mmdeploy/demo/csrc/ocr.cpp
Yue Zhou 9411fe0466
Add nms_rotated ort op (#312)
* fix pose demo and windows build (#307)

* init

* Update nms_rotated.cpp

* add postprocessing_masks gpu version (#276)

* add postprocessing_masks gpu version

* default device cpu

* pre-commit fix

Co-authored-by: hadoop-basecv <hadoop-basecv@set-gh-basecv-serving-classify11.mt>

* fixed a bug causes text-recognizer to fail when (non-NULL) empty bboxes list is passed (#310)

* [Fix] include missing <type_traits> for formatter.h (#313)

* fix formatter

* relax GCC version requirement

* fix

* fix lint

* fix lint

* [Fix] MMEditing cannot save results when testing (#336)

* fix show

* lint

* remove redundant codes

* resolve comment

* type hint

* docs(build): fix typo (#352)

* docs(build): add missing build option

* docs(build): add onnx install

* style(doc): trim whitespace

* docs(build): revert install onnx

* docs(build): add ncnn LD_LIBRARY_PATH

* docs(build): fix path error

* fix openvino export tmp model, add binary flag (#353)

* init circleci (#348)

* fix wrong input mat type (#362)

* fix wrong input mat type

* fix lint

* fix(docs): remove redundant doc tree (#360)

* fix missing ncnn_DIR & InferenceEngine_DIR (#364)

* update doc

Co-authored-by: Chen Xin <xinchen.tju@gmail.com>
Co-authored-by: Shengxi Li <982783556@qq.com>
Co-authored-by: hadoop-basecv <hadoop-basecv@set-gh-basecv-serving-classify11.mt>
Co-authored-by: lzhangzz <lzhang329@gmail.com>
Co-authored-by: Yifan Zhou <singlezombie@163.com>
Co-authored-by: tpoisonooo <khj.application@aliyun.com>
Co-authored-by: lvhan028 <lvhan_028@163.com>
2022-04-18 17:14:47 +08:00

80 lines
2.5 KiB
C++

#include <fstream>
#include <opencv2/imgcodecs/imgcodecs.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include <string>
#include "text_detector.h"
#include "text_recognizer.h"
int main(int argc, char *argv[]) {
if (argc != 5) {
fprintf(stderr, "usage:\n ocr device_name det_model_path reg_model_path image_path\n");
return 1;
}
auto device_name = argv[1];
auto det_model_path = argv[2];
auto reg_model_path = argv[3];
auto image_path = argv[4];
cv::Mat img = cv::imread(image_path);
if (!img.data) {
fprintf(stderr, "failed to load image: %s\n", image_path);
return 1;
}
mm_handle_t text_detector{};
int status{};
status = mmdeploy_text_detector_create_by_path(det_model_path, device_name, 0, &text_detector);
if (status != MM_SUCCESS) {
fprintf(stderr, "failed to create text_detector, code: %d\n", (int)status);
return 1;
}
mm_handle_t text_recognizer{};
status = mmdeploy_text_recognizer_create_by_path(reg_model_path, device_name, 0, &text_recognizer);
if (status != MM_SUCCESS) {
fprintf(stderr, "failed to create text_recognizer, code: %d\n", (int)status);
return 1;
}
mm_mat_t mat{img.data, img.rows, img.cols, 3, MM_BGR, MM_INT8};
mm_text_detect_t *bboxes{};
int *bbox_count{};
status = mmdeploy_text_detector_apply(text_detector, &mat, 1, &bboxes, &bbox_count);
if (status != MM_SUCCESS) {
fprintf(stderr, "failed to apply text_detector, code: %d\n", (int)status);
return 1;
}
fprintf(stdout, "bbox_count=%d\n", *bbox_count);
mm_text_recognize_t *texts{};
status =
mmdeploy_text_recognizer_apply_bbox(text_recognizer, &mat, 1, bboxes, bbox_count, &texts);
if (status != MM_SUCCESS) {
fprintf(stderr, "failed to apply text_recognizer, code: %d\n", (int)status);
return 1;
}
for (int i = 0; i < *bbox_count; ++i) {
fprintf(stdout, "box[%d]: %s\n", i, texts[i].text);
std::vector<cv::Point> poly_points;
for (int j = 0; j < 4; ++j) {
auto const &pt = bboxes[i].bbox[j];
fprintf(stdout, "x: %.2f, y: %.2f, ", pt.x, pt.y);
poly_points.push_back({(int)pt.x, (int)pt.y});
}
fprintf(stdout, "\n");
cv::polylines(img, poly_points, true, cv::Scalar{0, 255, 0});
}
cv::imwrite("output_ocr.png", img);
mmdeploy_text_recognizer_release_result(texts, *bbox_count);
mmdeploy_text_recognizer_destroy(text_recognizer);
mmdeploy_text_detector_release_result(bboxes, bbox_count, 1);
mmdeploy_text_detector_destroy(text_detector);
return 0;
}