Update app.py

app.py

@@ -1,56 +1,48 @@
+from typing import List
+
 import pytesseract
 from PIL import Image
-import gradio as gr
-import cv2
-import numpy as np
-import os
-
-def select_roi_and_ocr(filepath: str):
-    if not os.path.exists(filepath):
-        return "Dosya mevcut değil. Lütfen tekrar yükleyin."
-    # Görseli yükle
-    image = cv2.imread(filepath)
-    image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)  # Gradio ile uyumlu hale getirmek için
-
-    # Kullanıcıdan alan seçmesini iste
-    roi = cv2.selectROI("Alanı Seçin (ESC ile çıkın)", image_rgb, showCrosshair=True)
-    cv2.destroyAllWindows()
-
-    # Koordinatları al
-    x, y, w, h = roi
-    if w == 0 or h == 0:  # Hiçbir şey seçilmemişse
-        return "Hiçbir alan seçilmedi!"
-
-    # Seçilen alanı kırp
-    cropped_image = image[y:y+h, x:x+w]
-    cropped_image_pil = Image.fromarray(cv2.cvtColor(cropped_image, cv2.COLOR_BGR2RGB))  # OCR için PIL formatına dönüştür
-
-    # OCR işlemi
-    text = pytesseract.image_to_string(cropped_image_pil, lang="eng")
-    return text
-
-# Gradio arayüzü
-with gr.Blocks() as demo:
-    with gr.Row():
-        gr.Markdown("## Tesseract OCR with Mouse Selection Box")
 
-    with gr.Row():
-        img_input = gr.Image(type="filepath", label="Upload Image")
+import gradio as gr
 
+def tesseract_ocr(filepath: str, languages: List[str]=None):
+    image = Image.open(filepath)
+    return pytesseract.image_to_string(image=image, lang=', '.join(languages) if languages else None)
+
+title = "Tesseract OCR"
+description = "Gradio demo for Tesseract. Tesseract is an open source text recognition (OCR) Engine."
+article = "<p style='text-align: center'><a href='https://tesseract-ocr.github.io/' target='_blank'>Tesseract documentation</a> | <a href='https://github.com/tesseract-ocr/tesseract' target='_blank'>Github Repo</a></p>"
+examples = [
+    ["examples/weird_unicode_math_symbols.png", []],
+    ["examples/eurotext.png", ["eng"]],
+    ["examples/tesseract_sample.png", ["jpn", "eng"]],
+    ["examples/chi.jpg", ["HanS", "HanT"]],
+]
+
+with gr.Blocks(title=title) as demo:
+    gr.Markdown(f'<h1 style="text-align: center; margin-bottom: 1rem;">{title}</h1>')
+    gr.Markdown(description)
     with gr.Row():
-        ocr_button = gr.Button("Run OCR with Mouse Selection")
-    
-    with gr.Row():
-        ocr_output = gr.Textbox(label="OCR Result")
-
-    def run_ocr_with_mouse_selection(image_path):
-        return select_roi_and_ocr(image_path)
-
-    ocr_button.click(
-        run_ocr_with_mouse_selection,
-        inputs=[img_input],
-        outputs=[ocr_output]
+        with gr.Column():
+            image = gr.Image(type="filepath", label="Input")
+            language_choices = pytesseract.get_languages()
+            with gr.Accordion("Languages", open=False):
+                languages = gr.CheckboxGroup(language_choices, type="value", value=["eng"], label='language')
+            with gr.Row():
+                btn_clear = gr.ClearButton([image, languages])
+                btn_submit = gr.Button(value="Submit", variant="primary")
+        with gr.Column():
+            text = gr.Textbox(label="Output")
+
+    btn_submit.click(tesseract_ocr, inputs=[image, languages], outputs=text, api_name="tesseract-ocr")
+    btn_clear.add(text)
+
+    gr.Examples(
+        examples=examples,
+        inputs=[image, languages],
     )
 
-if __name__ == "__main__":
-    demo.launch(debug=True)
+    gr.Markdown(article)
+
+if __name__ == '__main__':
+    demo.launch()