|
||||
#include <vector>
|
||||
#include <sys/stat.h>
|
||||
#include <dirent.h>
|
||||
|
||||
#include <algorithm>
|
||||
#include <cstring>
|
||||
|
|
@ -34,11 +36,42 @@ namespace PaddleOCR {
|
|||
|
||||
class Utility {
|
||||
public:
|
||||
static std::vector<std::string> ReadDict(const std::string &path);
|
||||
|
||||
static std::vector<std::string> ReadDict(const std::string &path) {
|
||||
std::ifstream in(path);
|
||||
std::string line;
|
||||
std::vector<std::string> m_vec;
|
||||
if (in) {
|
||||
while (getline(in, line)) {
|
||||
m_vec.push_back(line);
|
||||
}
|
||||
} else {
|
||||
std::cout << "no such label file: " << path << ", exit the program..."
|
||||
<< std::endl;
|
||||
exit(1);
|
||||
}
|
||||
return m_vec;
|
||||
}
|
||||
|
||||
static void
|
||||
VisualizeBboxes(const cv::Mat &srcimg,
|
||||
const std::vector<std::vector<std::vector<int>>> &boxes);
|
||||
const std::vector<std::vector<std::vector<int>>> &boxes) {
|
||||
cv::Mat img_vis;
|
||||
srcimg.copyTo(img_vis);
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
cv::Point rook_points[4];
|
||||
for (int m = 0; m < boxes[n].size(); m++) {
|
||||
rook_points[m] = cv::Point(int(boxes[n][m][0]), int(boxes[n][m][1]));
|
||||
}
|
||||
|
||||
const cv::Point *ppt[1] = {rook_points};
|
||||
int npt[] = {4};
|
||||
cv::polylines(img_vis, ppt, npt, 1, 1, CV_RGB(0, 255, 0), 2, 8, 0);
|
||||
}
|
||||
|
||||
cv::imwrite("./ocr_vis.png", img_vis);
|
||||
std::cout << "The detection visualized image saved in ./ocr_vis.png"
|
||||
<< std::endl;
|
||||
}
|
||||
|
||||
template <class ForwardIterator>
|
||||
inline static size_t argmax(ForwardIterator first, ForwardIterator last) {
|
||||
|
|
@ -46,7 +79,36 @@ public:
|
|||
}
|
||||
|
||||
static void GetAllFiles(const char *dir_name,
|
||||
std::vector<std::string> &all_inputs);
|
||||
std::vector<std::string> &all_inputs) {
|
||||
if (NULL == dir_name) {
|
||||
std::cout << " dir_name is null ! " << std::endl;
|
||||
return;
|
||||
}
|
||||
struct stat s;
|
||||
lstat(dir_name, &s);
|
||||
if (!S_ISDIR(s.st_mode)) {
|
||||
std::cout << "dir_name is not a valid directory !" << std::endl;
|
||||
all_inputs.push_back(dir_name);
|
||||
return;
|
||||
} else {
|
||||
struct dirent *filename; // return value for readdir()
|
||||
DIR *dir; // return value for opendir()
|
||||
dir = opendir(dir_name);
|
||||
if (NULL == dir) {
|
||||
std::cout << "Can not open dir " << dir_name << std::endl;
|
||||
return;
|
||||
}
|
||||
std::cout << "Successfully opened the dir !" << std::endl;
|
||||
while ((filename = readdir(dir)) != NULL) {
|
||||
if (strcmp(filename->d_name, ".") == 0 ||
|
||||
strcmp(filename->d_name, "..") == 0)
|
||||
continue;
|
||||
// img_dir + std::string("/") + all_inputs[0];
|
||||
all_inputs.push_back(dir_name + std::string("/") +
|
||||
std::string(filename->d_name));
|
||||
}
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
} // namespace PaddleOCR
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -13,6 +13,8 @@
|
|||
// limitations under the License.
|
||||
|
||||
#include <include/ocr_det.h>
|
||||
#include <include/preprocess_op.cpp>
|
||||
#include <include/postprocess_op.cpp>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
|
|
|
|||
|
|
@ -1,355 +0,0 @@
|
|||
// 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 <include/postprocess_op.h>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
void PostProcessor::GetContourArea(const std::vector<std::vector<float>> &box,
|
||||
float unclip_ratio, float &distance) {
|
||||
int pts_num = 4;
|
||||
float area = 0.0f;
|
||||
float dist = 0.0f;
|
||||
for (int i = 0; i < pts_num; i++) {
|
||||
area += box[i][0] * box[(i + 1) % pts_num][1] -
|
||||
box[i][1] * box[(i + 1) % pts_num][0];
|
||||
dist += sqrtf((box[i][0] - box[(i + 1) % pts_num][0]) *
|
||||
(box[i][0] - box[(i + 1) % pts_num][0]) +
|
||||
(box[i][1] - box[(i + 1) % pts_num][1]) *
|
||||
(box[i][1] - box[(i + 1) % pts_num][1]));
|
||||
}
|
||||
area = fabs(float(area / 2.0));
|
||||
|
||||
distance = area * unclip_ratio / dist;
|
||||
}
|
||||
|
||||
cv::RotatedRect PostProcessor::UnClip(std::vector<std::vector<float>> box,
|
||||
const float &unclip_ratio) {
|
||||
float distance = 1.0;
|
||||
|
||||
GetContourArea(box, unclip_ratio, distance);
|
||||
|
||||
ClipperLib::ClipperOffset offset;
|
||||
ClipperLib::Path p;
|
||||
p << ClipperLib::IntPoint(int(box[0][0]), int(box[0][1]))
|
||||
<< ClipperLib::IntPoint(int(box[1][0]), int(box[1][1]))
|
||||
<< ClipperLib::IntPoint(int(box[2][0]), int(box[2][1]))
|
||||
<< ClipperLib::IntPoint(int(box[3][0]), int(box[3][1]));
|
||||
offset.AddPath(p, ClipperLib::jtRound, ClipperLib::etClosedPolygon);
|
||||
|
||||
ClipperLib::Paths soln;
|
||||
offset.Execute(soln, distance);
|
||||
std::vector<cv::Point2f> points;
|
||||
|
||||
for (int j = 0; j < soln.size(); j++) {
|
||||
for (int i = 0; i < soln[soln.size() - 1].size(); i++) {
|
||||
points.emplace_back(soln[j][i].X, soln[j][i].Y);
|
||||
}
|
||||
}
|
||||
cv::RotatedRect res;
|
||||
if (points.size() <= 0) {
|
||||
res = cv::RotatedRect(cv::Point2f(0, 0), cv::Size2f(1, 1), 0);
|
||||
} else {
|
||||
res = cv::minAreaRect(points);
|
||||
}
|
||||
return res;
|
||||
}
|
||||
|
||||
float **PostProcessor::Mat2Vec(cv::Mat mat) {
|
||||
auto **array = new float *[mat.rows];
|
||||
for (int i = 0; i < mat.rows; ++i)
|
||||
array[i] = new float[mat.cols];
|
||||
for (int i = 0; i < mat.rows; ++i) {
|
||||
for (int j = 0; j < mat.cols; ++j) {
|
||||
array[i][j] = mat.at<float>(i, j);
|
||||
}
|
||||
}
|
||||
|
||||
return array;
|
||||
}
|
||||
|
||||
std::vector<std::vector<int>>
|
||||
PostProcessor::OrderPointsClockwise(std::vector<std::vector<int>> pts) {
|
||||
std::vector<std::vector<int>> box = pts;
|
||||
std::sort(box.begin(), box.end(), XsortInt);
|
||||
|
||||
std::vector<std::vector<int>> leftmost = {box[0], box[1]};
|
||||
std::vector<std::vector<int>> rightmost = {box[2], box[3]};
|
||||
|
||||
if (leftmost[0][1] > leftmost[1][1])
|
||||
std::swap(leftmost[0], leftmost[1]);
|
||||
|
||||
if (rightmost[0][1] > rightmost[1][1])
|
||||
std::swap(rightmost[0], rightmost[1]);
|
||||
|
||||
std::vector<std::vector<int>> rect = {leftmost[0], rightmost[0], rightmost[1],
|
||||
leftmost[1]};
|
||||
return rect;
|
||||
}
|
||||
|
||||
std::vector<std::vector<float>> PostProcessor::Mat2Vector(cv::Mat mat) {
|
||||
std::vector<std::vector<float>> img_vec;
|
||||
std::vector<float> tmp;
|
||||
|
||||
for (int i = 0; i < mat.rows; ++i) {
|
||||
tmp.clear();
|
||||
for (int j = 0; j < mat.cols; ++j) {
|
||||
tmp.push_back(mat.at<float>(i, j));
|
||||
}
|
||||
img_vec.push_back(tmp);
|
||||
}
|
||||
return img_vec;
|
||||
}
|
||||
|
||||
bool PostProcessor::XsortFp32(std::vector<float> a, std::vector<float> b) {
|
||||
if (a[0] != b[0])
|
||||
return a[0] < b[0];
|
||||
return false;
|
||||
}
|
||||
|
||||
bool PostProcessor::XsortInt(std::vector<int> a, std::vector<int> b) {
|
||||
if (a[0] != b[0])
|
||||
return a[0] < b[0];
|
||||
return false;
|
||||
}
|
||||
|
||||
std::vector<std::vector<float>> PostProcessor::GetMiniBoxes(cv::RotatedRect box,
|
||||
float &ssid) {
|
||||
ssid = std::max(box.size.width, box.size.height);
|
||||
|
||||
cv::Mat points;
|
||||
cv::boxPoints(box, points);
|
||||
|
||||
auto array = Mat2Vector(points);
|
||||
std::sort(array.begin(), array.end(), XsortFp32);
|
||||
|
||||
std::vector<float> idx1 = array[0], idx2 = array[1], idx3 = array[2],
|
||||
idx4 = array[3];
|
||||
if (array[3][1] <= array[2][1]) {
|
||||
idx2 = array[3];
|
||||
idx3 = array[2];
|
||||
} else {
|
||||
idx2 = array[2];
|
||||
idx3 = array[3];
|
||||
}
|
||||
if (array[1][1] <= array[0][1]) {
|
||||
idx1 = array[1];
|
||||
idx4 = array[0];
|
||||
} else {
|
||||
idx1 = array[0];
|
||||
idx4 = array[1];
|
||||
}
|
||||
|
||||
array[0] = idx1;
|
||||
array[1] = idx2;
|
||||
array[2] = idx3;
|
||||
array[3] = idx4;
|
||||
|
||||
return array;
|
||||
}
|
||||
|
||||
float PostProcessor::PolygonScoreAcc(std::vector<cv::Point> contour,
|
||||
cv::Mat pred) {
|
||||
int width = pred.cols;
|
||||
int height = pred.rows;
|
||||
std::vector<float> box_x;
|
||||
std::vector<float> box_y;
|
||||
for (int i = 0; i < contour.size(); ++i) {
|
||||
box_x.push_back(contour[i].x);
|
||||
box_y.push_back(contour[i].y);
|
||||
}
|
||||
|
||||
int xmin =
|
||||
clamp(int(std::floor(*(std::min_element(box_x.begin(), box_x.end())))), 0,
|
||||
width - 1);
|
||||
int xmax =
|
||||
clamp(int(std::ceil(*(std::max_element(box_x.begin(), box_x.end())))), 0,
|
||||
width - 1);
|
||||
int ymin =
|
||||
clamp(int(std::floor(*(std::min_element(box_y.begin(), box_y.end())))), 0,
|
||||
height - 1);
|
||||
int ymax =
|
||||
clamp(int(std::ceil(*(std::max_element(box_y.begin(), box_y.end())))), 0,
|
||||
height - 1);
|
||||
|
||||
cv::Mat mask;
|
||||
mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1);
|
||||
|
||||
|
||||
cv::Point* rook_point = new cv::Point[contour.size()];
|
||||
|
||||
for (int i = 0; i < contour.size(); ++i) {
|
||||
rook_point[i] = cv::Point(int(box_x[i]) - xmin, int(box_y[i]) - ymin);
|
||||
}
|
||||
const cv::Point *ppt[1] = {rook_point};
|
||||
int npt[] = {int(contour.size())};
|
||||
|
||||
|
||||
cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1));
|
||||
|
||||
cv::Mat croppedImg;
|
||||
pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1)).copyTo(croppedImg);
|
||||
float score = cv::mean(croppedImg, mask)[0];
|
||||
|
||||
delete []rook_point;
|
||||
return score;
|
||||
}
|
||||
|
||||
float PostProcessor::BoxScoreFast(std::vector<std::vector<float>> box_array,
|
||||
cv::Mat pred) {
|
||||
auto array = box_array;
|
||||
int width = pred.cols;
|
||||
int height = pred.rows;
|
||||
|
||||
float box_x[4] = {array[0][0], array[1][0], array[2][0], array[3][0]};
|
||||
float box_y[4] = {array[0][1], array[1][1], array[2][1], array[3][1]};
|
||||
|
||||
int xmin = clamp(int(std::floor(*(std::min_element(box_x, box_x + 4)))), 0,
|
||||
width - 1);
|
||||
int xmax = clamp(int(std::ceil(*(std::max_element(box_x, box_x + 4)))), 0,
|
||||
width - 1);
|
||||
int ymin = clamp(int(std::floor(*(std::min_element(box_y, box_y + 4)))), 0,
|
||||
height - 1);
|
||||
int ymax = clamp(int(std::ceil(*(std::max_element(box_y, box_y + 4)))), 0,
|
||||
height - 1);
|
||||
|
||||
cv::Mat mask;
|
||||
mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1);
|
||||
|
||||
cv::Point root_point[4];
|
||||
root_point[0] = cv::Point(int(array[0][0]) - xmin, int(array[0][1]) - ymin);
|
||||
root_point[1] = cv::Point(int(array[1][0]) - xmin, int(array[1][1]) - ymin);
|
||||
root_point[2] = cv::Point(int(array[2][0]) - xmin, int(array[2][1]) - ymin);
|
||||
root_point[3] = cv::Point(int(array[3][0]) - xmin, int(array[3][1]) - ymin);
|
||||
const cv::Point *ppt[1] = {root_point};
|
||||
int npt[] = {4};
|
||||
cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1));
|
||||
|
||||
cv::Mat croppedImg;
|
||||
pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1))
|
||||
.copyTo(croppedImg);
|
||||
|
||||
auto score = cv::mean(croppedImg, mask)[0];
|
||||
return score;
|
||||
}
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> PostProcessor::BoxesFromBitmap(
|
||||
const cv::Mat pred, const cv::Mat bitmap, const float &box_thresh,
|
||||
const float &det_db_unclip_ratio, const bool &use_polygon_score) {
|
||||
const int min_size = 3;
|
||||
const int max_candidates = 1000;
|
||||
|
||||
int width = bitmap.cols;
|
||||
int height = bitmap.rows;
|
||||
|
||||
std::vector<std::vector<cv::Point>> contours;
|
||||
std::vector<cv::Vec4i> hierarchy;
|
||||
|
||||
cv::findContours(bitmap, contours, hierarchy, cv::RETR_LIST,
|
||||
cv::CHAIN_APPROX_SIMPLE);
|
||||
|
||||
int num_contours =
|
||||
contours.size() >= max_candidates ? max_candidates : contours.size();
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> boxes;
|
||||
|
||||
for (int _i = 0; _i < num_contours; _i++) {
|
||||
if (contours[_i].size() <= 2) {
|
||||
continue;
|
||||
}
|
||||
float ssid;
|
||||
cv::RotatedRect box = cv::minAreaRect(contours[_i]);
|
||||
auto array = GetMiniBoxes(box, ssid);
|
||||
|
||||
auto box_for_unclip = array;
|
||||
// end get_mini_box
|
||||
|
||||
if (ssid < min_size) {
|
||||
continue;
|
||||
}
|
||||
|
||||
float score;
|
||||
if (use_polygon_score)
|
||||
/* compute using polygon*/
|
||||
score = PolygonScoreAcc(contours[_i], pred);
|
||||
else
|
||||
score = BoxScoreFast(array, pred);
|
||||
|
||||
if (score < box_thresh)
|
||||
continue;
|
||||
|
||||
// start for unclip
|
||||
cv::RotatedRect points = UnClip(box_for_unclip, det_db_unclip_ratio);
|
||||
if (points.size.height < 1.001 && points.size.width < 1.001) {
|
||||
continue;
|
||||
}
|
||||
// end for unclip
|
||||
|
||||
cv::RotatedRect clipbox = points;
|
||||
auto cliparray = GetMiniBoxes(clipbox, ssid);
|
||||
|
||||
if (ssid < min_size + 2)
|
||||
continue;
|
||||
|
||||
int dest_width = pred.cols;
|
||||
int dest_height = pred.rows;
|
||||
std::vector<std::vector<int>> intcliparray;
|
||||
|
||||
for (int num_pt = 0; num_pt < 4; num_pt++) {
|
||||
std::vector<int> a{int(clampf(roundf(cliparray[num_pt][0] / float(width) *
|
||||
float(dest_width)),
|
||||
0, float(dest_width))),
|
||||
int(clampf(roundf(cliparray[num_pt][1] /
|
||||
float(height) * float(dest_height)),
|
||||
0, float(dest_height)))};
|
||||
intcliparray.push_back(a);
|
||||
}
|
||||
boxes.push_back(intcliparray);
|
||||
|
||||
} // end for
|
||||
return boxes;
|
||||
}
|
||||
|
||||
std::vector<std::vector<std::vector<int>>>
|
||||
PostProcessor::FilterTagDetRes(std::vector<std::vector<std::vector<int>>> boxes,
|
||||
float ratio_h, float ratio_w, cv::Mat srcimg) {
|
||||
int oriimg_h = srcimg.rows;
|
||||
int oriimg_w = srcimg.cols;
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> root_points;
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
boxes[n] = OrderPointsClockwise(boxes[n]);
|
||||
for (int m = 0; m < boxes[0].size(); m++) {
|
||||
boxes[n][m][0] /= ratio_w;
|
||||
boxes[n][m][1] /= ratio_h;
|
||||
|
||||
boxes[n][m][0] = int(_min(_max(boxes[n][m][0], 0), oriimg_w - 1));
|
||||
boxes[n][m][1] = int(_min(_max(boxes[n][m][1], 0), oriimg_h - 1));
|
||||
}
|
||||
}
|
||||
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
int rect_width, rect_height;
|
||||
rect_width = int(sqrt(pow(boxes[n][0][0] - boxes[n][1][0], 2) +
|
||||
pow(boxes[n][0][1] - boxes[n][1][1], 2)));
|
||||
rect_height = int(sqrt(pow(boxes[n][0][0] - boxes[n][3][0], 2) +
|
||||
pow(boxes[n][0][1] - boxes[n][3][1], 2)));
|
||||
if (rect_width <= 4 || rect_height <= 4)
|
||||
continue;
|
||||
root_points.push_back(boxes[n]);
|
||||
}
|
||||
return root_points;
|
||||
}
|
||||
|
||||
} // namespace PaddleOCR
|
||||
|
|
@ -1,95 +0,0 @@
|
|||
// 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 <dirent.h>
|
||||
#include <include/utility.h>
|
||||
#include <iostream>
|
||||
#include <ostream>
|
||||
#include <sys/stat.h>
|
||||
#include <sys/types.h>
|
||||
#include <vector>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
std::vector<std::string> Utility::ReadDict(const std::string &path) {
|
||||
std::ifstream in(path);
|
||||
std::string line;
|
||||
std::vector<std::string> m_vec;
|
||||
if (in) {
|
||||
while (getline(in, line)) {
|
||||
m_vec.push_back(line);
|
||||
}
|
||||
} else {
|
||||
std::cout << "no such label file: " << path << ", exit the program..."
|
||||
<< std::endl;
|
||||
exit(1);
|
||||
}
|
||||
return m_vec;
|
||||
}
|
||||
|
||||
void Utility::VisualizeBboxes(
|
||||
const cv::Mat &srcimg,
|
||||
const std::vector<std::vector<std::vector<int>>> &boxes) {
|
||||
cv::Mat img_vis;
|
||||
srcimg.copyTo(img_vis);
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
cv::Point rook_points[4];
|
||||
for (int m = 0; m < boxes[n].size(); m++) {
|
||||
rook_points[m] = cv::Point(int(boxes[n][m][0]), int(boxes[n][m][1]));
|
||||
}
|
||||
|
||||
const cv::Point *ppt[1] = {rook_points};
|
||||
int npt[] = {4};
|
||||
cv::polylines(img_vis, ppt, npt, 1, 1, CV_RGB(0, 255, 0), 2, 8, 0);
|
||||
}
|
||||
|
||||
cv::imwrite("./ocr_vis.png", img_vis);
|
||||
std::cout << "The detection visualized image saved in ./ocr_vis.png"
|
||||
<< std::endl;
|
||||
}
|
||||
|
||||
// list all files under a directory
|
||||
void Utility::GetAllFiles(const char *dir_name,
|
||||
std::vector<std::string> &all_inputs) {
|
||||
if (NULL == dir_name) {
|
||||
std::cout << " dir_name is null ! " << std::endl;
|
||||
return;
|
||||
}
|
||||
struct stat s;
|
||||
lstat(dir_name, &s);
|
||||
if (!S_ISDIR(s.st_mode)) {
|
||||
std::cout << "dir_name is not a valid directory !" << std::endl;
|
||||
all_inputs.push_back(dir_name);
|
||||
return;
|
||||
} else {
|
||||
struct dirent *filename; // return value for readdir()
|
||||
DIR *dir; // return value for opendir()
|
||||
dir = opendir(dir_name);
|
||||
if (NULL == dir) {
|
||||
std::cout << "Can not open dir " << dir_name << std::endl;
|
||||
return;
|
||||
}
|
||||
std::cout << "Successfully opened the dir !" << std::endl;
|
||||
while ((filename = readdir(dir)) != NULL) {
|
||||
if (strcmp(filename->d_name, ".") == 0 ||
|
||||
strcmp(filename->d_name, "..") == 0)
|
||||
continue;
|
||||
// img_dir + std::string("/") + all_inputs[0];
|
||||
all_inputs.push_back(dir_name + std::string("/") +
|
||||
std::string(filename->d_name));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace PaddleOCR
|
||||
|
|
@ -13,6 +13,7 @@
|
|||
// limitations under the License.
|
||||
|
||||
#include <include/ocr_rec.h>
|
||||
#include <include/preprocess_op.cpp>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
|
|
|
|||
|
|
@ -1,355 +0,0 @@
|
|||
// 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 <include/postprocess_op.h>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
void PostProcessor::GetContourArea(const std::vector<std::vector<float>> &box,
|
||||
float unclip_ratio, float &distance) {
|
||||
int pts_num = 4;
|
||||
float area = 0.0f;
|
||||
float dist = 0.0f;
|
||||
for (int i = 0; i < pts_num; i++) {
|
||||
area += box[i][0] * box[(i + 1) % pts_num][1] -
|
||||
box[i][1] * box[(i + 1) % pts_num][0];
|
||||
dist += sqrtf((box[i][0] - box[(i + 1) % pts_num][0]) *
|
||||
(box[i][0] - box[(i + 1) % pts_num][0]) +
|
||||
(box[i][1] - box[(i + 1) % pts_num][1]) *
|
||||
(box[i][1] - box[(i + 1) % pts_num][1]));
|
||||
}
|
||||
area = fabs(float(area / 2.0));
|
||||
|
||||
distance = area * unclip_ratio / dist;
|
||||
}
|
||||
|
||||
cv::RotatedRect PostProcessor::UnClip(std::vector<std::vector<float>> box,
|
||||
const float &unclip_ratio) {
|
||||
float distance = 1.0;
|
||||
|
||||
GetContourArea(box, unclip_ratio, distance);
|
||||
|
||||
ClipperLib::ClipperOffset offset;
|
||||
ClipperLib::Path p;
|
||||
p << ClipperLib::IntPoint(int(box[0][0]), int(box[0][1]))
|
||||
<< ClipperLib::IntPoint(int(box[1][0]), int(box[1][1]))
|
||||
<< ClipperLib::IntPoint(int(box[2][0]), int(box[2][1]))
|
||||
<< ClipperLib::IntPoint(int(box[3][0]), int(box[3][1]));
|
||||
offset.AddPath(p, ClipperLib::jtRound, ClipperLib::etClosedPolygon);
|
||||
|
||||
ClipperLib::Paths soln;
|
||||
offset.Execute(soln, distance);
|
||||
std::vector<cv::Point2f> points;
|
||||
|
||||
for (int j = 0; j < soln.size(); j++) {
|
||||
for (int i = 0; i < soln[soln.size() - 1].size(); i++) {
|
||||
points.emplace_back(soln[j][i].X, soln[j][i].Y);
|
||||
}
|
||||
}
|
||||
cv::RotatedRect res;
|
||||
if (points.size() <= 0) {
|
||||
res = cv::RotatedRect(cv::Point2f(0, 0), cv::Size2f(1, 1), 0);
|
||||
} else {
|
||||
res = cv::minAreaRect(points);
|
||||
}
|
||||
return res;
|
||||
}
|
||||
|
||||
float **PostProcessor::Mat2Vec(cv::Mat mat) {
|
||||
auto **array = new float *[mat.rows];
|
||||
for (int i = 0; i < mat.rows; ++i)
|
||||
array[i] = new float[mat.cols];
|
||||
for (int i = 0; i < mat.rows; ++i) {
|
||||
for (int j = 0; j < mat.cols; ++j) {
|
||||
array[i][j] = mat.at<float>(i, j);
|
||||
}
|
||||
}
|
||||
|
||||
return array;
|
||||
}
|
||||
|
||||
std::vector<std::vector<int>>
|
||||
PostProcessor::OrderPointsClockwise(std::vector<std::vector<int>> pts) {
|
||||
std::vector<std::vector<int>> box = pts;
|
||||
std::sort(box.begin(), box.end(), XsortInt);
|
||||
|
||||
std::vector<std::vector<int>> leftmost = {box[0], box[1]};
|
||||
std::vector<std::vector<int>> rightmost = {box[2], box[3]};
|
||||
|
||||
if (leftmost[0][1] > leftmost[1][1])
|
||||
std::swap(leftmost[0], leftmost[1]);
|
||||
|
||||
if (rightmost[0][1] > rightmost[1][1])
|
||||
std::swap(rightmost[0], rightmost[1]);
|
||||
|
||||
std::vector<std::vector<int>> rect = {leftmost[0], rightmost[0], rightmost[1],
|
||||
leftmost[1]};
|
||||
return rect;
|
||||
}
|
||||
|
||||
std::vector<std::vector<float>> PostProcessor::Mat2Vector(cv::Mat mat) {
|
||||
std::vector<std::vector<float>> img_vec;
|
||||
std::vector<float> tmp;
|
||||
|
||||
for (int i = 0; i < mat.rows; ++i) {
|
||||
tmp.clear();
|
||||
for (int j = 0; j < mat.cols; ++j) {
|
||||
tmp.push_back(mat.at<float>(i, j));
|
||||
}
|
||||
img_vec.push_back(tmp);
|
||||
}
|
||||
return img_vec;
|
||||
}
|
||||
|
||||
bool PostProcessor::XsortFp32(std::vector<float> a, std::vector<float> b) {
|
||||
if (a[0] != b[0])
|
||||
return a[0] < b[0];
|
||||
return false;
|
||||
}
|
||||
|
||||
bool PostProcessor::XsortInt(std::vector<int> a, std::vector<int> b) {
|
||||
if (a[0] != b[0])
|
||||
return a[0] < b[0];
|
||||
return false;
|
||||
}
|
||||
|
||||
std::vector<std::vector<float>> PostProcessor::GetMiniBoxes(cv::RotatedRect box,
|
||||
float &ssid) {
|
||||
ssid = std::max(box.size.width, box.size.height);
|
||||
|
||||
cv::Mat points;
|
||||
cv::boxPoints(box, points);
|
||||
|
||||
auto array = Mat2Vector(points);
|
||||
std::sort(array.begin(), array.end(), XsortFp32);
|
||||
|
||||
std::vector<float> idx1 = array[0], idx2 = array[1], idx3 = array[2],
|
||||
idx4 = array[3];
|
||||
if (array[3][1] <= array[2][1]) {
|
||||
idx2 = array[3];
|
||||
idx3 = array[2];
|
||||
} else {
|
||||
idx2 = array[2];
|
||||
idx3 = array[3];
|
||||
}
|
||||
if (array[1][1] <= array[0][1]) {
|
||||
idx1 = array[1];
|
||||
idx4 = array[0];
|
||||
} else {
|
||||
idx1 = array[0];
|
||||
idx4 = array[1];
|
||||
}
|
||||
|
||||
array[0] = idx1;
|
||||
array[1] = idx2;
|
||||
array[2] = idx3;
|
||||
array[3] = idx4;
|
||||
|
||||
return array;
|
||||
}
|
||||
|
||||
float PostProcessor::PolygonScoreAcc(std::vector<cv::Point> contour,
|
||||
cv::Mat pred) {
|
||||
int width = pred.cols;
|
||||
int height = pred.rows;
|
||||
std::vector<float> box_x;
|
||||
std::vector<float> box_y;
|
||||
for (int i = 0; i < contour.size(); ++i) {
|
||||
box_x.push_back(contour[i].x);
|
||||
box_y.push_back(contour[i].y);
|
||||
}
|
||||
|
||||
int xmin =
|
||||
clamp(int(std::floor(*(std::min_element(box_x.begin(), box_x.end())))), 0,
|
||||
width - 1);
|
||||
int xmax =
|
||||
clamp(int(std::ceil(*(std::max_element(box_x.begin(), box_x.end())))), 0,
|
||||
width - 1);
|
||||
int ymin =
|
||||
clamp(int(std::floor(*(std::min_element(box_y.begin(), box_y.end())))), 0,
|
||||
height - 1);
|
||||
int ymax =
|
||||
clamp(int(std::ceil(*(std::max_element(box_y.begin(), box_y.end())))), 0,
|
||||
height - 1);
|
||||
|
||||
cv::Mat mask;
|
||||
mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1);
|
||||
|
||||
|
||||
cv::Point* rook_point = new cv::Point[contour.size()];
|
||||
|
||||
for (int i = 0; i < contour.size(); ++i) {
|
||||
rook_point[i] = cv::Point(int(box_x[i]) - xmin, int(box_y[i]) - ymin);
|
||||
}
|
||||
const cv::Point *ppt[1] = {rook_point};
|
||||
int npt[] = {int(contour.size())};
|
||||
|
||||
|
||||
cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1));
|
||||
|
||||
cv::Mat croppedImg;
|
||||
pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1)).copyTo(croppedImg);
|
||||
float score = cv::mean(croppedImg, mask)[0];
|
||||
|
||||
delete []rook_point;
|
||||
return score;
|
||||
}
|
||||
|
||||
float PostProcessor::BoxScoreFast(std::vector<std::vector<float>> box_array,
|
||||
cv::Mat pred) {
|
||||
auto array = box_array;
|
||||
int width = pred.cols;
|
||||
int height = pred.rows;
|
||||
|
||||
float box_x[4] = {array[0][0], array[1][0], array[2][0], array[3][0]};
|
||||
float box_y[4] = {array[0][1], array[1][1], array[2][1], array[3][1]};
|
||||
|
||||
int xmin = clamp(int(std::floor(*(std::min_element(box_x, box_x + 4)))), 0,
|
||||
width - 1);
|
||||
int xmax = clamp(int(std::ceil(*(std::max_element(box_x, box_x + 4)))), 0,
|
||||
width - 1);
|
||||
int ymin = clamp(int(std::floor(*(std::min_element(box_y, box_y + 4)))), 0,
|
||||
height - 1);
|
||||
int ymax = clamp(int(std::ceil(*(std::max_element(box_y, box_y + 4)))), 0,
|
||||
height - 1);
|
||||
|
||||
cv::Mat mask;
|
||||
mask = cv::Mat::zeros(ymax - ymin + 1, xmax - xmin + 1, CV_8UC1);
|
||||
|
||||
cv::Point root_point[4];
|
||||
root_point[0] = cv::Point(int(array[0][0]) - xmin, int(array[0][1]) - ymin);
|
||||
root_point[1] = cv::Point(int(array[1][0]) - xmin, int(array[1][1]) - ymin);
|
||||
root_point[2] = cv::Point(int(array[2][0]) - xmin, int(array[2][1]) - ymin);
|
||||
root_point[3] = cv::Point(int(array[3][0]) - xmin, int(array[3][1]) - ymin);
|
||||
const cv::Point *ppt[1] = {root_point};
|
||||
int npt[] = {4};
|
||||
cv::fillPoly(mask, ppt, npt, 1, cv::Scalar(1));
|
||||
|
||||
cv::Mat croppedImg;
|
||||
pred(cv::Rect(xmin, ymin, xmax - xmin + 1, ymax - ymin + 1))
|
||||
.copyTo(croppedImg);
|
||||
|
||||
auto score = cv::mean(croppedImg, mask)[0];
|
||||
return score;
|
||||
}
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> PostProcessor::BoxesFromBitmap(
|
||||
const cv::Mat pred, const cv::Mat bitmap, const float &box_thresh,
|
||||
const float &det_db_unclip_ratio, const bool &use_polygon_score) {
|
||||
const int min_size = 3;
|
||||
const int max_candidates = 1000;
|
||||
|
||||
int width = bitmap.cols;
|
||||
int height = bitmap.rows;
|
||||
|
||||
std::vector<std::vector<cv::Point>> contours;
|
||||
std::vector<cv::Vec4i> hierarchy;
|
||||
|
||||
cv::findContours(bitmap, contours, hierarchy, cv::RETR_LIST,
|
||||
cv::CHAIN_APPROX_SIMPLE);
|
||||
|
||||
int num_contours =
|
||||
contours.size() >= max_candidates ? max_candidates : contours.size();
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> boxes;
|
||||
|
||||
for (int _i = 0; _i < num_contours; _i++) {
|
||||
if (contours[_i].size() <= 2) {
|
||||
continue;
|
||||
}
|
||||
float ssid;
|
||||
cv::RotatedRect box = cv::minAreaRect(contours[_i]);
|
||||
auto array = GetMiniBoxes(box, ssid);
|
||||
|
||||
auto box_for_unclip = array;
|
||||
// end get_mini_box
|
||||
|
||||
if (ssid < min_size) {
|
||||
continue;
|
||||
}
|
||||
|
||||
float score;
|
||||
if (use_polygon_score)
|
||||
/* compute using polygon*/
|
||||
score = PolygonScoreAcc(contours[_i], pred);
|
||||
else
|
||||
score = BoxScoreFast(array, pred);
|
||||
|
||||
if (score < box_thresh)
|
||||
continue;
|
||||
|
||||
// start for unclip
|
||||
cv::RotatedRect points = UnClip(box_for_unclip, det_db_unclip_ratio);
|
||||
if (points.size.height < 1.001 && points.size.width < 1.001) {
|
||||
continue;
|
||||
}
|
||||
// end for unclip
|
||||
|
||||
cv::RotatedRect clipbox = points;
|
||||
auto cliparray = GetMiniBoxes(clipbox, ssid);
|
||||
|
||||
if (ssid < min_size + 2)
|
||||
continue;
|
||||
|
||||
int dest_width = pred.cols;
|
||||
int dest_height = pred.rows;
|
||||
std::vector<std::vector<int>> intcliparray;
|
||||
|
||||
for (int num_pt = 0; num_pt < 4; num_pt++) {
|
||||
std::vector<int> a{int(clampf(roundf(cliparray[num_pt][0] / float(width) *
|
||||
float(dest_width)),
|
||||
0, float(dest_width))),
|
||||
int(clampf(roundf(cliparray[num_pt][1] /
|
||||
float(height) * float(dest_height)),
|
||||
0, float(dest_height)))};
|
||||
intcliparray.push_back(a);
|
||||
}
|
||||
boxes.push_back(intcliparray);
|
||||
|
||||
} // end for
|
||||
return boxes;
|
||||
}
|
||||
|
||||
std::vector<std::vector<std::vector<int>>>
|
||||
PostProcessor::FilterTagDetRes(std::vector<std::vector<std::vector<int>>> boxes,
|
||||
float ratio_h, float ratio_w, cv::Mat srcimg) {
|
||||
int oriimg_h = srcimg.rows;
|
||||
int oriimg_w = srcimg.cols;
|
||||
|
||||
std::vector<std::vector<std::vector<int>>> root_points;
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
boxes[n] = OrderPointsClockwise(boxes[n]);
|
||||
for (int m = 0; m < boxes[0].size(); m++) {
|
||||
boxes[n][m][0] /= ratio_w;
|
||||
boxes[n][m][1] /= ratio_h;
|
||||
|
||||
boxes[n][m][0] = int(_min(_max(boxes[n][m][0], 0), oriimg_w - 1));
|
||||
boxes[n][m][1] = int(_min(_max(boxes[n][m][1], 0), oriimg_h - 1));
|
||||
}
|
||||
}
|
||||
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
int rect_width, rect_height;
|
||||
rect_width = int(sqrt(pow(boxes[n][0][0] - boxes[n][1][0], 2) +
|
||||
pow(boxes[n][0][1] - boxes[n][1][1], 2)));
|
||||
rect_height = int(sqrt(pow(boxes[n][0][0] - boxes[n][3][0], 2) +
|
||||
pow(boxes[n][0][1] - boxes[n][3][1], 2)));
|
||||
if (rect_width <= 4 || rect_height <= 4)
|
||||
continue;
|
||||
root_points.push_back(boxes[n]);
|
||||
}
|
||||
return root_points;
|
||||
}
|
||||
|
||||
} // namespace PaddleOCR
|
||||
|
|
@ -1,133 +0,0 @@
|
|||
// 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 <chrono>
|
||||
#include <iomanip>
|
||||
#include <iostream>
|
||||
#include <ostream>
|
||||
#include <vector>
|
||||
|
||||
#include <cstring>
|
||||
#include <fstream>
|
||||
#include <numeric>
|
||||
|
||||
#include <include/preprocess_op.h>
|
||||
|
||||
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<float> &mean,
|
||||
const std::vector<float> &scale, const bool is_scale) {
|
||||
double e = 1.0;
|
||||
if (is_scale) {
|
||||
e /= 255.0;
|
||||
}
|
||||
(*im).convertTo(*im, CV_32FC3, e);
|
||||
std::vector<cv::Mat> bgr_channels(3);
|
||||
cv::split(*im, bgr_channels);
|
||||
for (auto i = 0; i < bgr_channels.size(); i++) {
|
||||
bgr_channels[i].convertTo(bgr_channels[i], CV_32FC1, 1.0 * scale[i],
|
||||
(0.0 - mean[i]) * scale[i]);
|
||||
}
|
||||
cv::merge(bgr_channels, *im);
|
||||
}
|
||||
|
||||
void ResizeImgType0::Run(const cv::Mat &img, cv::Mat &resize_img,
|
||||
int max_size_len, float &ratio_h, float &ratio_w,
|
||||
bool use_tensorrt) {
|
||||
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);
|
||||
|
||||
resize_h = max(int(round(float(resize_h) / 32) * 32), 32);
|
||||
resize_w = max(int(round(float(resize_w) / 32) * 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 &resize_img, float wh_ratio,
|
||||
bool use_tensorrt,
|
||||
const std::vector<int> &rec_image_shape) {
|
||||
int imgC, imgH, imgW;
|
||||
imgC = rec_image_shape[0];
|
||||
imgH = rec_image_shape[1];
|
||||
imgW = rec_image_shape[2];
|
||||
|
||||
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::resize(img, resize_img, cv::Size(resize_w, imgH), 0.f, 0.f,
|
||||
cv::INTER_LINEAR);
|
||||
cv::copyMakeBorder(resize_img, 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,
|
||||
bool use_tensorrt,
|
||||
const std::vector<int> &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
|
||||
|
|
@ -1,95 +0,0 @@
|
|||
// 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 <dirent.h>
|
||||
#include <include/utility.h>
|
||||
#include <iostream>
|
||||
#include <ostream>
|
||||
#include <sys/stat.h>
|
||||
#include <sys/types.h>
|
||||
#include <vector>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
std::vector<std::string> Utility::ReadDict(const std::string &path) {
|
||||
std::ifstream in(path);
|
||||
std::string line;
|
||||
std::vector<std::string> m_vec;
|
||||
if (in) {
|
||||
while (getline(in, line)) {
|
||||
m_vec.push_back(line);
|
||||
}
|
||||
} else {
|
||||
std::cout << "no such label file: " << path << ", exit the program..."
|
||||
<< std::endl;
|
||||
exit(1);
|
||||
}
|
||||
return m_vec;
|
||||
}
|
||||
|
||||
void Utility::VisualizeBboxes(
|
||||
const cv::Mat &srcimg,
|
||||
const std::vector<std::vector<std::vector<int>>> &boxes) {
|
||||
cv::Mat img_vis;
|
||||
srcimg.copyTo(img_vis);
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
cv::Point rook_points[4];
|
||||
for (int m = 0; m < boxes[n].size(); m++) {
|
||||
rook_points[m] = cv::Point(int(boxes[n][m][0]), int(boxes[n][m][1]));
|
||||
}
|
||||
|
||||
const cv::Point *ppt[1] = {rook_points};
|
||||
int npt[] = {4};
|
||||
cv::polylines(img_vis, ppt, npt, 1, 1, CV_RGB(0, 255, 0), 2, 8, 0);
|
||||
}
|
||||
|
||||
cv::imwrite("./ocr_vis.png", img_vis);
|
||||
std::cout << "The detection visualized image saved in ./ocr_vis.png"
|
||||
<< std::endl;
|
||||
}
|
||||
|
||||
// list all files under a directory
|
||||
void Utility::GetAllFiles(const char *dir_name,
|
||||
std::vector<std::string> &all_inputs) {
|
||||
if (NULL == dir_name) {
|
||||
std::cout << " dir_name is null ! " << std::endl;
|
||||
return;
|
||||
}
|
||||
struct stat s;
|
||||
lstat(dir_name, &s);
|
||||
if (!S_ISDIR(s.st_mode)) {
|
||||
std::cout << "dir_name is not a valid directory !" << std::endl;
|
||||
all_inputs.push_back(dir_name);
|
||||
return;
|
||||
} else {
|
||||
struct dirent *filename; // return value for readdir()
|
||||
DIR *dir; // return value for opendir()
|
||||
dir = opendir(dir_name);
|
||||
if (NULL == dir) {
|
||||
std::cout << "Can not open dir " << dir_name << std::endl;
|
||||
return;
|
||||
}
|
||||
std::cout << "Successfully opened the dir !" << std::endl;
|
||||
while ((filename = readdir(dir)) != NULL) {
|
||||
if (strcmp(filename->d_name, ".") == 0 ||
|
||||
strcmp(filename->d_name, "..") == 0)
|
||||
continue;
|
||||
// img_dir + std::string("/") + all_inputs[0];
|
||||
all_inputs.push_back(dir_name + std::string("/") +
|
||||
std::string(filename->d_name));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace PaddleOCR
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -28,10 +28,8 @@
|
|||
#include <numeric>
|
||||
|
||||
#include <glog/logging.h>
|
||||
// #include <include/config.h>
|
||||
#include <include/ocr_det.h>
|
||||
#include <include/ocr_rec.h>
|
||||
// #include <include/utility.h>
|
||||
#include <sys/stat.h>
|
||||
|
||||
#include <gflags/gflags.h>
|
||||
|
|
|
|||
|
|
@ -13,6 +13,8 @@
|
|||
// limitations under the License.
|
||||
|
||||
#include <include/ocr_det.h>
|
||||
#include <include/preprocess_op.cpp>
|
||||
#include <include/postprocess_op.cpp>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
|
|
|
|||
|
|
@ -1,133 +0,0 @@
|
|||
// 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 <chrono>
|
||||
#include <iomanip>
|
||||
#include <iostream>
|
||||
#include <ostream>
|
||||
#include <vector>
|
||||
|
||||
#include <cstring>
|
||||
#include <fstream>
|
||||
#include <numeric>
|
||||
|
||||
#include <include/preprocess_op.h>
|
||||
|
||||
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<float> &mean,
|
||||
const std::vector<float> &scale, const bool is_scale) {
|
||||
double e = 1.0;
|
||||
if (is_scale) {
|
||||
e /= 255.0;
|
||||
}
|
||||
(*im).convertTo(*im, CV_32FC3, e);
|
||||
std::vector<cv::Mat> bgr_channels(3);
|
||||
cv::split(*im, bgr_channels);
|
||||
for (auto i = 0; i < bgr_channels.size(); i++) {
|
||||
bgr_channels[i].convertTo(bgr_channels[i], CV_32FC1, 1.0 * scale[i],
|
||||
(0.0 - mean[i]) * scale[i]);
|
||||
}
|
||||
cv::merge(bgr_channels, *im);
|
||||
}
|
||||
|
||||
void ResizeImgType0::Run(const cv::Mat &img, cv::Mat &resize_img,
|
||||
int max_size_len, float &ratio_h, float &ratio_w,
|
||||
bool use_tensorrt) {
|
||||
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);
|
||||
|
||||
resize_h = max(int(round(float(resize_h) / 32) * 32), 32);
|
||||
resize_w = max(int(round(float(resize_w) / 32) * 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 &resize_img, float wh_ratio,
|
||||
bool use_tensorrt,
|
||||
const std::vector<int> &rec_image_shape) {
|
||||
int imgC, imgH, imgW;
|
||||
imgC = rec_image_shape[0];
|
||||
imgH = rec_image_shape[1];
|
||||
imgW = rec_image_shape[2];
|
||||
|
||||
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::resize(img, resize_img, cv::Size(resize_w, imgH), 0.f, 0.f,
|
||||
cv::INTER_LINEAR);
|
||||
cv::copyMakeBorder(resize_img, 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,
|
||||
bool use_tensorrt,
|
||||
const std::vector<int> &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
|
||||
|
|
@ -1,95 +0,0 @@
|
|||
// 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 <dirent.h>
|
||||
#include <include/utility.h>
|
||||
#include <iostream>
|
||||
#include <ostream>
|
||||
#include <sys/stat.h>
|
||||
#include <sys/types.h>
|
||||
#include <vector>
|
||||
|
||||
namespace PaddleOCR {
|
||||
|
||||
std::vector<std::string> Utility::ReadDict(const std::string &path) {
|
||||
std::ifstream in(path);
|
||||
std::string line;
|
||||
std::vector<std::string> m_vec;
|
||||
if (in) {
|
||||
while (getline(in, line)) {
|
||||
m_vec.push_back(line);
|
||||
}
|
||||
} else {
|
||||
std::cout << "no such label file: " << path << ", exit the program..."
|
||||
<< std::endl;
|
||||
exit(1);
|
||||
}
|
||||
return m_vec;
|
||||
}
|
||||
|
||||
void Utility::VisualizeBboxes(
|
||||
const cv::Mat &srcimg,
|
||||
const std::vector<std::vector<std::vector<int>>> &boxes) {
|
||||
cv::Mat img_vis;
|
||||
srcimg.copyTo(img_vis);
|
||||
for (int n = 0; n < boxes.size(); n++) {
|
||||
cv::Point rook_points[4];
|
||||
for (int m = 0; m < boxes[n].size(); m++) {
|
||||
rook_points[m] = cv::Point(int(boxes[n][m][0]), int(boxes[n][m][1]));
|
||||
}
|
||||
|
||||
const cv::Point *ppt[1] = {rook_points};
|
||||
int npt[] = {4};
|
||||
cv::polylines(img_vis, ppt, npt, 1, 1, CV_RGB(0, 255, 0), 2, 8, 0);
|
||||
}
|
||||
|
||||
cv::imwrite("./ocr_vis.png", img_vis);
|
||||
std::cout << "The detection visualized image saved in ./ocr_vis.png"
|
||||
<< std::endl;
|
||||
}
|
||||
|
||||
// list all files under a directory
|
||||
void Utility::GetAllFiles(const char *dir_name,
|
||||
std::vector<std::string> &all_inputs) {
|
||||
if (NULL == dir_name) {
|
||||
std::cout << " dir_name is null ! " << std::endl;
|
||||
return;
|
||||
}
|
||||
struct stat s;
|
||||
lstat(dir_name, &s);
|
||||
if (!S_ISDIR(s.st_mode)) {
|
||||
std::cout << "dir_name is not a valid directory !" << std::endl;
|
||||
all_inputs.push_back(dir_name);
|
||||
return;
|
||||
} else {
|
||||
struct dirent *filename; // return value for readdir()
|
||||
DIR *dir; // return value for opendir()
|
||||
dir = opendir(dir_name);
|
||||
if (NULL == dir) {
|
||||
std::cout << "Can not open dir " << dir_name << std::endl;
|
||||
return;
|
||||
}
|
||||
std::cout << "Successfully opened the dir !" << std::endl;
|
||||
while ((filename = readdir(dir)) != NULL) {
|
||||
if (strcmp(filename->d_name, ".") == 0 ||
|
||||
strcmp(filename->d_name, "..") == 0)
|
||||
continue;
|
||||
// img_dir + std::string("/") + all_inputs[0];
|
||||
all_inputs.push_back(dir_name + std::string("/") +
|
||||
std::string(filename->d_name));
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
} // namespace PaddleOCR
|
||||
Loading…
Reference in New Issue