Update app.py

app.py

@@ -1,140 +1,79 @@
 import streamlit as st
-from streamlit_drawable_canvas import st_canvas
-import cv2
 import numpy as np
-from tensorflow.keras.models import load_model
-from PIL import Image
-import easyocr
 import pandas as pd
+import easyocr
+from PIL import Image
+from streamlit_drawable_canvas import st_canvas
 
-# Load the model for Myanmar character recognition
-model = load_model('mm.h5')
-
-# Initialize EasyOCR reader for English
-reader = easyocr.Reader(['en'], gpu=False)
-
-class_lists = [
-   "0",
-   "1",
-   "2",
-   "3",
-   "4",
-   "5",
-   "6",
-   "7",
-   "8",
-   "9",
-    "Ah",
-    "Aha",
-    "au2",
-    "au3",
-    "ay2",
-    "ba_htoat_chite",
-    "ba_kone",
-    "da_htway",
-    "da_out_chite",
-    "da_yay_hmote",
-    "da_yin_kout",
-    "e1",
-    "e2",
-    "eeare",
-    "ga_khi",
-    "ga_nge",
-    "ha",
-    "hsa_lain",
-    "hta_hsin_htu",
-    "hta_wun_beare",
-    "ka_kji",
-    "kha_khway",
-    "la",
-    "la_kji",
-    "ma",
-    "na_kji",
-    "na_ngear",
-    "nga",
-    "nga_kyi",
-    "O",
-    "pa_sout",
-    "pfa_u_htoat",
-    "sah_lone",
-    "ta_thun_lyin_chate",
-    "ta_wun_pu",
-    "tha",
-    "u1",
-    "u2",
-    "un",
-    "wa",
-    "yah_kout",
-    "yah_pet_let",
-    "za_kwear",
-    "za_myin_hsware"
-]
-
-# Streamlit UI
-st.title('Text and Character Recognizer')
-st.markdown('''
-Select the mode for recognition:
-''')
-
-# Choose mode
-mode = st.radio("Mode", ('English Text Recognition', 'Myanmar Character Recognition'))
-
-if mode == 'English Text Recognition':
-    uploaded_file = st.file_uploader("Upload your file here...", key="uploader_english")
-    if uploaded_file is not None:
-        image = Image.open(uploaded_file)
-        st.image(image, caption='Uploaded Image', use_column_width=True)
+def rectangle(image, result):
+    """Draw rectangles on image based on predicted coordinates using PIL."""
+    from PIL import ImageDraw
+    draw = ImageDraw.Draw(image)
+    for res in result:
+        top_left = tuple(res[0][0])
+        bottom_right = tuple(res[0][2])
+        draw.rectangle((top_left, bottom_right), outline="blue", width=2)
+    return image
 
-        # EasyOCR to recognize text
-        result = reader.readtext(np.array(image))
-        for detection in result:
-            st.write(f'Detected text: {detection[1]}, Confidence: {detection[2]}')
+def main():
+    # Set up Streamlit page
+    st.set_page_config(
+        page_title="OCR App",
+        page_icon=":mag:",
+        layout="centered",
+        initial_sidebar_state="auto",
+    )
 
-elif mode == 'Myanmar Character Recognition':
+    st.title("Optical Character Recognition (OCR) with EasyOCR")
+    
+    st.markdown("""
+    Upload an image or use the canvas to draw, and the app will recognize and extract text from it.
+    Supported languages for recognition include English and Japanese.
+    """)
+    
+    # Upload image or draw
     col1, col2 = st.columns(2)
-
     with col1:
-        uploaded_file = st.file_uploader("Upload your file here...", key="uploader_myanmar")
-
+        file = st.file_uploader("Upload Image", type=['png', 'jpg', 'jpeg'])
     with col2:
-        # Initialize canvas
+        stroke_width = st.slider("Stroke Width: ", 1, 25, 3)
         canvas_result = st_canvas(
             fill_color="rgba(255, 165, 0, 0.3)",
-            stroke_width=3,
+            stroke_width=stroke_width,
             stroke_color="#ffffff",
             background_color="#000000",
             update_streamlit=True,
-            width=200,
-            height=200,
+            width=400,
+            height=400,
             drawing_mode="freedraw",
             key="canvas",
         )
 
-    # Process the image for prediction
-    image_data = None
-    if uploaded_file is not None:
-        image_data = Image.open(uploaded_file).convert('RGB')
+    # Process uploaded image or drawing
+    if file is not None:
+        image = Image.open(file).convert('RGB')
     elif canvas_result.image_data is not None:
-        image_data = Image.fromarray(np.uint8(canvas_result.image_data)).convert('RGB')
-
-    if image_data is not None:
-        # Convert PIL image to OpenCV format
-        image_cv = np.array(image_data)
-        image_cv = cv2.cvtColor(image_cv, cv2.COLOR_RGB2BGR)
-        resized_image = cv2.resize(image_cv, (200, 200))
-        # Prepare image for model input
-        model_input = resized_image[np.newaxis, :, :, :3]
-
-        st.write('Model Input')
-        st.image(model_input, width=200)  # Display the input image to model
+        image = Image.fromarray(np.array(canvas_result.image_data).astype('uint8'), 'RGBA').convert('RGB')
+    else:
+        st.warning("Please upload an image or use the canvas to draw.")
+        st.stop()
 
-        if st.button('Predict Myanmar Character'):
-            # Predict the class
-            val = model.predict(model_input)
-            predicted_class_index = np.argmax(val)
-            mm_text = class_lists[predicted_class_index]
-            st.write(f'Result: {mm_text}, Index: {predicted_class_index}')
-            st.bar_chart(val[0])
+    st.image(image, caption='Uploaded Image', use_column_width=True)
+    
+    # OCR
+    reader = easyocr.Reader(['en', 'ja'], gpu=False)
+    result = reader.readtext(np.array(image))
+    
+    # Display results
+    if result:
+        image = rectangle(image, result)
+        st.image(image, caption='Processed Image with Detected Text', use_column_width=True)
+        
+        textdic_easyocr = {idx: {'text': res[1], 'confidence': res[2]} for idx, res in enumerate(result)}
+        df = pd.DataFrame.from_dict(textdic_easyocr, orient='index')
+        st.dataframe(df)
     else:
-        if mode == 'Myanmar Character Recognition':
-            st.write("Please upload an image or draw in the canvas above.")
+        st.info("No text detected.")
+
+if __name__ == "__main__":
+    main()