add paddle ocr

app.py

@@ -77,7 +77,7 @@ def process(
     image_input.save(image_save_path)
     # import pdb; pdb.set_trace()
 
-    ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_save_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9})
+    ocr_bbox_rslt, is_goal_filtered = check_ocr_box(image_save_path, display_img = False, output_bb_format='xyxy', goal_filtering=None, easyocr_args={'paragraph': False, 'text_threshold':0.9}, use_paddleocr=True)
     text, ocr_bbox = ocr_bbox_rslt
     # print('prompt:', prompt)
     dino_labled_img, label_coordinates, parsed_content_list = get_som_labeled_img(image_save_path, yolo_model, BOX_TRESHOLD = box_threshold, output_coord_in_ratio=True, ocr_bbox=ocr_bbox,draw_bbox_config=draw_bbox_config, caption_model_processor=caption_model_processor, ocr_text=text,iou_threshold=iou_threshold)
@@ -117,5 +117,5 @@ with gr.Blocks() as demo:
     )
 
 # demo.launch(debug=False, show_error=True, share=True)
-demo.launch(share=True, server_port=7861, server_name='0.0.0.0')
-# demo.queue().launch(share=False)
+# demo.launch(share=True, server_port=7861, server_name='0.0.0.0')
+demo.queue().launch(share=False)

requirements.txt

@@ -14,3 +14,5 @@ dill
 accelerate
 timm
 einops==0.8.0
+paddlepaddle
+paddleocr

utils.py

@@ -18,7 +18,17 @@ import numpy as np
 # %matplotlib inline
 from matplotlib import pyplot as plt
 import easyocr
+from paddleocr import PaddleOCR
 reader = easyocr.Reader(['en'])
+paddle_ocr = PaddleOCR(
+    lang='en',  # other lang also available
+    use_angle_cls=False,
+    use_gpu=False,  # using cuda will conflict with pytorch in the same process
+    show_log=False,
+    max_batch_size=1024,
+    use_dilation=True,  # improves accuracy
+    det_db_score_mode='slow',  # improves accuracy
+    rec_batch_num=1024)
 import time
 import base64
 
@@ -370,14 +380,18 @@ def get_xywh_yolo(input):
     
 
 
-def check_ocr_box(image_path, display_img = True, output_bb_format='xywh', goal_filtering=None, easyocr_args=None):
-    if easyocr_args is None:
-        easyocr_args = {}
-    result = reader.readtext(image_path, **easyocr_args)
-    is_goal_filtered = False
-    # print('goal filtering pred:', result[-5:])
-    coord = [item[0] for item in result]
-    text = [item[1] for item in result]
+def check_ocr_box(image_path, display_img = True, output_bb_format='xywh', goal_filtering=None, easyocr_args=None, use_paddleocr=False):
+    if use_paddleocr:
+        result = paddle_ocr.ocr(image_path, cls=False)[0]
+        coord = [item[0] for item in result]
+        text = [item[1][0] for item in result]
+    else:  # EasyOCR
+        if easyocr_args is None:
+            easyocr_args = {}
+        result = reader.readtext(image_path, **easyocr_args)
+        # print('goal filtering pred:', result[-5:])
+        coord = [item[0] for item in result]
+        text = [item[1] for item in result]
     # read the image using cv2
     if display_img:
         opencv_img = cv2.imread(image_path)
@@ -397,7 +411,7 @@ def check_ocr_box(image_path, display_img = True, output_bb_format='xywh', goal_
         elif output_bb_format == 'xyxy':
             bb = [get_xyxy(item) for item in coord]
         # print('bounding box!!!', bb)
-    return (text, bb), is_goal_filtered
+    return (text, bb), goal_filtering