Gesture simplification

Dockerfile

@@ -29,18 +29,18 @@ WORKDIR $HOME/app
 RUN pip install --no-cache-dir --upgrade pip
 
 # Copy requirements first for better Docker layer caching
-COPY --chown=user requirements.txt $HOME/app/
+COPY --chown=user docker/requirements.txt $HOME/app/
 
 # Install Python dependencies
 RUN pip install --no-cache-dir --user -r requirements.txt
 
-# Copy the source code
-COPY --chown=user src/ $HOME/app/src/
-COPY --chown=user models/ $HOME/app/models/
+# Copy the source code from parent directory
+COPY --chown=user ../src/ $HOME/app/src/
+COPY --chown=user ../models/ $HOME/app/models/
 
-# Copy the main entry point
-COPY --chown=user main.py $HOME/app/
-COPY --chown=user README.md $HOME/app/
+# Copy the main entry point from parent directory
+COPY --chown=user ../main.py $HOME/app/
+COPY --chown=user ../README.md $HOME/app/
 
 # Expose the port that the app runs on (HF Spaces default is 7860)
 EXPOSE 7860

src/gesturedetection/api.py

@@ -8,7 +8,7 @@ from fastapi import FastAPI, UploadFile, File, HTTPException, Form
 from fastapi.responses import ORJSONResponse
 from fastapi.encoders import jsonable_encoder
 
-from .models import Gesture, GestureResponse, GESTURE_MAPPING, FULL_GESTURE_MAPPING
+from .models import Gesture, GestureResponse, GESTURE_MAPPING, FULL_GESTURE_MAPPING, PRODUCTION_GESTURE_MAPPING
 from .config import get_logfire_token, is_monitoring_enabled
 
 # Import the gesture detection components
@@ -178,7 +178,7 @@ def process_video_for_gestures(video_path: str, detector_path: str = "models/han
                     # Adjust minimum duration based on frame skip
                     min_duration = max(5, frame_skip * 2)  # At least 2 processed frames
                     if current_gesture is not None and current_duration >= min_duration:
-                        gesture_name = FULL_GESTURE_MAPPING.get(current_gesture, f"unknown_{current_gesture}")
+                        gesture_name = PRODUCTION_GESTURE_MAPPING.get(current_gesture, f"unknown_{current_gesture}")
                         avg_confidence = current_confidence / current_duration if current_duration > 0 else 0.0
                         # Scale duration back to original frame count
                         scaled_duration = current_duration * frame_skip
@@ -208,7 +208,7 @@ def process_video_for_gestures(video_path: str, detector_path: str = "models/han
             # Don't forget the last gesture
             min_duration = max(5, frame_skip * 2)  # At least 2 processed frames
             if current_gesture is not None and current_duration >= min_duration:
-                gesture_name = FULL_GESTURE_MAPPING.get(current_gesture, f"unknown_{current_gesture}")
+                gesture_name = PRODUCTION_GESTURE_MAPPING.get(current_gesture, f"unknown_{current_gesture}")
                 avg_confidence = current_confidence / current_duration if current_duration > 0 else 0.0
                 # Scale duration back to original frame count
                 scaled_duration = current_duration * frame_skip

src/gesturedetection/models.py

@@ -39,7 +39,43 @@ GESTURE_MAPPING = {
     35: "stop",            # stop gesture
 }
 
-# Additional gesture mappings for completeness
+# Production gesture mapping with clean, consistent names
+# Hand-agnostic counting (left/right variations map to same gesture)
+PRODUCTION_GESTURE_MAPPING = {
+    # Counting gestures (1-5) - hand agnostic
+    30: "one",             # 1 finger (any direction)
+    42: "one",             # 1 finger left (maps to "one")
+    43: "one",             # 1 finger right (maps to "one")
+    44: "one",             # 1 finger down (maps to "one")
+    
+    32: "two",             # 2 fingers (peace sign)
+    39: "two",             # 2 fingers up (maps to "two")
+    14: "two",             # 2 fingers left (maps to "two")
+    15: "two",             # 2 fingers right (maps to "two")
+    16: "two",             # 2 fingers down (maps to "two")
+    
+    37: "three",           # 3 fingers (any direction)
+    21: "three",           # 3 fingers variant (maps to "three")
+    38: "three",           # 3 fingers variant 2 (maps to "three")
+    
+    26: "four",            # 4 fingers
+    
+    31: "five",            # 5 fingers (open palm)
+    
+    # Extra gestures for production
+    27: "thumbs_up",       # thumbs up gesture
+    23: "middle_finger",   # middle finger
+    33: "peace_inverted",  # peace sign inverted
+    
+    # Additional useful gestures
+    29: "ok",              # OK sign
+    20: "call",            # call me gesture
+    25: "fist",            # closed fist
+    19: "point",           # pointing
+    35: "stop",            # stop gesture
+}
+
+# Additional gesture mappings for completeness (all raw model outputs)
 FULL_GESTURE_MAPPING = {
     0: "hand_down",
     1: "hand_right", 

src/validate/gesture_validator.py

@@ -60,11 +60,11 @@ class GestureValidator:
         # Import here to avoid circular imports and handle missing dependencies gracefully
         try:
             from ..gesturedetection.main_controller import MainController
-            from ..gesturedetection.models import FULL_GESTURE_MAPPING
+            from ..gesturedetection.models import PRODUCTION_GESTURE_MAPPING
             self._main_controller_class = MainController
-            self._gesture_mapping = FULL_GESTURE_MAPPING
+            self._gesture_mapping = PRODUCTION_GESTURE_MAPPING
             self._initialized = True
-            logger.info("GestureValidator initialized successfully")
+            logger.info("GestureValidator initialized successfully with PRODUCTION_GESTURE_MAPPING")
         except ImportError as e:
             logger.warning(f"Could not import gesture detection components: {e}")
             self._initialized = False
@@ -458,7 +458,11 @@ class GestureValidator:
 
     def _normalize_gesture_name(self, gesture_name: str) -> str:
         """
-        Normalize gesture names to standard format.
+        Normalize gesture names to production-standard format.
+        
+        Handles legacy naming and variations to ensure consistent gesture names
+        across different parts of the system. Maps old names like "like" to 
+        "thumbs_up", and handles hand-agnostic counting variations.
 
         Parameters
         ----------
@@ -468,25 +472,26 @@ class GestureValidator:
         Returns
         -------
         str
-            Normalized gesture name
+            Normalized gesture name matching PRODUCTION_GESTURE_MAPPING
         """
         # Convert to lowercase and remove common variations
         normalized = gesture_name.lower().strip()
 
-        # Handle common variations
+        # Handle common variations and legacy names
         variations = {
-            "thumbs_up": ["thumbsup", "thumb_up", "like"],
-            "peace": ["peace_sign", "victory", "two_fingers"],
+            "thumbs_up": ["thumbsup", "thumb_up", "like"],  # "like" is legacy name
+            "one": ["one_finger", "one_left", "one_right", "one_down"],  # Hand-agnostic
+            "two": ["peace_sign", "victory", "two_fingers", "two_up", "two_left", "two_right", "two_down"],  # Hand-agnostic
+            "three": ["three_fingers", "three2", "three3"],  # Hand-agnostic
+            "four": ["four_fingers"],
+            "five": ["palm", "open_palm", "five_fingers"],  # "palm" is alias for "five"
+            "peace_inverted": ["peace_inverted_sign"],
             "ok": ["okay", "ok_sign"],
             "call": ["call_me", "phone"],
-            "palm": ["open_palm", "five_fingers"],
             "fist": ["closed_fist"],
             "point": ["pointing"],
             "stop": ["stop_sign"],
-            "one": ["one_finger"],
-            "two_up": ["two_fingers_up"],
-            "three": ["three_fingers"],
-            "four": ["four_fingers"]
+            "middle_finger": ["middle"],
         }
 
         for standard_name, variant_list in variations.items():