• For any query, contact us at
  • +91-9872993883
  • +91-8283824812
  • info@ris-ai.com
RIS AI - Thesis Expert
Most Viewed Articles
Object Detection | Start up Profit Prediction | RealTime Eye Blink Detection | House Budget Prediction | Human Detection and Counting | Pencil Sketch of Photo | Predict Next Word with Python | Hand Gesture Recognition | Handwritten Character Recognition
  • Blogs >

  • Overview of OCR(optical character recognition).

OCR - Optical Character Recognition

Optical Character Recognition (OCR) technology is a Business Solution for automating data extraction from a scanned document or image file and then convert it into the text into a machine-readable form so that it can be used for data processing like editing or searching.

Optical Character Recognition

PaddleOCR

PaddleOCR was developed by a Chinese company named 'Baidu' in September 2020. They have used the PaddlePaddle deep learning framework.

Detection Angle Classification and Recognition

In [73]:
from paddleocr import PaddleOCR,draw_ocr
# Paddleocr supports Chinese, English, French, German, Korean and Japanese.
# You can set the parameter `lang` as `ch`, `en`, `french`, `german`, `korean`, `japan`
# to switch the language model in order.
ocr = PaddleOCR(use_angle_cls=True, lang='en') # need to run only once to download and load model into memory
img_path = 'image.jpeg'
result = ocr.ocr(img_path, cls=True)
for line in result:
    print(line)


# draw result
from PIL import Image
image = Image.open(img_path).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='fonts/cyrillic.ttf')
im_show = Image.fromarray(im_show)
im_show.save('result.jpg')

Namespace(benchmark=False, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir='.paddleocr/2.2.0.2/ocr/cls/ch_ppocr_mobile_v2.0_cls_infer', cls_thresh=0.9, cpu_threads=10, det=True, det_algorithm='DB', det_db_box_thresh=0.6, det_db_score_mode='fast', det_db_thresh=0.3, det_db_unclip_ratio=1.5, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='.paddleocr/2.2.0.2/ocr/det/en/en_ppocr_mobile_v2.0_det_infer', det_sast_nms_thresh=0.2, det_sast_polygon=False, det_sast_score_thresh=0.5, drop_score=0.5, e2e_algorithm='PGNet', e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_limit_side_len=768, e2e_limit_type='max', e2e_model_dir=None, e2e_pgnet_mode='fast', e2e_pgnet_polygon=True, e2e_pgnet_score_thresh=0.5, e2e_pgnet_valid_set='totaltext', enable_mkldnn=False, gpu_mem=500, help='==SUPPRESS==', image_dir=None, ir_optim=True, label_list=['0', '180'], lang='en', layout_path_model='lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config', max_batch_size=10, max_text_length=25, min_subgraph_size=10, output='./output/table', precision='fp32', process_id=0, rec=True, rec_algorithm='CRNN', rec_batch_num=6, rec_char_dict_path='local/lib/python3.6/site-packages/paddleocr/ppocr/utils/en_dict.txt', rec_char_type='ch', rec_image_shape='3, 32, 320', rec_model_dir='.paddleocr/2.2.0.2/ocr/rec/en/en_number_mobile_v2.0_rec_infer', save_log_path='./log_output/', show_log=True, table_char_dict_path=None, table_char_type='en', table_max_len=488, table_model_dir=None, total_process_num=1, type='ocr', use_angle_cls=True, use_dilation=False, use_gpu=True, use_mp=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, vis_font_path='./doc/fonts/simfang.ttf', warmup=True)
[2021/08/13 19:21:01] root DEBUG: dt_boxes num : 10, elapse : 0.4250295162200928
[2021/08/13 19:21:01] root DEBUG: cls num  : 10, elapse : 0.06311750411987305
[2021/08/13 19:21:01] root DEBUG: rec_res num  : 10, elapse : 0.16244864463806152
[[[104.0, 93.0], [256.0, 103.0], [254.0, 134.0], [102.0, 124.0]], ('MALA', 0.98211896)]
[[[66.0, 161.0], [265.0, 157.0], [266.0, 181.0], [66.0, 184.0]], ('00418-00-6418', 0.9912834)]
[[[60.0, 360.0], [152.0, 360.0], [152.0, 378.0], [60.0, 378.0]], ('BINTLAR', 0.9820388)]
[[[158.0, 364.0], [200.0, 364.0], [200.0, 378.0], [158.0, 378.0]], ('RN', 0.8610319)]
[[[56.0, 403.0], [140.0, 406.0], [139.0, 427.0], [55.0, 424.0]], ('LOT2272', 0.99408233)]
[[[54.0, 429.0], [265.0, 427.0], [266.0, 455.0], [54.0, 457.0]], ('4B400PETALING JAYA', 0.9694132)]
[[[521.0, 438.0], [663.0, 436.0], [663.0, 450.0], [521.0, 452.0]], ('WARGANEGARA', 0.9971807)]
[[[55.0, 461.0], [162.0, 461.0], [162.0, 485.0], [55.0, 485.0]], ('SELANGOR', 0.9964472)]
[[[586.0, 454.0], [697.0, 452.0], [697.0, 466.0], [587.0, 468.0]], ('PEREMPUAN', 0.9980258)]
In [79]:
from paddleocr import PaddleOCR, draw_ocr
# Also switch the language by modifying the lang parameter
ocr = PaddleOCR(lang="en") # The model file will be downloaded automatically when executed for the first time
img_path ='image.jpeg'
result = ocr.ocr(img_path)

# Print detection frame and recognition result
# from PIL import Image, ImageFilter

# #Open existing image
# OriImage = Image.open('image.jpeg')
# # OriImage.show()

# blurImage = OriImage.filter(ImageFilter.BLUR)
# blurImage.show()
#Save blurImage
result = ocr.ocr(img_path)

for line in result:
    print(line)

# Visualization
from PIL import Image
image = Image.open(blurImage).convert('RGB')
boxes = [line[0] for line in result]
txts = [line[1][0] for line in result]
scores = [line[1][1] for line in result]
im_show = draw_ocr(image, boxes, txts, scores, font_path='PaddleOCR-release-2.2/doc/fonts/cyrillic.ttf')
im_show = Image.fromarray(im_show)
im_show.save('img_path.jpg')
im_show.show()

Namespace(benchmark=False, cls_batch_num=6, cls_image_shape='3, 48, 192', cls_model_dir='.paddleocr/2.2.0.2/ocr/cls/ch_ppocr_mobile_v2.0_cls_infer', cls_thresh=0.9, cpu_threads=10, det=True, det_algorithm='DB', det_db_box_thresh=0.6, det_db_score_mode='fast', det_db_thresh=0.3, det_db_unclip_ratio=1.5, det_east_cover_thresh=0.1, det_east_nms_thresh=0.2, det_east_score_thresh=0.8, det_limit_side_len=960, det_limit_type='max', det_model_dir='.paddleocr/2.2.0.2/ocr/det/en/en_ppocr_mobile_v2.0_det_infer', det_sast_nms_thresh=0.2, det_sast_polygon=False, det_sast_score_thresh=0.5, drop_score=0.5, e2e_algorithm='PGNet', e2e_char_dict_path='./ppocr/utils/ic15_dict.txt', e2e_limit_side_len=768, e2e_limit_type='max', e2e_model_dir=None, e2e_pgnet_mode='fast', e2e_pgnet_polygon=True, e2e_pgnet_score_thresh=0.5, e2e_pgnet_valid_set='totaltext', enable_mkldnn=False, gpu_mem=500, help='==SUPPRESS==', image_dir=None, ir_optim=True, label_list=['0', '180'], lang='en', layout_path_model='lp://PubLayNet/ppyolov2_r50vd_dcn_365e_publaynet/config', max_batch_size=10, max_text_length=25, min_subgraph_size=10, output='./output/table', precision='fp32', process_id=0, rec=True, rec_algorithm='CRNN', rec_batch_num=6, rec_char_dict_path='.local/lib/python3.6/site-packages/paddleocr/ppocr/utils/en_dict.txt', rec_char_type='ch', rec_image_shape='3, 32, 320', rec_model_dir='.paddleocr/2.2.0.2/ocr/rec/en/en_number_mobile_v2.0_rec_infer', save_log_path='./log_output/', show_log=True, table_char_dict_path=None, table_char_type='en', table_max_len=488, table_model_dir=None, total_process_num=1, type='ocr', use_angle_cls=False, use_dilation=False, use_gpu=True, use_mp=False, use_pdserving=False, use_space_char=True, use_tensorrt=False, vis_font_path='./doc/fonts/simfang.ttf', warmup=True)
[2021/08/13 19:23:56] root WARNING: Since the angle classifier is not initialized, the angle classifier will not be uesd during the forward process
[2021/08/13 19:23:57] root DEBUG: dt_boxes num : 10, elapse : 0.32827091217041016
[2021/08/13 19:23:57] root DEBUG: rec_res num  : 10, elapse : 0.12045407295227051
[2021/08/13 19:23:57] root WARNING: Since the angle classifier is not initialized, the angle classifier will not be uesd during the forward process
[2021/08/13 19:23:57] root DEBUG: dt_boxes num : 10, elapse : 0.34050536155700684
[2021/08/13 19:23:57] root DEBUG: rec_res num  : 10, elapse : 0.16071629524230957
[[[104.0, 93.0], [256.0, 103.0], [254.0, 134.0], [102.0, 124.0]], ('MALA', 0.98211896)]
[[[66.0, 161.0], [265.0, 157.0], [266.0, 181.0], [66.0, 184.0]], ('00418-00-6418', 0.9912834)]
[[[60.0, 360.0], [152.0, 360.0], [152.0, 378.0], [60.0, 378.0]], ('BINTLAR', 0.9820388)]
[[[158.0, 364.0], [200.0, 364.0], [200.0, 378.0], [158.0, 378.0]], ('RN', 0.8610319)]
[[[56.0, 403.0], [140.0, 406.0], [139.0, 427.0], [55.0, 424.0]], ('LOT2272', 0.99408233)]
[[[54.0, 429.0], [265.0, 427.0], [266.0, 455.0], [54.0, 457.0]], ('4B400PETALING JAYA', 0.9694132)]
[[[521.0, 438.0], [663.0, 436.0], [663.0, 450.0], [521.0, 452.0]], ('WARGANEGARA', 0.9971807)]
[[[55.0, 461.0], [162.0, 461.0], [162.0, 485.0], [55.0, 485.0]], ('SELANGOR', 0.9964472)]
[[[586.0, 454.0], [697.0, 452.0], [697.0, 466.0], [587.0, 468.0]], ('PEREMPUAN', 0.9980258)]

---------------------------------------------------------------------------
AttributeError                            Traceback (most recent call last)
<ipython-input-79-f33617dd18df> in <module>
     22 # Visualization
     23 from PIL import Image
---> 24 image = Image.open(blurImage).convert('RGB')
     25 boxes = [line[0] for line in result]
     26 txts = [line[1][0] for line in result]

~/.local/lib/python3.6/site-packages/PIL/Image.py in open(fp, mode, formats)
   2975         exclusive_fp = True
   2976 
-> 2977     prefix = fp.read(16)
   2978 
   2979     preinit()

~/.local/lib/python3.6/site-packages/PIL/Image.py in __getattr__(self, name)
    544             )
    545             return self._category
--> 546         raise AttributeError(name)
    547 
    548     @property

AttributeError: read
Conclusion - We have extracted an image file into machine readable format.
By employing OCR technology , businesses can:
  1. Accelerate and Automate Processes
  2. Reduce Costs
  3. Improve service

Search Article

Resources You Will Ever Need

Popular Searches