v2.0.1-Simple OCR using Tesseract and OpenCV

app.py

@@ -1,7 +1,40 @@
 import gradio as gr
 
+# try:
+#  from PIL import Image
+# except ImportError:
+#  import Image
+import cv2
+import pytesseract
+
+sample_img = cv2.imread(r'/content/image.png')
+
+def ocr_core(img):
+  text = pytesseract.image_to_string(img)
+  return text
+
+def get_grayscale(image):
+    return cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
+
+def remove_noise(image):
+    return cv2.medianBlur(image,5)
+
+def thresholding(image):
+    return cv2.threshold(image, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)[1]
+
+def final_ocr(img):
+    gray = get_grayscale(img)
+    thresh = thresholding(gray)
+    noiseless = remove_noise(thresh)
+    return ocr_core(noiseless)
+
 def greet(name):
     return "Hello " + name + "!!"
 
-iface = gr.Interface(fn=greet, inputs="text", outputs="text")
-iface.launch()
+# iface = gr.Interface(fn=greet, inputs="text", outputs="text")
+
+# iface.launch()
+demo = gr.Interface(fn=final_ocr,
+                    inputs=gr.inputs.Image(type="pil"),
+                    outputs=gr.outputs.Textbox())
+demo.launch()

requirements.txt

@@ -1 +1,3 @@
-gradio
+pytesseract
+PIL 
+opencv_python