增加模糊图片增强功能
This commit is contained in:
parent
aafd81fc5f
commit
54d5deb832
|
|
@ -2,12 +2,11 @@
|
|||
#include <string>
|
||||
#include <vector>
|
||||
|
||||
|
||||
FacePipeline::FacePipeline(const std::string &model_dir)
|
||||
: m_env(ORT_LOGGING_LEVEL_WARNING, "FaceSDK"),
|
||||
m_memory_info(
|
||||
Ort::MemoryInfo::CreateCpu(OrtArenaAllocator, OrtMemTypeDefault)) {
|
||||
m_session_options.SetIntraOpNumThreads(4);
|
||||
m_session_options.SetIntraOpNumThreads(4);
|
||||
m_session_options.SetGraphOptimizationLevel(
|
||||
GraphOptimizationLevel::ORT_ENABLE_ALL);
|
||||
|
||||
|
|
@ -22,7 +21,6 @@ FacePipeline::FacePipeline(const std::string &model_dir)
|
|||
|
||||
FacePipeline::~FacePipeline() {}
|
||||
|
||||
|
||||
bool FacePipeline::LoadModels(const std::string &model_dir) {
|
||||
auto load_session = [&](std::unique_ptr<Ort::Session> &session,
|
||||
const std::string &model_name) {
|
||||
|
|
@ -57,9 +55,8 @@ bool FacePipeline::LoadModels(const std::string &model_dir) {
|
|||
return true;
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::InitMemoryAllocators() {
|
||||
|
||||
|
||||
auto get_io_names = [&](Ort::Session *session,
|
||||
std::vector<const char *> &input_names,
|
||||
std::vector<const char *> &output_names,
|
||||
|
|
@ -99,7 +96,6 @@ void FacePipeline::InitMemoryAllocators() {
|
|||
throw std::runtime_error("Model input shape is empty");
|
||||
}
|
||||
|
||||
|
||||
std::string shape_str = "[";
|
||||
for (long long dim : input_shape)
|
||||
shape_str += std::to_string(dim) + ", ";
|
||||
|
|
@ -107,13 +103,12 @@ void FacePipeline::InitMemoryAllocators() {
|
|||
LOGI("Model %s input shape: %s", model_name, shape_str.c_str());
|
||||
|
||||
if (input_shape[0] < 1)
|
||||
input_shape[0] = 1;
|
||||
input_shape[0] = 1;
|
||||
} else {
|
||||
LOGE("Model %s has no inputs!", model_name);
|
||||
}
|
||||
};
|
||||
|
||||
|
||||
get_io_names(m_session_rotator.get(), m_rot_input_names, m_rot_output_names,
|
||||
m_rot_input_shape, "Rotator");
|
||||
get_io_names(m_session_detector.get(), m_det_input_names, m_det_output_names,
|
||||
|
|
@ -129,41 +124,38 @@ void FacePipeline::InitMemoryAllocators() {
|
|||
get_io_names(m_session_recognizer.get(), m_rec_input_names,
|
||||
m_rec_output_names, m_rec_input_shape, "Recognizer");
|
||||
|
||||
|
||||
if (m_det_input_shape.size() < 4) {
|
||||
LOGE("Detector input shape has < 4 dimensions! Cannot generate anchors.");
|
||||
throw std::runtime_error("Detector input shape invalid");
|
||||
}
|
||||
|
||||
|
||||
if (m_det_input_shape[2] < 0 || m_det_input_shape[3] < 0) {
|
||||
LOGE("Detector input shape is dynamic (H/W is -1). This is not supported "
|
||||
"by the Python logic.");
|
||||
|
||||
|
||||
LOGI("Forcing detector H/W to 640x640.");
|
||||
m_det_input_shape[2] = 640;
|
||||
m_det_input_shape[3] = 640;
|
||||
}
|
||||
generate_anchors_faceboxes(m_det_input_shape[2], m_det_input_shape[3]);
|
||||
|
||||
|
||||
size_t max_blob_size = 0;
|
||||
|
||||
|
||||
auto update_max = [&](const std::vector<int64_t> &shape,
|
||||
const char *model_name) {
|
||||
if (shape.size() <= 1) {
|
||||
return;
|
||||
return;
|
||||
}
|
||||
|
||||
size_t s = 1;
|
||||
|
||||
|
||||
for (size_t i = 1; i < shape.size(); ++i) {
|
||||
if (shape[i] < 0) {
|
||||
|
||||
|
||||
LOGE("Model %s has dynamic dimension at index %zu. Skipping for "
|
||||
"max_blob_size calculation.",
|
||||
model_name, i);
|
||||
return;
|
||||
return;
|
||||
}
|
||||
s *= static_cast<size_t>(shape[i]);
|
||||
}
|
||||
|
|
@ -178,7 +170,6 @@ void FacePipeline::InitMemoryAllocators() {
|
|||
update_max(m_pose_var_input_shape, "PoseVar");
|
||||
update_max(m_lm1_input_shape, "Landmarker1");
|
||||
update_max(m_rec_input_shape, "Recognizer");
|
||||
|
||||
|
||||
if (max_blob_size == 0) {
|
||||
LOGE(
|
||||
|
|
@ -191,7 +182,6 @@ void FacePipeline::InitMemoryAllocators() {
|
|||
LOGI("m_blob_buffer resized successfully.");
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::image_to_blob(const cv::Mat &img, std::vector<float> &blob,
|
||||
const float *mean, const float *std) {
|
||||
int channels = img.channels();
|
||||
|
|
@ -221,8 +211,6 @@ FacePipeline::create_tensor(const std::vector<float> &blob_data,
|
|||
input_shape.data(), input_shape.size());
|
||||
}
|
||||
|
||||
|
||||
|
||||
bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
||||
if (!m_initialized) {
|
||||
LOGE("Extract failed: Pipeline is not initialized.");
|
||||
|
|
@ -233,8 +221,6 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
int rot_angle_code = RunRotation(image);
|
||||
cv::Mat upright_image;
|
||||
if (rot_angle_code >= 0) {
|
||||
|
|
@ -243,8 +229,6 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
upright_image = image;
|
||||
}
|
||||
|
||||
|
||||
|
||||
std::vector<FaceBox> boxes;
|
||||
if (!RunDetection(upright_image, boxes)) {
|
||||
LOGI("Extract failed: No face detected.");
|
||||
|
|
@ -252,9 +236,6 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
}
|
||||
FaceBox best_box = boxes[0];
|
||||
|
||||
|
||||
|
||||
|
||||
cv::Rect face_rect_raw(best_box.x1, best_box.y1, best_box.x2 - best_box.x1,
|
||||
best_box.y2 - best_box.y1);
|
||||
int pad_top = std::max(0, -face_rect_raw.y);
|
||||
|
|
@ -273,7 +254,6 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
face_rect_raw.y + pad_top, face_rect_raw.width,
|
||||
face_rect_raw.height);
|
||||
|
||||
|
||||
if (face_rect_padded.width <= 0 || face_rect_padded.height <= 0 ||
|
||||
face_rect_padded.x < 0 || face_rect_padded.y < 0 ||
|
||||
face_rect_padded.x + face_rect_padded.width > face_crop_padded.cols ||
|
||||
|
|
@ -288,33 +268,24 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
FaceLandmark landmark;
|
||||
if (!RunLandmark(upright_image, best_box, landmark)) {
|
||||
LOGI("Extract failed: Landmark detection failed.");
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
cv::Mat aligned_face = RunAlignment(upright_image, landmark);
|
||||
if (aligned_face.empty()) {
|
||||
LOGI("Extract failed: Alignment produced an empty image.");
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
FacePose pose;
|
||||
if (!RunPose(aligned_face, pose))
|
||||
{
|
||||
if (!RunPose(aligned_face, pose)) {
|
||||
LOGI("Extract failed: Pose estimation failed.");
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (std::abs(pose.yaw) > m_pose_yaw_threshold ||
|
||||
std::abs(pose.pitch) > m_pose_pitch_threshold) {
|
||||
LOGI("Extract failed: Face pose (Y:%.1f, P:%.1f) exceeds threshold "
|
||||
|
|
@ -322,45 +293,36 @@ bool FacePipeline::Extract(const cv::Mat &image, std::vector<float> &feature) {
|
|||
pose.yaw, pose.pitch, m_pose_yaw_threshold, m_pose_pitch_threshold);
|
||||
return false;
|
||||
}
|
||||
cv::Mat enhanced_face_region = PreprocessSmallFace(face_region);
|
||||
|
||||
|
||||
|
||||
if (!CheckResolution(face_region)) {
|
||||
if (!CheckResolution(enhanced_face_region)) {
|
||||
LOGI("Extract failed: Resolution (H:%d, W:%d) below threshold (%d, %d)",
|
||||
face_region.rows, face_region.cols, m_quality_min_resolution.height,
|
||||
m_quality_min_resolution.width);
|
||||
enhanced_face_region.rows, enhanced_face_region.cols,
|
||||
m_quality_min_resolution.height, m_quality_min_resolution.width);
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (!CheckBrightness(face_region)) {
|
||||
if (!CheckBrightness(enhanced_face_region)) {
|
||||
LOGI("Extract failed: Brightness check failed (thresholds [%.1f, %.1f]).",
|
||||
m_quality_bright_v1, m_quality_bright_v2);
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (!CheckClarity(face_region)) {
|
||||
if (!CheckClarity(enhanced_face_region)) {
|
||||
LOGI("Extract failed: Clarity check failed (threshold [%.2f]).",
|
||||
m_quality_clarity_low_thresh);
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
|
||||
if (!RunRecognition(aligned_face, feature)) {
|
||||
LOGI("Extract failed: Feature recognition failed.");
|
||||
return false;
|
||||
}
|
||||
|
||||
|
||||
LOGI("Extract success.");
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::preprocess_rotation(const cv::Mat &image,
|
||||
std::vector<float> &blob_data) {
|
||||
cv::Mat gray_img, resized, cropped, gray_3d;
|
||||
|
|
@ -369,12 +331,10 @@ void FacePipeline::preprocess_rotation(const cv::Mat &image,
|
|||
int start = (256 - 224) / 2;
|
||||
cv::Rect crop_rect(start, start, 224, 224);
|
||||
cropped = resized(crop_rect);
|
||||
cv::cvtColor(cropped, gray_3d, cv::COLOR_GRAY2BGR);
|
||||
cv::cvtColor(cropped, gray_3d, cv::COLOR_GRAY2BGR);
|
||||
|
||||
|
||||
const float mean[3] = {0.0f, 0.0f, 0.0f};
|
||||
const float std[3] = {1.0f / 255.0f, 1.0f / 255.0f,
|
||||
1.0f / 255.0f};
|
||||
const float std[3] = {1.0f / 255.0f, 1.0f / 255.0f, 1.0f / 255.0f};
|
||||
image_to_blob(gray_3d, blob_data, mean, std);
|
||||
}
|
||||
|
||||
|
|
@ -390,7 +350,6 @@ int FacePipeline::RunRotation(const cv::Mat &image) {
|
|||
int max_index = std::distance(output_data,
|
||||
std::max_element(output_data, output_data + 4));
|
||||
|
||||
|
||||
if (max_index == 1)
|
||||
return cv::ROTATE_90_CLOCKWISE;
|
||||
if (max_index == 2)
|
||||
|
|
@ -400,15 +359,13 @@ int FacePipeline::RunRotation(const cv::Mat &image) {
|
|||
return -1;
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::preprocess_detection(const cv::Mat &img,
|
||||
std::vector<float> &blob_data) {
|
||||
cv::Mat resized;
|
||||
cv::resize(img, resized,
|
||||
cv::Size(m_det_input_shape[3], m_det_input_shape[2]));
|
||||
cv::Size(m_det_input_shape[3], m_det_input_shape[2]));
|
||||
|
||||
|
||||
const float mean[3] = {104.0f, 117.0f, 123.0f};
|
||||
const float mean[3] = {104.0f, 117.0f, 123.0f};
|
||||
const float std[3] = {1.0f, 1.0f, 1.0f};
|
||||
image_to_blob(resized, blob_data, mean, std);
|
||||
}
|
||||
|
|
@ -423,12 +380,10 @@ bool FacePipeline::RunDetection(const cv::Mat &image,
|
|||
|
||||
auto output_tensors = m_session_detector->Run(
|
||||
Ort::RunOptions{nullptr}, m_det_input_names.data(), &input_tensor, 1,
|
||||
m_det_output_names.data(), 2);
|
||||
m_det_output_names.data(), 2);
|
||||
|
||||
const float *bboxes_data =
|
||||
output_tensors[0].GetTensorData<float>();
|
||||
const float *probs_data =
|
||||
output_tensors[1].GetTensorData<float>();
|
||||
const float *bboxes_data = output_tensors[0].GetTensorData<float>();
|
||||
const float *probs_data = output_tensors[1].GetTensorData<float>();
|
||||
long num_anchors =
|
||||
output_tensors[0].GetTensorTypeAndShapeInfo().GetShape()[1];
|
||||
|
||||
|
|
@ -439,10 +394,10 @@ bool FacePipeline::RunDetection(const cv::Mat &image,
|
|||
}
|
||||
|
||||
std::vector<FaceBox> bbox_collection;
|
||||
const float variance[2] = {0.1f, 0.2f};
|
||||
const float variance[2] = {0.1f, 0.2f};
|
||||
|
||||
for (long i = 0; i < num_anchors; ++i) {
|
||||
float conf = probs_data[i * 2 + 1];
|
||||
float conf = probs_data[i * 2 + 1];
|
||||
if (conf < m_det_threshold)
|
||||
continue;
|
||||
|
||||
|
|
@ -452,24 +407,23 @@ bool FacePipeline::RunDetection(const cv::Mat &image,
|
|||
float dw = bboxes_data[i * 4 + 2];
|
||||
float dh = bboxes_data[i * 4 + 3];
|
||||
|
||||
float cx = anchor.cx + dx * variance[0] * anchor.s_kx;
|
||||
float cy = anchor.cy + dy * variance[0] * anchor.s_ky;
|
||||
float w = anchor.s_kx * std::exp(dw * variance[1]);
|
||||
float h = anchor.s_ky * std::exp(dh * variance[1]);
|
||||
float cx = anchor.cx + dx * variance[0] * anchor.s_kx;
|
||||
float cy = anchor.cy + dy * variance[0] * anchor.s_ky;
|
||||
float w = anchor.s_kx * std::exp(dw * variance[1]);
|
||||
float h = anchor.s_ky * std::exp(dh * variance[1]);
|
||||
|
||||
bbox_collection.push_back(
|
||||
{(cx - w / 2.0f) * img_width, (cy - h / 2.0f) * img_height,
|
||||
(cx + w / 2.0f) * img_width, (cy + h / 2.0f) * img_height, conf});
|
||||
}
|
||||
|
||||
boxes = hard_nms(bbox_collection, m_det_iou_threshold,
|
||||
m_det_topk);
|
||||
boxes = hard_nms(bbox_collection, m_det_iou_threshold, m_det_topk);
|
||||
return !boxes.empty();
|
||||
}
|
||||
|
||||
void FacePipeline::generate_anchors_faceboxes(int target_height,
|
||||
int target_width) {
|
||||
|
||||
|
||||
m_anchors.clear();
|
||||
std::vector<int> steps = {32, 64, 128};
|
||||
std::vector<std::vector<int>> min_sizes = {{32, 64, 128}, {256}, {512}};
|
||||
|
|
@ -516,13 +470,9 @@ void FacePipeline::generate_anchors_faceboxes(int target_height,
|
|||
}
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::preprocess_pose(const cv::Mat &img,
|
||||
std::vector<float> &blob_data) {
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
float pad = 0.3f;
|
||||
int h = img.rows;
|
||||
int w = img.cols;
|
||||
|
|
@ -535,27 +485,23 @@ void FacePipeline::preprocess_pose(const cv::Mat &img,
|
|||
img.copyTo(canvas(cv::Rect(nx1, ny1, w, h)));
|
||||
|
||||
cv::Mat resized;
|
||||
cv::resize(
|
||||
canvas, resized,
|
||||
cv::Size(m_pose_var_input_shape[3], m_pose_var_input_shape[2]));
|
||||
cv::resize(canvas, resized,
|
||||
cv::Size(m_pose_var_input_shape[3], m_pose_var_input_shape[2]));
|
||||
|
||||
|
||||
const float mean[3] = {127.5f, 127.5f, 127.5f};
|
||||
const float std[3] = {1.0f / 127.5f, 1.0f / 127.5f, 1.0f / 127.5f};
|
||||
image_to_blob(resized, blob_data, mean, std);
|
||||
}
|
||||
|
||||
bool FacePipeline::RunPose(const cv::Mat &face_input, FacePose &pose) {
|
||||
|
||||
|
||||
preprocess_pose(face_input, m_blob_buffer);
|
||||
|
||||
|
||||
auto input_tensor_var = create_tensor(m_blob_buffer, m_pose_var_input_shape);
|
||||
auto output_var = m_session_pose_var->Run(
|
||||
Ort::RunOptions{nullptr}, m_pose_var_input_names.data(),
|
||||
&input_tensor_var, 1, m_pose_var_output_names.data(), 1);
|
||||
|
||||
|
||||
auto input_tensor_conv =
|
||||
create_tensor(m_blob_buffer, m_pose_conv_input_shape);
|
||||
auto output_conv = m_session_pose_conv->Run(
|
||||
|
|
@ -565,28 +511,24 @@ bool FacePipeline::RunPose(const cv::Mat &face_input, FacePose &pose) {
|
|||
const float *data_var = output_var[0].GetTensorData<float>();
|
||||
const float *data_conv = output_conv[0].GetTensorData<float>();
|
||||
|
||||
|
||||
pose.yaw = (data_var[0] + data_conv[0]) / 2.0f;
|
||||
pose.pitch = (data_var[1] + data_conv[1]) / 2.0f;
|
||||
pose.roll = (data_var[2] + data_conv[2]) / 2.0f;
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::preprocess_landmark_net1(const cv::Mat &img,
|
||||
std::vector<float> &blob_data) {
|
||||
cv::Mat resized, gray_img;
|
||||
cv::resize(img, resized,
|
||||
cv::Size(m_lm1_input_shape[3], m_lm1_input_shape[2]));
|
||||
cv::cvtColor(resized, gray_img, cv::COLOR_BGR2GRAY);
|
||||
cv::Size(m_lm1_input_shape[3], m_lm1_input_shape[2]));
|
||||
cv::cvtColor(resized, gray_img, cv::COLOR_BGR2GRAY);
|
||||
|
||||
|
||||
const float mean[1] = {0.0f};
|
||||
const float std[1] = {1.0f};
|
||||
image_to_blob(gray_img, blob_data, mean, std);
|
||||
}
|
||||
|
||||
|
||||
std::vector<float>
|
||||
FacePipeline::shape_index_process(const Ort::Value &feat_val,
|
||||
const Ort::Value &pos_val) {
|
||||
|
|
@ -595,13 +537,13 @@ FacePipeline::shape_index_process(const Ort::Value &feat_val,
|
|||
const float *feat_data = feat_val.GetTensorData<float>();
|
||||
const float *pos_data = pos_val.GetTensorData<float>();
|
||||
|
||||
long feat_n = feat_shape[0];
|
||||
long feat_n = feat_shape[0];
|
||||
long feat_c = feat_shape[1];
|
||||
long feat_h = feat_shape[2];
|
||||
long feat_w = feat_shape[3];
|
||||
long pos_n = pos_shape[0];
|
||||
long landmark_x2 = pos_shape[1];
|
||||
int landmark_num = landmark_x2 / 2;
|
||||
long pos_n = pos_shape[0];
|
||||
long landmark_x2 = pos_shape[1];
|
||||
int landmark_num = landmark_x2 / 2;
|
||||
|
||||
float m_origin[] = {112.0f, 112.0f};
|
||||
float m_origin_patch[] = {15.0f, 15.0f};
|
||||
|
|
@ -655,7 +597,7 @@ FacePipeline::shape_index_process(const Ort::Value &feat_val,
|
|||
|
||||
bool FacePipeline::RunLandmark(const cv::Mat &image, const FaceBox &box,
|
||||
FaceLandmark &landmark) {
|
||||
|
||||
|
||||
cv::Rect face_rect_raw(box.x1, box.y1, box.x2 - box.x1, box.y2 - box.y1);
|
||||
int pad_top = std::max(0, -face_rect_raw.y);
|
||||
int pad_bottom =
|
||||
|
|
@ -671,41 +613,34 @@ bool FacePipeline::RunLandmark(const cv::Mat &image, const FaceBox &box,
|
|||
face_rect_raw.height);
|
||||
cv::Mat face_crop = face_crop_padded(face_rect_padded);
|
||||
|
||||
|
||||
preprocess_landmark_net1(face_crop, m_blob_buffer);
|
||||
auto input_tensor_net1 = create_tensor(m_blob_buffer, m_lm1_input_shape);
|
||||
|
||||
|
||||
auto output_net1 = m_session_landmarker1->Run(
|
||||
Ort::RunOptions{nullptr}, m_lm1_input_names.data(), &input_tensor_net1, 1,
|
||||
m_lm1_output_names.data(), 2);
|
||||
m_lm1_output_names.data(), 2);
|
||||
|
||||
|
||||
std::vector<float> shape_index_blob =
|
||||
shape_index_process(output_net1[0], output_net1[1]);
|
||||
|
||||
|
||||
auto input_tensor_net2 = Ort::Value::CreateTensor<float>(
|
||||
m_memory_info, shape_index_blob.data(), shape_index_blob.size(),
|
||||
m_lm2_input_shape.data(), m_lm2_input_shape.size());
|
||||
|
||||
|
||||
auto output_net2 = m_session_landmarker2->Run(
|
||||
Ort::RunOptions{nullptr}, m_lm2_input_names.data(), &input_tensor_net2, 1,
|
||||
m_lm2_output_names.data(), 1);
|
||||
|
||||
|
||||
const float *data_net1_pos = output_net1[1].GetTensorData<float>();
|
||||
const float *data_net2 = output_net2[0].GetTensorData<float>();
|
||||
auto shape_net1_pos =
|
||||
output_net1[1].GetTensorTypeAndShapeInfo().GetShape();
|
||||
auto shape_net1_pos = output_net1[1].GetTensorTypeAndShapeInfo().GetShape();
|
||||
int landmark_x2 = shape_net1_pos[1];
|
||||
|
||||
float scale_x = (box.x2 - box.x1) / 112.0f;
|
||||
float scale_y = (box.y2 - box.y1) / 112.0f;
|
||||
|
||||
for (int i = 0; i < 5; ++i) {
|
||||
|
||||
|
||||
float x_norm = (data_net2[i * 2 + 0] + data_net1_pos[i * 2 + 0]) * 112.0f;
|
||||
float y_norm = (data_net2[i * 2 + 1] + data_net1_pos[i * 2 + 1]) * 112.0f;
|
||||
|
||||
|
|
@ -719,10 +654,9 @@ bool FacePipeline::RunLandmark(const cv::Mat &image, const FaceBox &box,
|
|||
return true;
|
||||
}
|
||||
|
||||
|
||||
cv::Mat FacePipeline::RunAlignment(const cv::Mat &image,
|
||||
const FaceLandmark &landmark) {
|
||||
|
||||
|
||||
std::vector<cv::Point2f> src_points;
|
||||
std::vector<cv::Point2f> dst_points;
|
||||
|
||||
|
|
@ -732,49 +666,40 @@ cv::Mat FacePipeline::RunAlignment(const cv::Mat &image,
|
|||
m_landmark_template.at<float>(i, 1)));
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
cv::Mat transform_matrix =
|
||||
cv::estimateAffinePartial2D(src_points, dst_points);
|
||||
|
||||
cv::Mat aligned_face;
|
||||
|
||||
|
||||
|
||||
cv::warpAffine(image, aligned_face, transform_matrix, m_align_output_size,
|
||||
cv::INTER_LINEAR);
|
||||
|
||||
return aligned_face;
|
||||
}
|
||||
|
||||
|
||||
void FacePipeline::preprocess_recognition(const cv::Mat &img,
|
||||
std::vector<float> &blob_data) {
|
||||
cv::Mat resized, rgb_img;
|
||||
|
||||
const cv::Size target_size(248, 248);
|
||||
|
||||
|
||||
cv::resize(img, resized, target_size);
|
||||
|
||||
|
||||
cv::cvtColor(resized, rgb_img, cv::COLOR_BGR2RGB);
|
||||
|
||||
|
||||
const float mean[3] = {0.0f, 0.0f, 0.0f};
|
||||
const float std[3] = {1.0f, 1.0f, 1.0f};
|
||||
image_to_blob(rgb_img, blob_data, mean, std);
|
||||
}
|
||||
|
||||
void FacePipeline::normalize_sqrt_l2(std::vector<float> &v) {
|
||||
|
||||
|
||||
double norm = 0.0;
|
||||
for (float &val : v) {
|
||||
val = std::sqrt(std::max(0.0f, val));
|
||||
val = std::sqrt(std::max(0.0f, val));
|
||||
norm += val * val;
|
||||
}
|
||||
|
||||
|
||||
if (norm > 1e-6) {
|
||||
norm = std::sqrt(norm);
|
||||
for (float &val : v) {
|
||||
|
|
@ -785,19 +710,13 @@ void FacePipeline::normalize_sqrt_l2(std::vector<float> &v) {
|
|||
|
||||
bool FacePipeline::RunRecognition(const cv::Mat &aligned_face,
|
||||
std::vector<float> &feature) {
|
||||
|
||||
|
||||
|
||||
preprocess_recognition(aligned_face, m_blob_buffer);
|
||||
|
||||
|
||||
|
||||
const std::vector<int64_t> hardcoded_shape = {1, 3, 248, 248};
|
||||
const std::vector<int64_t> hardcoded_shape = {1, 3, 248, 248};
|
||||
|
||||
|
||||
auto input_tensor = create_tensor(m_blob_buffer, hardcoded_shape);
|
||||
|
||||
|
||||
auto output_tensors = m_session_recognizer->Run(
|
||||
Ort::RunOptions{nullptr}, m_rec_input_names.data(), &input_tensor, 1,
|
||||
m_rec_output_names.data(), 1);
|
||||
|
|
@ -809,15 +728,11 @@ bool FacePipeline::RunRecognition(const cv::Mat &aligned_face,
|
|||
feature.resize(feature_dim);
|
||||
memcpy(feature.data(), output_data, feature_dim * sizeof(float));
|
||||
|
||||
|
||||
normalize_sqrt_l2(feature);
|
||||
|
||||
return true;
|
||||
}
|
||||
|
||||
|
||||
|
||||
|
||||
bool FacePipeline::CheckResolution(const cv::Mat &face_region) {
|
||||
if (face_region.rows < m_quality_min_resolution.height ||
|
||||
face_region.cols < m_quality_min_resolution.width) {
|
||||
|
|
@ -826,7 +741,6 @@ bool FacePipeline::CheckResolution(const cv::Mat &face_region) {
|
|||
return true;
|
||||
}
|
||||
|
||||
|
||||
bool FacePipeline::CheckBrightness(const cv::Mat &face_region) {
|
||||
cv::Mat gray;
|
||||
if (face_region.channels() == 3)
|
||||
|
|
@ -836,17 +750,14 @@ bool FacePipeline::CheckBrightness(const cv::Mat &face_region) {
|
|||
|
||||
float bright_value = grid_max_bright(gray, 3, 3);
|
||||
|
||||
|
||||
return (bright_value >= m_quality_bright_v1 &&
|
||||
bright_value <= m_quality_bright_v2);
|
||||
}
|
||||
|
||||
|
||||
float FacePipeline::grid_max_bright(const cv::Mat &gray_img, int rows,
|
||||
int cols) {
|
||||
float max_bright = 0.0f;
|
||||
|
||||
|
||||
if (rows == 0 || cols == 0)
|
||||
return 0.0f;
|
||||
int row_height = gray_img.rows / rows;
|
||||
|
|
@ -867,14 +778,12 @@ float FacePipeline::grid_max_bright(const cv::Mat &gray_img, int rows,
|
|||
return max_bright;
|
||||
}
|
||||
|
||||
|
||||
bool FacePipeline::CheckClarity(const cv::Mat &face_region) {
|
||||
float clarity = clarity_estimate(face_region);
|
||||
|
||||
|
||||
return (clarity >= m_quality_clarity_low_thresh);
|
||||
}
|
||||
|
||||
|
||||
float FacePipeline::clarity_estimate(const cv::Mat &image) {
|
||||
cv::Mat gray;
|
||||
if (image.channels() == 3)
|
||||
|
|
@ -885,21 +794,19 @@ float FacePipeline::clarity_estimate(const cv::Mat &image) {
|
|||
float blur_val = grid_max_reblur(gray, 2, 2);
|
||||
float clarity = 1.0f - blur_val;
|
||||
|
||||
|
||||
return std::max(0.0f, std::min(1.0f, clarity));
|
||||
}
|
||||
|
||||
|
||||
float FacePipeline::grid_max_reblur(const cv::Mat &img, int rows, int cols) {
|
||||
|
||||
|
||||
int row_height = img.rows / rows;
|
||||
int col_width = img.cols / cols;
|
||||
if (row_height == 0 || col_width == 0)
|
||||
return 1.0f;
|
||||
return 1.0f;
|
||||
|
||||
float max_blur_val = -FLT_MAX;
|
||||
cv::Mat data_float;
|
||||
img.convertTo(data_float, CV_32F);
|
||||
img.convertTo(data_float, CV_32F);
|
||||
|
||||
for (int y = 0; y < rows; ++y) {
|
||||
for (int x = 0; x < cols; ++x) {
|
||||
|
|
@ -916,14 +823,13 @@ float FacePipeline::grid_max_reblur(const cv::Mat &img, int rows, int cols) {
|
|||
return std::max(max_blur_val, 0.0f);
|
||||
}
|
||||
|
||||
|
||||
float FacePipeline::reblur(const cv::Mat &data) {
|
||||
|
||||
if (data.rows <= 1 || data.cols <= 1)
|
||||
return 1.0f;
|
||||
|
||||
cv::Mat kernel_v = cv::Mat::ones(9, 1, CV_32F) / 9.0f;
|
||||
cv::Mat kernel_h = cv::Mat::ones(1, 9, CV_32F) / 9.0f;
|
||||
if (data.rows <= 1 || data.cols <= 1)
|
||||
return 1.0f;
|
||||
|
||||
cv::Mat kernel_v = cv::Mat::ones(9, 1, CV_32F) / 9.0f;
|
||||
cv::Mat kernel_h = cv::Mat::ones(1, 9, CV_32F) / 9.0f;
|
||||
cv::Mat BVer, BHor;
|
||||
|
||||
cv::filter2D(data, BVer, CV_32F, kernel_v, cv::Point(-1, -1), 0,
|
||||
|
|
@ -952,4 +858,42 @@ float FacePipeline::reblur(const cv::Mat &data) {
|
|||
(s_FHor > 1e-6) ? static_cast<float>((s_FHor - s_VHor) / s_FHor) : 0.0f;
|
||||
|
||||
return std::max(b_FVer, b_FHor);
|
||||
}
|
||||
|
||||
cv::Mat FacePipeline::PreprocessSmallFace(const cv::Mat &face_region) {
|
||||
int h = face_region.rows;
|
||||
int w = face_region.cols;
|
||||
|
||||
if (h >= m_quality_min_resolution.height &&
|
||||
w >= m_quality_min_resolution.width) {
|
||||
return face_region;
|
||||
}
|
||||
|
||||
LOGI("PreprocessSmallFace: Input (H:%d, W:%d) is small. Enhancing...", h, w);
|
||||
|
||||
float scale_w = (w < m_quality_min_resolution.width)
|
||||
? (float)m_quality_min_resolution.width / w
|
||||
: 1.0f;
|
||||
float scale_h = (h < m_quality_min_resolution.height)
|
||||
? (float)m_quality_min_resolution.height / h
|
||||
: 1.0f;
|
||||
float scale = std::max(scale_w, scale_h);
|
||||
|
||||
int new_width = static_cast<int>(w * scale);
|
||||
int new_height = static_cast<int>(h * scale);
|
||||
|
||||
cv::Mat resized;
|
||||
|
||||
cv::resize(face_region, resized, cv::Size(new_width, new_height), 0, 0,
|
||||
cv::INTER_CUBIC);
|
||||
|
||||
cv::Mat blurred;
|
||||
|
||||
cv::GaussianBlur(resized, blurred, cv::Size(0, 0), 2.0);
|
||||
|
||||
cv::Mat sharpened;
|
||||
|
||||
cv::addWeighted(resized, 1.5, blurred, -0.5, 0, sharpened);
|
||||
|
||||
return sharpened;
|
||||
}
|
||||
|
|
@ -197,4 +197,6 @@ private:
|
|||
const float m_quality_bright_v2 = 230.0f;
|
||||
|
||||
const float m_quality_clarity_low_thresh = 0.10f;
|
||||
|
||||
cv::Mat PreprocessSmallFace(const cv::Mat &face_region);
|
||||
};
|
||||
Loading…
Reference in New Issue