refactor: ensemble monitoring and weight optimization agents, refactor minmax processing function, and update requirements

app_mcp.py

@@ -12,17 +12,17 @@ import io
 import logging
 from utils.utils import softmax, augment_image, convert_pil_to_bytes
 from utils.gradient import gradient_processing
-from utils.minmax import preprocess as minmax_preprocess
+from utils.minmax import minmax_process
 from utils.ela import genELA as ELA
 from utils.wavelet import wavelet_blocking_noise_estimation
 from utils.bitplane import bit_plane_extractor
 from utils.hf_logger import log_inference_data
 from utils.text_content import QUICK_INTRO, IMPLEMENTATION
-from agents.monitoring_agents import EnsembleMonitorAgent, WeightOptimizationAgent, SystemHealthAgent
+from agents.ensemble_team import EnsembleMonitorAgent, WeightOptimizationAgent, SystemHealthAgent
 from agents.smart_agents import ContextualIntelligenceAgent, ForensicAnomalyDetectionAgent
 
 from forensics.registry import register_model, MODEL_REGISTRY, ModelEntry
-from agents.weight_management import ModelWeightManager
+from agents.ensemble_weights import ModelWeightManager
 from dotenv import load_dotenv
 import json
 from huggingface_hub import CommitScheduler
@@ -361,7 +361,7 @@ def predict_image_with_json(img, confidence_threshold, augment_methods, rotate_d
     
     # 6. Perform forensic processing
     gradient_image = gradient_processing(img_np_og)  # Added gradient processing
-    minmax_image = minmax_preprocess(img_np_og)  # Added MinMax processing
+    minmax_image = minmax_process(img_np_og)  # Added MinMax processing
     bitplane_image = bit_plane_extractor(img_np_og)
     
 
@@ -617,7 +617,7 @@ with gr.Blocks(css="#post-gallery { overflow: hidden !important;} .grid-wrap{ ov
         )
     with gr.Tab("MinMax Processing", visible=False):
         gr.Interface(
-            fn=minmax_preprocess,
+            fn=minmax_process,
             inputs=[
                 gr.Image(type="pil", label="Input Image"),
                 gr.Radio([0, 1, 2, 3, 4], label="Channel (0:Grayscale, 1:Blue, 2:Green, 3:Red, 4:RGB Norm)", value=4),

requirements.txt

@@ -15,4 +15,5 @@ pyexiftool
 psutil
 datasets
 Pillow
-python-dotenv
+python-dotenv
+smolagents[all]

utils/minmax.py

@@ -27,7 +27,19 @@ def blk_filter(img, radius):
             )
     return cv.normalize(result, None, 0, 127, cv.NORM_MINMAX, cv.CV_8UC1)
 
-def preprocess(image, channel=4, radius=2):
+def minmax_process(image, channel=4, radius=2):
+    """
+    Analyzes local pixel value deviations in an image to detect potential manipulation by comparing each pixel with its neighbors. This forensic technique helps identify areas where pixel values deviate significantly from their local context, which can indicate digital tampering or editing.
+    
+    Args:
+        image: Union[np.ndarray, Image.Image]: Input image to process
+        channel (int): Channel to process (0:Grayscale, 1:Blue, 2:Green, 3:Red, 4:RGB Norm)
+        radius (int): Radius for block filtering
+    Returns:
+        PIL.Image.Image: The processed image showing minmax deviations.
+    Raises:
+        ValueError: If the input image is invalid or channel/radius parameters are out of valid range.
+    """
     if not isinstance(image, np.ndarray):
         image = np.array(image)  # Ensure image is a NumPy array
     if channel == 0: