ImagePRO-Python 0.2.0__tar.gz → 0.4.0__tar.gz

{imagepro_python-0.2.0/src/ImagePRO_Python.egg-info → imagepro_python-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ImagePRO-Python
-Version: 0.2.0
+Version: 0.4.0
 Summary: clean, modular, and easy-to-use Python library for image processing tasks.
 Author-email: Parsa Safaie <parsasafaie.2568@proton.me>
 License: MIT
@@ -14,4 +14,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy<3.0,>=1.24
 Requires-Dist: opencv-python<5.0,>=4.8
+Requires-Dist: ultralytics<9.0,>=8.2.0
+Requires-Dist: mediapipe<1.0,>=0.10.0
 Dynamic: license-file

{imagepro_python-0.2.0 → imagepro_python-0.4.0}/pyproject.toml

@@ -7,7 +7,7 @@ where = ["src"]
 
 [project]
 name = "ImagePRO-Python"
-version = "0.2.0"
+version = "0.4.0"
 description = "clean, modular, and easy-to-use Python library for image processing tasks."
 readme = "README.md"
 requires-python = "==3.10.*"
@@ -24,6 +24,8 @@ classifiers = [
 dependencies = [
   "numpy>=1.24,<3.0",
   "opencv-python>=4.8,<5.0",
+  "ultralytics>=8.2.0,<9.0",
+  "mediapipe>=0.10.0,<1.0", 
 ]
 
 [tool.hatch.build.targets.wheel]

imagepro_python-0.4.0/src/ImagePRO/object_analysis/object_detection.py

@@ -0,0 +1,98 @@
+from ultralytics import YOLO
+import sys
+from pathlib import Path
+
+# Add parent directory to path for custom module imports
+parent_dir = Path(__file__).resolve().parent.parent
+sys.path.append(str(parent_dir))
+
+from utils.io_handler import IOHandler
+
+
+def detect_objects(
+    model=None,
+    accuracy_level=1,
+    src_image_path=None,
+    src_np_image=None,
+    output_image_path=None,
+    output_csv_path=None,
+    show_result=False
+):
+    """
+    Run object detection on a single image using Ultralytics YOLO.
+
+    Parameters
+    ----------
+    model : ultralytics.engine.model.YOLO | None, optional
+        A pre-loaded YOLO model instance. If provided, `accuracy_level` is ignored.
+        If None, a model is created based on `accuracy_level`.
+    accuracy_level : int, default=1
+        Model size preset in {1..5} mapping to:
+        1 -> "yolo11n.pt", 2 -> "yolo11s.pt", 3 -> "yolo11m.pt",
+        4 -> "yolo11l.pt", 5 -> "yolo11x.pt".
+    src_image_path : str | None, optional
+        Path to the input image on disk. Used by IOHandler if `src_np_image` is None.
+    src_np_image : np.ndarray | None, optional
+        Image array (BGR). If provided, it is preferred over `src_image_path`.
+    output_image_path : str | None, optional
+        If provided, saves the annotated image (result.plot()) to this path.
+    output_csv_path : str | None, optional
+        If provided, saves detections as rows of `[class_id, [x1n, y1n, x2n, y2n], confidence]`.
+        Note: coordinates are normalized in [0, 1].
+    show_result : bool, default=False
+        If True, shows the result window via `result.show()` (may require a GUI environment).
+
+    Returns
+    -------
+    tuple
+        (annotated_image: np.ndarray, lines: list[list])
+        where `annotated_image` is the result of `result.plot()` and
+        `lines` is a list of detection rows saved to CSV when requested.
+
+    Raises
+    ------
+    ValueError
+        If `accuracy_level` is not in {1..5}, or if image loading fails inside IOHandler.
+    """
+    # Create a model from preset if not provided by caller
+    if model is None:
+        if accuracy_level == 1:
+            model_name = "yolo11n.pt"
+        elif accuracy_level == 2:
+            model_name = "yolo11s.pt"
+        elif accuracy_level == 3:
+            model_name = "yolo11m.pt"
+        elif accuracy_level == 4:
+            model_name = "yolo11l.pt"
+        elif accuracy_level == 5:
+            model_name = "yolo11x.pt"
+        else:
+            raise ValueError('Unknown accuracy level.')
+
+        model = YOLO(model=model_name)
+
+    # Load image from path or ndarray using the shared IO helper
+    frame = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
+
+    # Run inference (first result only)
+    result = model(frame)[0]
+    boxes = result.boxes
+
+    # Collect rows as: [class_id, [x1n, y1n, x2n, y2n], confidence]
+    lines = []
+    for box in boxes:
+        box_class = int(box.cls)
+        conf = float(box.conf)
+        x1, y1, x2, y2 = [float(c) for c in box.xyxyn.squeeze().tolist()]
+        lines.append([box_class, [x1, y1, x2, y2], conf])
+
+    # Optional visualization and saving
+    if show_result:
+        result.show()
+    if output_image_path:
+        IOHandler.save_image(np_image=result.plot(), result_path=output_image_path)
+    if output_csv_path:
+        IOHandler.save_csv(data=lines, result_path=output_csv_path)
+
+    # Return the plotted image and the CSV-friendly rows
+    return result.plot(), lines

imagepro_python-0.4.0/src/ImagePRO/pre_processing/dataset_generator.py

@@ -0,0 +1,178 @@
+import sys
+import time
+import random
+from pathlib import Path
+
+import cv2
+import mediapipe as mp
+
+# Add parent directory to sys.path for local imports
+parent_dir = Path(__file__).resolve().parent.parent
+sys.path.append(str(parent_dir))
+
+from human_analysis.face_analysis.face_detection import detect_faces
+from blur import apply_median_blur
+from sharpen import apply_laplacian_sharpening
+from rotate import rotate_image_custom
+from grayscale import convert_to_grayscale
+from resize import resize_image
+
+
+def capture_bulk_pictures(
+    folder_path: str | Path,
+    face_id: str | int,
+    num_images: int = 200,
+    start_index: int = 0,
+    min_confidence: float = 0.7,
+    camera_index: int = 0,
+    apply_blur: bool = False,
+    apply_grayscale: bool = False,
+    apply_sharpen: bool = False,
+    apply_rotate: bool = False,
+    apply_resize: tuple = False,
+    delay: float = 0.1,
+) -> None:
+    """
+    Capture frames from webcam and save cropped face images, with optional preprocessing.
+
+    Processing order (if enabled):
+    median blur → laplacian sharpen → grayscale → resize → random rotate
+
+    Parameters
+    ----------
+    folder_path : str | Path
+        Base directory where the face-id folder will be created.
+    face_id : str | int
+        Subfolder name (e.g., user id). A new folder "<folder_path>/<face_id>" will be created.
+    num_images : int, default=200
+        Number of frames to capture/save.
+    start_index : int, default=0
+        Starting index for saved filenames (zero-padded).
+    min_confidence : float, default=0.7
+        Detection confidence for MediaPipe FaceMesh.
+    camera_index : int, default=0
+        OpenCV camera index.
+    apply_blur : bool, default=False
+        Apply median blur (filter_size=3) before other steps.
+    apply_grayscale : bool, default=False
+        Convert frame to single-channel grayscale.
+    apply_sharpen : bool, default=False
+        Apply Laplacian-based sharpening (coefficient=1.0).
+    apply_rotate : bool, default=False
+        Apply a random rotation in [-45°, +45°] with random scale {1.0, 1.1, 1.2, 1.3}.
+    apply_resize : tuple[int, int] | None, default=None
+        If provided, resize to (width, height) before rotation.
+    delay : float, default=0.1
+        Delay between each capture in seconds.
+
+    Raises
+    ------
+    ValueError
+        If arguments are invalid.
+    FileExistsError
+        If the destination folder already exists.
+    RuntimeError
+        If the webcam cannot be opened.
+    """
+    if not isinstance(num_images, int) or num_images <= 0:
+        raise ValueError("'num_images' must be a positive integer.")
+    if not isinstance(start_index, int) or start_index < 0:
+        raise ValueError("'start_index' must be a non-negative integer.")
+    if not isinstance(min_confidence, (int, float)) or not (0 <= min_confidence <= 1):
+        raise ValueError("'min_confidence' must be between 0 and 1.")
+    if not isinstance(delay, (int, float)) or delay < 0:
+        raise ValueError("'delay' must be a non-negative number.")
+
+    base_dir = Path(folder_path)
+    face_folder = base_dir / str(face_id)
+
+    # Create destination folder (fail if exists to avoid accidental overwrite)
+    try:
+        face_folder.mkdir(parents=True, exist_ok=False)
+    except FileExistsError as e:
+        raise FileExistsError(f"Destination already exists: {face_folder}") from e
+
+    # Open webcam
+    cap = cv2.VideoCapture(camera_index)
+    if not cap.isOpened():
+        raise RuntimeError(f"Failed to open webcam (index={camera_index}).")
+
+    # Initialize FaceMesh for live stream (tracking mode)
+    face_mesh = mp.solutions.face_mesh.FaceMesh(
+        max_num_faces=1,
+        min_detection_confidence=min_confidence,
+        refine_landmarks=True,
+        static_image_mode=False,
+    )
+
+    saved = 0
+    try:
+        while saved < num_images:
+            ok, frame = cap.read()
+            if not ok:
+                print("Skipping empty frame.")
+                continue
+
+            # Optional preprocessing steps
+            proc = frame
+
+            if apply_blur:
+                # Small kernel to keep facial details while reducing salt-and-pepper noise
+                proc = apply_median_blur(src_np_image=proc, filter_size=3)
+
+            if apply_sharpen:
+                # Gentle sharpening; adjust coefficient if needed
+                proc = apply_laplacian_sharpening(src_np_image=proc, coefficient=1.0)
+
+            if apply_grayscale:
+                proc = convert_to_grayscale(src_np_image=proc)
+
+            if apply_resize is not None:
+                proc = resize_image(new_size=apply_resize, src_np_image=proc)
+
+            if apply_rotate:
+                angle = float(random.randint(-45, 45))
+                scale = random.choice([1.0, 1.1, 1.2, 1.3])
+                proc = rotate_image_custom(src_np_image=proc, angle=angle, scale=scale)
+
+            # Zero-padded filenames for better ordering
+            filename = f"{start_index + saved:04d}.jpg"
+            out_path = face_folder / filename
+
+            try:
+                # Save cropped face image via standardized detect_faces
+                detect_faces(
+                    max_faces=1,
+                    min_confidence=min_confidence,
+                    src_np_image=proc,
+                    output_image_path=str(out_path),
+                    face_mesh_obj=face_mesh,
+                )
+                saved += 1
+
+                if delay > 0:
+                    time.sleep(delay)
+
+            except ValueError:
+                # No face detected; skip this frame
+                continue
+    finally:
+        cap.release()
+        cv2.destroyAllWindows()
+
+
+if __name__ == "__main__":
+    capture_bulk_pictures(
+        folder_path=r"tmp",
+        face_id="0",
+        num_images=200,
+        start_index=0,
+        min_confidence=0.7,
+        camera_index=0,
+        apply_blur=True,
+        apply_sharpen=True,
+        apply_grayscale=True,
+        apply_resize=(224, 224),
+        apply_rotate=True,
+        delay=0.1
+    )

{imagepro_python-0.2.0 → imagepro_python-0.4.0/src/ImagePRO_Python.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ImagePRO-Python
-Version: 0.2.0
+Version: 0.4.0
 Summary: clean, modular, and easy-to-use Python library for image processing tasks.
 Author-email: Parsa Safaie <parsasafaie.2568@proton.me>
 License: MIT
@@ -14,4 +14,6 @@ Description-Content-Type: text/markdown
 License-File: LICENSE
 Requires-Dist: numpy<3.0,>=1.24
 Requires-Dist: opencv-python<5.0,>=4.8
+Requires-Dist: ultralytics<9.0,>=8.2.0
+Requires-Dist: mediapipe<1.0,>=0.10.0
 Dynamic: license-file

{imagepro_python-0.2.0 → imagepro_python-0.4.0}/src/ImagePRO_Python.egg-info/SOURCES.txt

@@ -10,10 +10,12 @@ src/ImagePRO/human_analysis/face_analysis/eye_status_analysis.py
 src/ImagePRO/human_analysis/face_analysis/face_detection.py
 src/ImagePRO/human_analysis/face_analysis/face_mesh_analysis.py
 src/ImagePRO/human_analysis/face_analysis/head_pose_estimation.py
+src/ImagePRO/object_analysis/object_detection.py
 src/ImagePRO/pre_processing/__init__.py
 src/ImagePRO/pre_processing/blur.py
 src/ImagePRO/pre_processing/contrast.py
 src/ImagePRO/pre_processing/crop.py
+src/ImagePRO/pre_processing/dataset_generator.py
 src/ImagePRO/pre_processing/grayscale.py
 src/ImagePRO/pre_processing/resize.py
 src/ImagePRO/pre_processing/rotate.py

imagepro_python-0.4.0/src/ImagePRO_Python.egg-info/requires.txt

@@ -0,0 +1,4 @@
+numpy<3.0,>=1.24
+opencv-python<5.0,>=4.8
+ultralytics<9.0,>=8.2.0
+mediapipe<1.0,>=0.10.0

imagepro_python-0.2.0/src/ImagePRO_Python.egg-info/requires.txt

@@ -1,2 +0,0 @@
-numpy<3.0,>=1.24
-opencv-python<5.0,>=4.8