MVP on OCT and webcam

main.py

@@ -0,0 +1,70 @@
+import cv2
+import easyocr
+import numpy as np
+from PIL import Image
+from collections import Counter
+
+# Initialize the EasyOCR reader
+reader = easyocr.Reader(['en'])
+
+def preprocess_image(image):
+    # Convert to PIL image for EasyOCR processing
+    return Image.fromarray(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
+
+def recognize_text(image):
+    processed_image = preprocess_image(image)
+    results = reader.readtext(np.array(processed_image), allowlist='0123456789')
+    # Concatenate all recognized text results
+    recognized_text = ''.join(result[1] for result in results)
+    return recognized_text
+
+def format_number(text, length=6):
+    # Remove non-numeric characters and pad with zeros if necessary
+    formatted = ''.join(filter(str.isdigit, text))
+    return formatted.zfill(length)[-length:]
+
+def most_common_number(numbers):
+    # Find the most common number from the list of numbers
+    counter = Counter(numbers)
+    most_common = counter.most_common(1)
+    return most_common[0][0] if most_common else ''
+
+def main():
+    cap = cv2.VideoCapture(2)
+
+    if not cap.isOpened():
+        print("Error: Could not open webcam.")
+        return
+
+    print("Press 'q' to quit.")
+    frame_count = 0
+    text_history = []
+
+    while True:
+        ret, frame = cap.read()
+        if not ret:
+            print("Error: Failed to capture image.")
+            break
+
+        # Recognize text from the current frame
+        recognized_text = recognize_text(frame)
+        formatted_number = format_number(recognized_text)
+
+        # Update the history with the latest recognized number
+        text_history.append(formatted_number)
+
+        # Keep only the last 10 frames
+        if len(text_history) > 20:
+            text_history.pop(0)
+
+        # Determine the most common number from the history
+        most_common = most_common_number(text_history)
+        print(f"Most common number from last 10 frames: {most_common}")
+
+        # if cv2.waitKey(1) & 0xFF == ord('q'):
+        #     break
+
+    cap.release()
+
+if __name__ == "__main__":
+    main()

requirements.txt

@@ -0,0 +1,75 @@
+absl-py==2.1.0
+astunparse==1.6.3
+certifi==2024.7.4
+charset-normalizer==3.3.2
+easyocr==1.7.1
+filelock==3.15.4
+flatbuffers==24.3.25
+fsspec==2024.6.1
+gast==0.6.0
+google-pasta==0.2.0
+grpcio==1.65.5
+h5py==3.11.0
+idna==3.7
+imageio==2.35.1
+Jinja2==3.1.4
+joblib==1.4.2
+keras==3.5.0
+lazy_loader==0.4
+libclang==18.1.1
+Markdown==3.7
+markdown-it-py==3.0.0
+MarkupSafe==2.1.5
+mdurl==0.1.2
+ml-dtypes==0.4.0
+mpmath==1.3.0
+namex==0.0.8
+networkx==3.3
+ninja==1.11.1.1
+numpy==1.26.4
+nvidia-cublas-cu12==12.1.3.1
+nvidia-cuda-cupti-cu12==12.1.105
+nvidia-cuda-nvrtc-cu12==12.1.105
+nvidia-cuda-runtime-cu12==12.1.105
+nvidia-cudnn-cu12==9.1.0.70
+nvidia-cufft-cu12==11.0.2.54
+nvidia-curand-cu12==10.3.2.106
+nvidia-cusolver-cu12==11.4.5.107
+nvidia-cusparse-cu12==12.1.0.106
+nvidia-nccl-cu12==2.20.5
+nvidia-nvjitlink-cu12==12.6.20
+nvidia-nvtx-cu12==12.1.105
+opencv-python==4.10.0.84
+opencv-python-headless==4.10.0.84
+opt-einsum==3.3.0
+optree==0.12.1
+packaging==24.1
+pillow==10.4.0
+protobuf==4.25.4
+pyclipper==1.3.0.post5
+Pygments==2.18.0
+pytesseract==0.3.13
+python-bidi==0.6.0
+PyYAML==6.0.2
+requests==2.32.3
+rich==13.7.1
+scikit-image==0.24.0
+scikit-learn==1.5.1
+scipy==1.14.1
+shapely==2.0.6
+six==1.16.0
+sympy==1.13.2
+tensorboard==2.17.1
+tensorboard-data-server==0.7.2
+tensorflow==2.17.0
+tensorflow-io-gcs-filesystem==0.37.1
+termcolor==2.4.0
+threadpoolctl==3.5.0
+tifffile==2024.8.10
+torch==2.4.0
+torchvision==0.19.0
+triton==3.0.0
+typing_extensions==4.12.2
+urllib3==2.2.2
+Werkzeug==3.0.4
+wrapt==1.16.0