Add layout detection app.py

README.md

@@ -1,5 +1,5 @@
 ---
-title: Layoutdetection
+title: Document Layout Detection
 emoji: 📈
 colorFrom: purple
 colorTo: red
@@ -23,7 +23,7 @@ Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gr
 `colorTo`: _string_
 Color for Thumbnail gradient (red, yellow, green, blue, indigo, purple, pink, gray)
 
-`sdk`: _string_
+`sdk`: `gradio`
 Can be either `gradio`, `streamlit`, or `static`
 
 `sdk_version` : _string_

app.py

@@ -0,0 +1,32 @@
+import os
+import gradio as gr
+import numpy as np
+import layoutparser as lp
+from PIL import Image
+import PIL
+
+model = lp.Detectron2LayoutModel('lp://PubLayNet/faster_rcnn_R_50_FPN_3x/config', 
+                                 extra_config=["MODEL.ROI_HEADS.SCORE_THRESH_TEST", 0.8],
+                                 label_map={0: "Text", 1: "Title", 2: "List", 3:"Table", 4:"Figure"})
+
+article="References<br>[1] Z. Shen, R. Zhang, M. Dell, B. C. G. Lee, J. Carlson, and W. Li, “LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis,” arXiv Prepr. arXiv2103.15348, 2021."
+description = "Layout Detection/Parsing is one of the important tasks of converting unstructured data into structured data. This task helps to automate, digitize and organize the data in a usable format. In this project, we utilize LayoutParser library (https://github.com/Layout-Parser/layout-parser) to perform Layout Detection using pre-trained Faster_rcnn_R_50_FPN model that can classify the layout based on Text, Title, List, Table and Figure. Upload an image of a document or click an example image to check this out."
+
+def show_preds(input_image):
+  
+  img = PIL.Image.fromarray(input_image, 'RGB')
+  basewidth = 900
+  wpercent = (basewidth/float(img.size[0]))
+
+  hsize = int((float(img.size[1])*float(wpercent)))
+  img = img.resize((basewidth,hsize), Image.ANTIALIAS)
+  image_array=np.array(img)
+  layout = model.detect(image_array)
+  return lp.draw_box(image_array, layout, show_element_type=True)
+
+outputs = gr.outputs.Image(type="pil")
+
+examples = [['example1.png'], ['example2.png']]
+
+gr_interface = gr.Interface(fn=show_preds, inputs=["image"], outputs=outputs, title='Document Layout Detector/Parser', article=article, description=description, examples=examples,  analytics_enabled = True, enable_queue=True)
+gr_interface.launch(inline=False, share=True, debug=True)

requirements.txt

@@ -0,0 +1,3 @@
+layoutparser
+git+https://github.com/facebookresearch/[email protected]#egg=detectron2
+layoutparser[ocr]