Duplicate from ajitrajasekharan/Image-Text-Detection

Co-authored-by: ajit rajasekharan <[email protected]>

.gitattributes

@@ -0,0 +1,27 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bin.* filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zstandard filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,13 @@
+---
+title: Image Text Detection
+emoji: 👀
+colorFrom: yellow
+colorTo: yellow
+sdk: streamlit
+app_file: app.py
+pinned: false
+license: mit
+duplicated_from: ajitrajasekharan/Image-Text-Detection
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -0,0 +1,62 @@
+import PIL 
+from PIL import ImageDraw
+from PIL import Image
+import streamlit as st
+import os
+
+
+def load_image(image_file):
+	img = PIL.Image.open(image_file)
+	return img
+
+def init_session_states():
+  if 'disp' not in st.session_state:
+    st.session_state['disp'] = st.empty()
+    st.session_state['disp'].text("Setting up environment with latest build of easyocr. This will take about a minute ")
+  if 'init' not in st.session_state:
+    st.session_state['init'] = 1
+    os.system('pip install git+git://github.com/jaidedai/easyocr.git')
+    os.system('pip install git+https://github.com/huggingface/transformers.git --upgrade')
+
+
+
+init_session_states()
+import easyocr
+from transformers import TrOCRProcessor, VisionEncoderDecoderModel
+
+def text_recognition(image):
+    processor = TrOCRProcessor.from_pretrained("microsoft/trocr-base-handwritten") 
+    model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-base-handwritten")
+    #processor = TrOCRProcessor.from_pretrained("microsoft/trocr-large-handwritten") 
+    #model = VisionEncoderDecoderModel.from_pretrained("microsoft/trocr-large-handwritten")
+
+    pixel_values = processor(image, return_tensors="pt").pixel_values 
+    generated_ids = model.generate(pixel_values)
+    generated_text = processor.batch_decode(generated_ids, skip_special_tokens=True)[0] 
+    st.write(generated_text)
+
+def main():
+   
+    st.session_state['disp'].text("Env setup up Complete")
+    uploaded_file = st.file_uploader("Choose image file to detect text",type=['jpeg','jpg'])
+    if uploaded_file is not None:
+        file_details = {"FileName":uploaded_file.name,"FileType":uploaded_file.type,"FileSize":uploaded_file.size}
+        st.write(file_details)
+        image = load_image(uploaded_file)
+        st.image(image,width=500)
+        st.write("Detecting text bounding box and Take 1 recognition...")
+        reader = easyocr.Reader(['en'],gpu=True)
+        bound = reader.readtext(image)
+        st.write("Bounding box Detection complete")
+        st.write(str(bound))
+        st.write("Recognizing text - Take 2....")
+        text_recognition(image)
+   
+   
+ 
+if __name__ == "__main__":
+    main()
+                  
+
+   
+    

requirements.txt

@@ -0,0 +1,4 @@
+pillow
+sentencepiece
+transformers
+streamlit==1.1.0