ImagePRO-Python 0.5.1__py3-none-any.whl → 0.5.2__py3-none-any.whl

ImagePRO/__init__.py

@@ -0,0 +1,33 @@
+"""
+ImagePRO - Professional & Modular Image Processing Library in Python
+
+A clean, modular, and easy-to-use Python library for image processing tasks,
+built with OpenCV, MediaPipe, YOLO and designed to be extensible for developers.
+
+Whether you're working on computer vision pipelines, preprocessing images for AI models,
+or simply automating batch image edits — ImagePRO gives you powerful tools with minimal effort.
+
+Features:
+- Image I/O management and batch processing
+- Pre-processing: resize, crop, rotate, blur, sharpen, contrast enhancement
+- Human analysis: face mesh, pose estimation, hand tracking
+- Object detection with YOLO models
+- Real-time processing capabilities
+"""
+
+__version__ = "0.5.2"
+__author__ = "Parsa Safaie"
+__email__ = "parsasafaie.2568@proton.me"
+
+# Core modules
+from . import utils
+from . import pre_processing
+from . import human_analysis
+from . import object_analysis
+
+__all__ = [
+    "utils",
+    "pre_processing", 
+    "human_analysis",
+    "object_analysis"
+]

ImagePRO/human_analysis/__init__.py

@@ -0,0 +1,7 @@
+# Human Analysis Module
+# Provides face and body analysis capabilities using MediaPipe
+
+from . import face_analysis
+from . import body_analysis
+
+__all__ = ["face_analysis", "body_analysis"]

ImagePRO/human_analysis/body_analysis/__init__.py

@@ -0,0 +1,7 @@
+# Body Analysis Module
+# Provides body pose estimation and hand tracking capabilities
+
+from . import body_pose_estimation
+from . import hand_tracking
+
+__all__ = ["body_pose_estimation", "hand_tracking"]

ImagePRO/human_analysis/body_analysis/body_pose_estimation.py

@@ -10,10 +10,15 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
 mp_pose = mp.solutions.pose
+TOTAL_LANDMARKS = 33
+DEFAULT_CONFIDENCE = 0.7
+LANDMARK_RADIUS = 3
+LANDMARK_COLOR = (0, 0, 255)  # Red color for landmarks
 
 def detect_body_pose(
-    model_accuracy: float = 0.7,
+    model_accuracy: float = DEFAULT_CONFIDENCE, 
     landmarks_idx: list | None = None,
     src_image_path: str | None = None,
     src_np_image=None,
@@ -56,7 +61,7 @@ def detect_body_pose(
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
 
     if landmarks_idx is None:
-        landmarks_idx = list(range(33))
+        landmarks_idx = list(range(TOTAL_LANDMARKS))
 
     if pose_obj is None:
         pose_obj = mp_pose.Pose(
@@ -71,7 +76,7 @@ def detect_body_pose(
     all_landmarks = []
 
     if result.pose_landmarks:
-        if len(landmarks_idx) == 33:
+        if len(landmarks_idx) == TOTAL_LANDMARKS:
             mp.solutions.drawing_utils.draw_landmarks(
                 annotated_image,
                 result.pose_landmarks,
@@ -83,7 +88,7 @@ def detect_body_pose(
             for idx in landmarks_idx:
                 lm = result.pose_landmarks.landmark[idx]
                 x, y = int(w * lm.x), int(h * lm.y)
-                cv2.circle(annotated_image, (x, y), 3, (0, 0, 255), -1)
+                cv2.circle(annotated_image, (x, y), LANDMARK_RADIUS, LANDMARK_COLOR, -1)
 
         for idx in landmarks_idx:
             lm = result.pose_landmarks.landmark[idx]
@@ -104,7 +109,7 @@ def detect_body_pose_live():
         raise RuntimeError("Failed to open webcam.")
 
     pose_obj = mp_pose.Pose(
-        min_detection_confidence=0.7,
+        min_detection_confidence=DEFAULT_CONFIDENCE,
         static_image_mode=False
     )
 

ImagePRO/human_analysis/body_analysis/hand_tracking.py

@@ -10,12 +10,18 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
 mp_hands = mp.solutions.hands
+DEFAULT_MAX_HANDS = 2
+DEFAULT_MIN_CONFIDENCE = 0.7
+TOTAL_HAND_LANDMARKS = 21
+LANDMARK_RADIUS = 3
+LANDMARK_COLOR = (0, 0, 255)  # Red color for landmarks
 
 
 def detect_hands(
-    max_hands: int = 2,
-    min_confidence: float = 0.7,
+    max_hands: int = DEFAULT_MAX_HANDS,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     landmarks_idx: list | None = None,
     src_image_path: str | None = None,
     src_np_image=None,
@@ -71,7 +77,7 @@ def detect_hands(
         )
 
     if landmarks_idx is None:
-        landmarks_idx = list(range(21))
+        landmarks_idx = list(range(TOTAL_HAND_LANDMARKS))
 
     rgb_image = cv2.cvtColor(np_image, cv2.COLOR_BGR2RGB)
     results = hands_obj.process(rgb_image)
@@ -81,7 +87,7 @@ def detect_hands(
 
     if results.multi_hand_landmarks:
         for hand_id, hand_landmarks in enumerate(results.multi_hand_landmarks):
-            if len(landmarks_idx) == 21:
+            if len(landmarks_idx) == TOTAL_HAND_LANDMARKS:
                 mp.solutions.drawing_utils.draw_landmarks(
                     image=annotated_image,
                     landmark_list=hand_landmarks,
@@ -94,7 +100,7 @@ def detect_hands(
                 for idx in landmarks_idx:
                     lm = hand_landmarks.landmark[idx]
                     x, y = int(w * lm.x), int(h * lm.y)
-                    cv2.circle(annotated_image, (x, y), 3, (0, 0, 255), -1)
+                    cv2.circle(annotated_image, (x, y), LANDMARK_RADIUS, LANDMARK_COLOR, -1)
 
             for idx in landmarks_idx:
                 lm = hand_landmarks.landmark[idx]
@@ -108,7 +114,7 @@ def detect_hands(
     return annotated_image, all_landmarks
 
 
-def detect_hands_live(max_hands: int = 2, min_confidence: float = 0.7):
+def detect_hands_live(max_hands: int = DEFAULT_MAX_HANDS, min_confidence: float = DEFAULT_MIN_CONFIDENCE):
     """Real-time hand detection via webcam. Press ESC to exit."""
     if not isinstance(max_hands, int) or max_hands <= 0:
         raise ValueError("'max_hands' must be a positive integer.")
@@ -149,4 +155,4 @@ def detect_hands_live(max_hands: int = 2, min_confidence: float = 0.7):
 
 
 if __name__ == "__main__":
-    detect_hands_live(max_hands=2)
+    detect_hands_live(max_hands=DEFAULT_MAX_HANDS)

ImagePRO/human_analysis/face_analysis/__init__.py

@@ -0,0 +1,16 @@
+# Face Analysis Module
+# Provides facial landmark detection, pose estimation, and eye status analysis
+
+from . import eye_status_analysis
+from . import face_comparison
+from . import face_detection
+from . import face_mesh_analysis
+from . import head_pose_estimation
+
+__all__ = [
+    "eye_status_analysis",
+    "face_comparison",
+    "face_detection", 
+    "face_mesh_analysis",
+    "head_pose_estimation"
+]

ImagePRO/human_analysis/face_analysis/eye_status_analysis.py

@@ -11,15 +11,19 @@ sys.path.append(str(parent_dir))
 from utils.io_handler import IOHandler
 from human_analysis.face_analysis.face_mesh_analysis import analyze_face_mesh
 
+# Constants
 mp_face_mesh = mp.solutions.face_mesh
+DEFAULT_MIN_CONFIDENCE = 0.7
+DEFAULT_THRESHOLD = 0.2
+RIGHT_EYE_INDICES = [386, 374, 263, 362]  # MediaPipe 468-point model
 
 
 def analyze_eye_status(
-    min_confidence: float = 0.7,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     src_image_path: str | None = None,
     src_np_image=None,
     face_mesh_obj=None,
-    threshold: float = 0.2,
+    threshold: float = DEFAULT_THRESHOLD,
 ) -> bool:
     """
     Analyze right-eye open/closed status via Eye Aspect Ratio (EAR).
@@ -72,7 +76,7 @@ def analyze_eye_status(
         )
 
     # Landmark indices for right eye (MediaPipe 468-point model)
-    indices = [386, 374, 263, 362]
+    indices = RIGHT_EYE_INDICES
 
     _, landmarks = analyze_face_mesh(
         max_faces=1,

ImagePRO/human_analysis/face_analysis/face_comparison.py

@@ -2,6 +2,12 @@ from insightface.app import FaceAnalysis
 import cv2
 import numpy as np
 
+# Constants
+DEFAULT_SIMILARITY_THRESHOLD = 0.5
+DEFAULT_MODEL_NAME = "buffalo_l"
+DEFAULT_PROVIDER = "CPUExecutionProvider"
+
+
 def compare_faces(src_image_path_1, src_image_path_2, app=None):
     """
     Compare two face images using FaceAnalysis embeddings.
@@ -24,8 +30,8 @@ def compare_faces(src_image_path_1, src_image_path_2, app=None):
     # Prepare FaceAnalysis model if not provided
     if app is None:
         app = FaceAnalysis(
-            name="buffalo_l",
-            providers=["CPUExecutionProvider"],
+            name=DEFAULT_MODEL_NAME,
+            providers=[DEFAULT_PROVIDER],
         )
         app.prepare(ctx_id=0)  # Run on CPU
 
@@ -57,4 +63,4 @@ def compare_faces(src_image_path_1, src_image_path_2, app=None):
     sim = np.dot(emb1, emb2) / (np.linalg.norm(emb1) * np.linalg.norm(emb2))
 
     # Return match result based on threshold
-    return True if sim > 0.5 else False
+    return True if sim > DEFAULT_SIMILARITY_THRESHOLD else False

ImagePRO/human_analysis/face_analysis/face_detection.py

@@ -11,10 +11,19 @@ sys.path.append(str(parent_dir))
 from utils.io_handler import IOHandler
 from human_analysis.face_analysis.face_mesh_analysis import analyze_face_mesh
 
+# Constants
+DEFAULT_MAX_FACES = 1
+DEFAULT_MIN_CONFIDENCE = 0.7
+FACE_OUTLINE_INDICES = [
+    10, 338, 297, 332, 284, 251, 389, 356, 454, 323,
+    361, 288, 397, 365, 379, 378, 400, 377, 152, 148,
+    176, 149, 150, 136, 164, 163, 153, 157
+]
+
 
 def detect_faces(
-    max_faces: int = 1,
-    min_confidence: float = 0.7,
+    max_faces: int = DEFAULT_MAX_FACES,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None,
@@ -68,11 +77,7 @@ def detect_faces(
     height, width = np_image.shape[:2]
 
     # Selected face outline landmark indices (MediaPipe 468-point model)
-    face_outline_indices = [
-        10, 338, 297, 332, 284, 251, 389, 356, 454, 323,
-        361, 288, 397, 365, 379, 378, 400, 377, 152, 148,
-        176, 149, 150, 136, 164, 163, 153, 157
-    ]
+    face_outline_indices = FACE_OUTLINE_INDICES
 
     # --- Run face mesh analysis ----------------------------------------------
     _, raw_landmarks = analyze_face_mesh(

ImagePRO/human_analysis/face_analysis/face_mesh_analysis.py

@@ -10,14 +10,18 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
 mp_face_mesh = mp.solutions.face_mesh
 mp_drawing_utils = mp.solutions.drawing_utils
 mp_drawing_styles = mp.solutions.drawing_styles
+DEFAULT_MAX_FACES = 1
+DEFAULT_MIN_CONFIDENCE = 0.7
+TOTAL_FACE_LANDMARKS = 468
 
 
 def analyze_face_mesh(
-    max_faces: int = 1,
-    min_confidence: float = 0.7,
+    max_faces: int = DEFAULT_MAX_FACES,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     landmarks_idx: list | None = None,
     src_image_path: str | None = None,
     src_np_image=None,
@@ -118,7 +122,7 @@ def analyze_face_mesh(
 
     for face_id, face_landmarks in enumerate(results.multi_face_landmarks):
         # Draw either the full tessellation or specific landmark dots
-        if len(landmarks_idx) == 468:
+        if len(landmarks_idx) == TOTAL_FACE_LANDMARKS:
             mp_drawing_utils.draw_landmarks(
                 image=annotated,
                 landmark_list=face_landmarks,
@@ -152,7 +156,7 @@ def analyze_face_mesh(
     return annotated, all_landmarks
 
 
-def analyze_face_mesh_live(max_faces: int = 1, min_confidence: float = 0.7):
+def analyze_face_mesh_live(max_faces: int = DEFAULT_MAX_FACES, min_confidence: float = DEFAULT_MIN_CONFIDENCE):
     """
     Launch webcam preview with real-time FaceMesh overlay.
 

ImagePRO/human_analysis/face_analysis/head_pose_estimation.py

@@ -11,12 +11,16 @@ sys.path.append(str(parent_dir))
 from utils.io_handler import IOHandler
 from human_analysis.face_analysis.face_mesh_analysis import analyze_face_mesh
 
+# Constants
 mp_face_mesh = mp.solutions.face_mesh
+DEFAULT_MAX_FACES = 1
+DEFAULT_MIN_CONFIDENCE = 0.7
+HEAD_POSE_INDICES = [1, 152, 33, 263, 168]  # nose_tip, chin, left_eye, right_eye, nasion
 
 
 def estimate_head_pose(
-    max_faces: int = 1,
-    min_confidence: float = 0.7,
+    max_faces: int = DEFAULT_MAX_FACES,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_csv_path: str | None = None,
@@ -64,7 +68,7 @@ def estimate_head_pose(
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
 
     # Important landmark indices (MediaPipe 468 model)
-    indices = [1, 152, 33, 263, 168]  # nose_tip, chin, left_eye, right_eye, nasion
+    indices = HEAD_POSE_INDICES
 
     _, landmarks = analyze_face_mesh(
         max_faces=max_faces,

ImagePRO/object_analysis/__init__.py

@@ -0,0 +1,6 @@
+# Object Analysis Module
+# Provides object detection capabilities using YOLO models
+
+from . import object_detection
+
+__all__ = ["object_detection"]

ImagePRO/object_analysis/object_detection.py

@@ -8,15 +8,26 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
+DEFAULT_ACCURACY_LEVEL = 1
+DEFAULT_CONFIDENCE = 0.5
+MODEL_MAPPING = {
+    1: "yolo11n.pt",
+    2: "yolo11s.pt", 
+    3: "yolo11m.pt",
+    4: "yolo11l.pt",
+    5: "yolo11x.pt"
+}
+
 
 def detect_objects(
     model=None,
-    accuracy_level=1,
-    src_image_path=None,
+    accuracy_level: int = DEFAULT_ACCURACY_LEVEL,
+    src_image_path: str | None = None,
     src_np_image=None,
-    output_image_path=None,
-    output_csv_path=None,
-    show_result=False
+    output_image_path: str | None = None,
+    output_csv_path: str | None = None,
+    show_result: bool = False
 ):
     """
     Run object detection on a single image using Ultralytics YOLO.
@@ -56,19 +67,10 @@ def detect_objects(
     """
     # 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.')
-
+        if accuracy_level not in MODEL_MAPPING:
+            raise ValueError(f"'accuracy_level' must be in {list(MODEL_MAPPING.keys())}, got {accuracy_level}")
+        
+        model_name = MODEL_MAPPING[accuracy_level]
         model = YOLO(model=model_name)
 
     # Load image from path or ndarray using the shared IO helper
@@ -90,9 +92,9 @@ def detect_objects(
     if show_result:
         result.show()
     if output_image_path:
-        IOHandler.save_image(np_image=result.plot(), result_path=output_image_path)
+        print(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)
+        print(IOHandler.save_csv(data=lines, result_path=output_csv_path))
 
     # Return the plotted image and the CSV-friendly rows
     return result.plot(), lines

ImagePRO/pre_processing/__init__.py

@@ -0,0 +1,22 @@
+# Pre-processing Module
+# Provides image manipulation, filtering, and enhancement capabilities
+
+from . import blur
+from . import contrast
+from . import crop
+from . import dataset_generator
+from . import grayscale
+from . import resize
+from . import rotate
+from . import sharpen
+
+__all__ = [
+    "blur",
+    "contrast", 
+    "crop",
+    "dataset_generator",
+    "grayscale",
+    "resize",
+    "rotate",
+    "sharpen"
+]

ImagePRO/pre_processing/blur.py

@@ -9,9 +9,15 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
+DEFAULT_KERNEL_SIZE = (5, 5)
+DEFAULT_FILTER_SIZE = 5
+DEFAULT_SIGMA_COLOR = 75
+DEFAULT_SIGMA_SPACE = 75
+
 
 def apply_average_blur(
-    kernel_size: tuple[int, int] = (5, 5),
+    kernel_size: tuple[int, int] = DEFAULT_KERNEL_SIZE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None
@@ -55,13 +61,15 @@ def apply_average_blur(
 
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
     blurred = cv2.blur(np_image, kernel_size)
+    
     if output_image_path:
         print(IOHandler.save_image(blurred, output_image_path))
+    
     return blurred
 
 
 def apply_gaussian_blur(
-    kernel_size: tuple[int, int] = (5, 5),
+    kernel_size: tuple[int, int] = DEFAULT_KERNEL_SIZE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None
@@ -98,14 +106,16 @@ def apply_gaussian_blur(
         raise ValueError("'kernel_size' must be a tuple of two odd positive integers.")
 
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
-    blurred = cv2.GaussianBlur(np_image, kernel_size, sigmaX=0)
+    blurred = cv2.GaussianBlur(np_image, kernel_size, 0)
+    
     if output_image_path:
         print(IOHandler.save_image(blurred, output_image_path))
+    
     return blurred
 
 
 def apply_median_blur(
-    filter_size: int = 5,
+    filter_size: int = DEFAULT_FILTER_SIZE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None
@@ -143,30 +153,32 @@ def apply_median_blur(
 
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
     blurred = cv2.medianBlur(np_image, filter_size)
+    
     if output_image_path:
         print(IOHandler.save_image(blurred, output_image_path))
+    
     return blurred
 
 
 def apply_bilateral_blur(
     filter_size: int = 9,
-    sigma_color: float = 75,
-    sigma_space: float = 75,
+    sigma_color: float = DEFAULT_SIGMA_COLOR,
+    sigma_space: float = DEFAULT_SIGMA_SPACE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None
 ) -> np.ndarray:
     """
-    Apply bilateral filter to smooth while preserving edges.
+    Apply bilateral blur to an image.
 
     Parameters
     ----------
     filter_size : int, default=9
-        Diameter of pixel neighborhood.
+        Filter size, must be a positive integer.
     sigma_color : float, default=75
-        Color-space standard deviation.
+        Color sigma, higher values mean more colors will be mixed.
     sigma_space : float, default=75
-        Coordinate-space standard deviation.
+        Space sigma, higher values mean farther pixels will influence each other.
     src_image_path : str | None, optional
         Path to input image.
     src_np_image : np.ndarray | None, optional
@@ -182,9 +194,9 @@ def apply_bilateral_blur(
     Raises
     ------
     ValueError
-        If parameters are invalid.
+        If filter size or sigma parameters are invalid.
     """
-    if not isinstance(filter_size, int) or filter_size < 1:
+    if not isinstance(filter_size, int) or filter_size <= 0:
         raise ValueError("'filter_size' must be a positive integer.")
     if not isinstance(sigma_color, (int, float)) or sigma_color <= 0:
         raise ValueError("'sigma_color' must be a positive number.")
@@ -193,6 +205,8 @@ def apply_bilateral_blur(
 
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
     blurred = cv2.bilateralFilter(np_image, filter_size, sigma_color, sigma_space)
+    
     if output_image_path:
         print(IOHandler.save_image(blurred, output_image_path))
+    
     return blurred

ImagePRO/pre_processing/contrast.py

@@ -10,10 +10,16 @@ sys.path.append(str(parent_dir))
 from pre_processing.grayscale import convert_to_grayscale
 from utils.io_handler import IOHandler
 
+# Constants
+DEFAULT_CLIP_LIMIT = 2.0
+DEFAULT_TILE_GRID_SIZE = (8, 8)
+DEFAULT_ALPHA = 1.5
+DEFAULT_BETA = 10
+
 
 def apply_clahe_contrast(
-    clip_limit: float = 2.0,
-    tile_grid_size: tuple[int, int] = (8, 8),
+    clip_limit: float = DEFAULT_CLIP_LIMIT,
+    tile_grid_size: tuple[int, int] = DEFAULT_TILE_GRID_SIZE,
     src_image_path: str | None = None,
     src_np_image=None,
     output_image_path: str | None = None

ImagePRO/pre_processing/crop.py

@@ -8,6 +8,10 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
+DEFAULT_START_POINT = (0, 0)
+DEFAULT_END_POINT = (100, 100)
+
 
 def crop_image(
     start_point: tuple[int, int],

ImagePRO/pre_processing/dataset_generator.py

@@ -17,20 +17,28 @@ from rotate import rotate_image_custom
 from grayscale import convert_to_grayscale
 from resize import resize_image
 
+# Constants
+DEFAULT_NUM_IMAGES = 200
+DEFAULT_START_INDEX = 0
+DEFAULT_MIN_CONFIDENCE = 0.7
+DEFAULT_CAMERA_INDEX = 0
+DEFAULT_DELAY = 0.1
+DEFAULT_FACE_ID = "unknown"
+
 
 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,
+    face_id: str | int = DEFAULT_FACE_ID,
+    num_images: int = DEFAULT_NUM_IMAGES,
+    start_index: int = DEFAULT_START_INDEX,
+    min_confidence: float = DEFAULT_MIN_CONFIDENCE,
+    camera_index: int = DEFAULT_CAMERA_INDEX,
     apply_blur: bool = False,
     apply_grayscale: bool = False,
     apply_sharpen: bool = False,
     apply_rotate: bool = False,
     apply_resize: tuple = False,
-    delay: float = 0.1,
+    delay: float = DEFAULT_DELAY,
 ) -> None:
     """
     Capture frames from webcam and save cropped face images, with optional preprocessing.

ImagePRO/pre_processing/grayscale.py

@@ -1,9 +1,9 @@
 import sys
 from pathlib import Path
-import numpy as np
 import cv2
+import numpy as np
 
-# Add parent directory to sys.path for importing custom modules
+# Add parent directory to sys.path for custom module imports
 parent_dir = Path(__file__).resolve().parent.parent
 sys.path.append(str(parent_dir))
 
@@ -12,20 +12,20 @@ from utils.io_handler import IOHandler
 
 def convert_to_grayscale(
     src_image_path: str | None = None,
-    src_np_image: np.ndarray | None = None,
+    src_np_image=None,
     output_image_path: str | None = None
 ) -> np.ndarray:
     """
-    Convert a BGR image to single-channel grayscale.
+    Convert an image to grayscale.
 
     Parameters
     ----------
     src_image_path : str | None, optional
-        Path to the input image file.
+        Path to input image.
     src_np_image : np.ndarray | None, optional
-        Preloaded BGR image. Used if `src_image_path` is None.
+        Preloaded BGR image array.
     output_image_path : str | None, optional
-        Path to save the grayscale image.
+        If provided, save the grayscale image.
 
     Returns
     -------
@@ -37,13 +37,14 @@ def convert_to_grayscale(
     TypeError
         If input types are invalid.
     FileNotFoundError
-        If the provided `src_image_path` does not exist.
+        If image path does not exist.
     IOError
         If saving the image fails.
     """
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
     grayscale = cv2.cvtColor(np_image, cv2.COLOR_BGR2GRAY)
-
+    
     if output_image_path:
         print(IOHandler.save_image(grayscale, output_image_path))
+    
     return grayscale

ImagePRO/pre_processing/resize.py

@@ -1,9 +1,9 @@
 import sys
 from pathlib import Path
-import numpy as np
 import cv2
+import numpy as np
 
-# Add parent directory to sys.path for importing custom modules
+# Add parent directory to sys.path for custom module imports
 parent_dir = Path(__file__).resolve().parent.parent
 sys.path.append(str(parent_dir))
 
@@ -13,22 +13,22 @@ from utils.io_handler import IOHandler
 def resize_image(
     new_size: tuple[int, int],
     src_image_path: str | None = None,
-    src_np_image: np.ndarray | None = None,
+    src_np_image=None,
     output_image_path: str | None = None
 ) -> np.ndarray:
     """
-    Resize an image to the specified dimensions.
+    Resize an image to new dimensions.
 
     Parameters
     ----------
     new_size : tuple[int, int]
-        (width, height) in pixels, both must be positive integers.
+        New image size as (width, height).
     src_image_path : str | None, optional
-        Path to the input image. Overrides `src_np_image` if provided.
+        Path to input image.
     src_np_image : np.ndarray | None, optional
-        Preloaded image array, used if `src_image_path` is None.
+        Preloaded BGR image array.
     output_image_path : str | None, optional
-        Path to save the resized image.
+        If provided, save the resized image.
 
     Returns
     -------
@@ -37,28 +37,26 @@ def resize_image(
 
     Raises
     ------
-    TypeError
-        If `new_size` is not a tuple of two integers.
     ValueError
-        If width or height are not positive integers.
+        If new_size is invalid.
+    TypeError
+        If input types are invalid.
     FileNotFoundError
-        If `src_image_path` does not exist.
+        If image path does not exist.
     IOError
         If saving the image fails.
     """
     if (
         not isinstance(new_size, tuple)
         or len(new_size) != 2
-        or not all(isinstance(x, int) for x in new_size)
+        or not all(isinstance(dim, int) and dim > 0 for dim in new_size)
     ):
-        raise TypeError("'new_size' must be a tuple of two integers: (width, height).")
-
-    if new_size[0] <= 0 or new_size[1] <= 0:
-        raise ValueError("Both width and height must be positive integers.")
+        raise ValueError("'new_size' must be a tuple of two positive integers.")
 
     np_image = IOHandler.load_image(image_path=src_image_path, np_image=src_np_image)
-    resized = cv2.resize(np_image, dsize=new_size)
-
+    resized = cv2.resize(np_image, new_size, interpolation=cv2.INTER_LINEAR)
+    
     if output_image_path:
         print(IOHandler.save_image(resized, output_image_path))
+    
     return resized

ImagePRO/pre_processing/rotate.py

@@ -9,6 +9,10 @@ sys.path.append(str(parent_dir))
 
 from utils.io_handler import IOHandler
 
+# Constants
+DEFAULT_SCALE = 1.0
+DEFAULT_ANGLE = 45.0
+
 
 def rotate_image_90(
     src_image_path: str | None = None,
@@ -67,7 +71,7 @@ def rotate_image_270(
 
 def rotate_image_custom(
     angle: float,
-    scale: float = 1.0,
+    scale: float = DEFAULT_SCALE,
     src_image_path: str | None = None,
     src_np_image: np.ndarray | None = None,
     output_image_path: str | None = None

ImagePRO/pre_processing/sharpen.py

@@ -10,9 +10,13 @@ sys.path.append(str(parent_dir))
 from utils.io_handler import IOHandler
 from pre_processing.blur import apply_average_blur
 
+# Constants
+DEFAULT_LAPLACIAN_COEFFICIENT = 3.0
+DEFAULT_UNSHARP_COEFFICIENT = 1.0
+
 
 def apply_laplacian_sharpening(
-    coefficient: float = 3.0,
+    coefficient: float = DEFAULT_LAPLACIAN_COEFFICIENT,
     src_image_path: str | None = None,
     src_np_image: np.ndarray | None = None,
     output_image_path: str | None = None
@@ -52,7 +56,7 @@ def apply_laplacian_sharpening(
 
 
 def apply_unsharp_masking(
-    coefficient: float = 1.0,
+    coefficient: float = DEFAULT_UNSHARP_COEFFICIENT,
     src_image_path: str | None = None,
     src_np_image: np.ndarray | None = None,
     output_image_path: str | None = None

ImagePRO/utils/__init__.py

@@ -0,0 +1,6 @@
+# Utils Module
+# Provides shared utilities for image I/O operations and data handling
+
+from .io_handler import IOHandler
+
+__all__ = ["IOHandler"]

imagepro_python-0.5.2.dist-info/METADATA

@@ -0,0 +1,30 @@
+Metadata-Version: 2.4
+Name: ImagePRO-Python
+Version: 0.5.2
+Summary: Professional & modular image processing library with OpenCV, MediaPipe, and YOLO integration.
+Author-email: Parsa Safaie <parsasafaie.2568@proton.me>
+License: MIT
+Project-URL: Homepage, https://github.com/parsasafaie/ImagePRO
+Project-URL: Repository, https://github.com/parsasafaie/ImagePRO.git
+Project-URL: Documentation, https://github.com/parsasafaie/ImagePRO#readme
+Project-URL: Issues, https://github.com/parsasafaie/ImagePRO/issues
+Keywords: opencv,mediapipe,computer-vision,face,pose,yolo,image-processing
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Scientific/Engineering :: Image Processing
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Requires-Python: ==3.10.*
+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
+Requires-Dist: insightface<1.0,>=0.7
+Dynamic: license-file

imagepro_python-0.5.2.dist-info/RECORD

@@ -0,0 +1,29 @@
+ImagePRO/__init__.py,sha256=WLaJEr5remdE8_84-TZ7gQbdv8G2qB5iXd-fkLK3zps,998
+ImagePRO/human_analysis/__init__.py,sha256=uSU0lM1p1HM6TNGv6u0nPHWy9QY505v43lqTkhClddM,190
+ImagePRO/human_analysis/body_analysis/__init__.py,sha256=czQoJJIrDAWz0UUY0h0mwxymSQ6L6CaZYYHhYFHyf4U,203
+ImagePRO/human_analysis/body_analysis/body_pose_estimation.py,sha256=SNuZ_fMhOhCq3PhHL4snCob0uozqkYz18tPlV2lZlJs,4307
+ImagePRO/human_analysis/body_analysis/hand_tracking.py,sha256=Qym-YK4ixgILk74ikX6D5YHQdOXErLG2OsaJF_w8P_4,5524
+ImagePRO/human_analysis/face_analysis/__init__.py,sha256=dKVZ6pq-0aQHL9vhMSt0BHs3WV_cTW65QPLJGnSiUgM,405
+ImagePRO/human_analysis/face_analysis/eye_status_analysis.py,sha256=ZbuBj2qkyUUBcUp-RSHquNwQU7Ntm0Go4jhAd-HkPLw,5739
+ImagePRO/human_analysis/face_analysis/face_comparison.py,sha256=dOi0MC6vkYMGo-44yQII9YoNEHYnSHK_j7lK6Gheu24,2180
+ImagePRO/human_analysis/face_analysis/face_detection.py,sha256=cPSytFmzUv8u-tNRxqaJ696Lucz5g6pt4EFqxHKprsQ,4146
+ImagePRO/human_analysis/face_analysis/face_mesh_analysis.py,sha256=zr_eBQDggsVkDWfaJdckJra24YnY3uyWviYv0MUGlKo,8533
+ImagePRO/human_analysis/face_analysis/head_pose_estimation.py,sha256=nPvAH21zuLQyzvqkq7UUl3ec_bx6oR94AwE8JtgqUmo,5903
+ImagePRO/object_analysis/__init__.py,sha256=pj1vjY8uVUqeVONpaCacWufUzHF7rS5-nmy_C5IfI2w,148
+ImagePRO/object_analysis/object_detection.py,sha256=PiweREsa9HOzW5DTUi1sVohfErm2QYROlRmes7UUaKg,3555
+ImagePRO/pre_processing/__init__.py,sha256=nXUhE8RnDyW7T93fKsSDPfqzGHIW50OvgQvznY5UH0E,417
+ImagePRO/pre_processing/blur.py,sha256=MXA2m-mB36A1OtmJEunZmFu_Q-cfRhvHdZj0tA9sc9A,6208
+ImagePRO/pre_processing/contrast.py,sha256=nhFUkXEOT6rXhubkWouu3yJY5ShdE4OZVWSgUqNgmvo,4480
+ImagePRO/pre_processing/crop.py,sha256=0PbKhgHyxwbCiP5ODyrTRKQca2hWt1O90_up7QpqLAE,2424
+ImagePRO/pre_processing/dataset_generator.py,sha256=k5MSO4WJfJe4V5crITXleZG4IXwtz1SW-iFgxAW4xDI,6308
+ImagePRO/pre_processing/grayscale.py,sha256=49xi9z2Wsa6MFXZDpNymIRY9wDnkLJZs70IWQJcdK3k,1241
+ImagePRO/pre_processing/resize.py,sha256=-lQINmrINSqywlsPQfDwIVyZJ4qVDT0p_6H-wl-E22w,1640
+ImagePRO/pre_processing/rotate.py,sha256=6poUFHAFGxJJP4wI9V2pl6MA7cVQnJhnIxLMMrIoPVw,3608
+ImagePRO/pre_processing/sharpen.py,sha256=TJLx0lMnFkJwxaz0BqSbEsKwa4EakdbBYku7yQNT22E,2841
+ImagePRO/utils/__init__.py,sha256=F3UA7o2Ai3o4PedPrP9yWtPgv0gipiojHHpioRWPKyM,146
+ImagePRO/utils/io_handler.py,sha256=lWc_UzoihbzZ7sObCFK7KXCOhsp00V6KUoMVpV-6tSs,6059
+imagepro_python-0.5.2.dist-info/licenses/LICENSE,sha256=sehkHN7dbe5umrINZJyJjIf9VTemZSgTfJlq6iIsbJQ,1069
+imagepro_python-0.5.2.dist-info/METADATA,sha256=xByO7dTlPdXAuHiNwRvPkgoLr6TNnmlkqjKEiw_Cj3E,1418
+imagepro_python-0.5.2.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+imagepro_python-0.5.2.dist-info/top_level.txt,sha256=UOuPzsoWrVKXgUupOSI96shJ6wE8Fhz-8bm8oMlLC3s,9
+imagepro_python-0.5.2.dist-info/RECORD,,

imagepro_python-0.5.1.dist-info/METADATA

@@ -1,20 +0,0 @@
-Metadata-Version: 2.4
-Name: ImagePRO-Python
-Version: 0.5.1
-Summary: clean, modular, and easy-to-use Python library for image processing tasks.
-Author-email: Parsa Safaie <parsasafaie.2568@proton.me>
-License: MIT
-Keywords: opencv,mediapipe,computer-vision,face,pose
-Classifier: Programming Language :: Python :: 3
-Classifier: License :: OSI Approved :: MIT License
-Classifier: Operating System :: OS Independent
-Classifier: Topic :: Scientific/Engineering :: Image Processing
-Requires-Python: ==3.10.*
-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
-Requires-Dist: insightface<1.0,>=0.7
-Dynamic: license-file

imagepro_python-0.5.1.dist-info/RECORD

@@ -1,28 +0,0 @@
-ImagePRO/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/human_analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/human_analysis/body_analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/human_analysis/body_analysis/body_pose_estimation.py,sha256=CXyJSyafARKTguMwThqIsd4xCdwb0rOwQM0pFVQx_oA,4099
-ImagePRO/human_analysis/body_analysis/hand_tracking.py,sha256=wVzW0soB3V1mLxF27oG27--vdpIuG1F1aVzhTtD2MGI,5220
-ImagePRO/human_analysis/face_analysis/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/human_analysis/face_analysis/eye_status_analysis.py,sha256=yzxzcniyVrTtlU2aADOx8IC2BMUYi2i7HfssPG-LfV4,5574
-ImagePRO/human_analysis/face_analysis/face_comparison.py,sha256=xdfLN7tljEO9YpnXI9MpR1Jvu4DuhOFDrSG6KR6UxbY,2030
-ImagePRO/human_analysis/face_analysis/face_detection.py,sha256=qob4dIVGZPZRDMy7_wS3LYWpaUNe7Q-P2_9IENrbc2E,4019
-ImagePRO/human_analysis/face_analysis/face_mesh_analysis.py,sha256=LjplQXxPpOzK0VdD_f73Be40PvSEG-T22_DFl4TvMKc,8356
-ImagePRO/human_analysis/face_analysis/head_pose_estimation.py,sha256=gRYRfW-sqZG1R1qeAH4S0rVMGZWS8ABosldfMhBbklI,5767
-ImagePRO/object_analysis/object_detection.py,sha256=PiMwZktfZDk6XftEFBmiwDZ4M0v-dcGrgf6w-JWo8n8,3482
-ImagePRO/pre_processing/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/pre_processing/blur.py,sha256=JqkM0cLfRrBlQEixkC-iuhu6rR62VPMA2KObzmcmt_Q,5909
-ImagePRO/pre_processing/contrast.py,sha256=00qp_BZ8-t1TqLE-bTWcLFS5bMCeAXTT7cNnADHUR3w,4341
-ImagePRO/pre_processing/crop.py,sha256=a5tF5nDOekCA-SqJqddYXzJo7PN2DZpcdIJsObpZBmA,2351
-ImagePRO/pre_processing/dataset_generator.py,sha256=DmcCfOPUbrkJUIltH5Zbv6C2gkAe5yT4JvihgVQg51E,6045
-ImagePRO/pre_processing/grayscale.py,sha256=PtdONZPmLzZpj7YpeBA9D_pYcVNTmOZPNJasDpeO9Yo,1325
-ImagePRO/pre_processing/resize.py,sha256=1ceEKZ7bHJK9a07QEzfEd6H3oqNT2yL5PWKI0HXmIkE,1890
-ImagePRO/pre_processing/rotate.py,sha256=tBNkiSZFpMPOjlQFQw9dR1y1zuT0Owqd4iBIRVEBrYs,3544
-ImagePRO/pre_processing/sharpen.py,sha256=CneU-avwfRsWRUU-COmAtpfWlMQgCN1WVp3hd96YJmc,2708
-ImagePRO/utils/__init__.py,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-ImagePRO/utils/io_handler.py,sha256=lWc_UzoihbzZ7sObCFK7KXCOhsp00V6KUoMVpV-6tSs,6059
-imagepro_python-0.5.1.dist-info/licenses/LICENSE,sha256=sehkHN7dbe5umrINZJyJjIf9VTemZSgTfJlq6iIsbJQ,1069
-imagepro_python-0.5.1.dist-info/METADATA,sha256=9f7vgjdNd-k7Qi6LMqTlWxOve-Rq7PgStxOoeaGM9V4,770
-imagepro_python-0.5.1.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-imagepro_python-0.5.1.dist-info/top_level.txt,sha256=UOuPzsoWrVKXgUupOSI96shJ6wE8Fhz-8bm8oMlLC3s,9
-imagepro_python-0.5.1.dist-info/RECORD,,