Introduction

NeuralMarker offers a variety of Pretrained Deep Learning Models for Optical Character Recognition (OCR) from different available frameworks like TensorFlow and PyTorch.

This list of models at hand is not static, as more models in the Neural Network Library of NeuralMarker will be added, then accordingly the below list will be updated too:

Pretrained Models

1. EAST-Text-Detector

2. CRAFT

3. EasyOCR-Telugu

4. EasyOCR-Azerbaijani

5. EasyOCR-Croatian

6. EasyOCR-Estonian

7. EasyOCR-Turkish

8. EasyOCR-Chinese

9. EasyOCR-Maithili

10. EasyOCR-Slovenian

11. EasyOCR-Swedish

12. EasyOCR-Afrikaans

13. EasyOCR-Marathi

14. EasyOCR-Maltese

15. EasyOCR-Bhojpuri

16. EasyOCR-Occitan

17. EasyOCR-Ingush

18. EasyOCR-Goan

19. EasyOCR-Irish

20. EasyOCR-Norwegian

21. EasyOCR-Portuguese

22. EasyOCR-Kannada

23. EasyOCR-Maori

24. EasyOCR-Serbian_cyr

25. EasyOCR-Icelandic

26. EasyOCR-Tamil

27. EasyOCR-Arabic

28. EasyOCR-Uyghur_ar

29. EasyOCR-Mongolian

30. EasyOCR-Uyghur_cyr

31. EasyOCR-Lithuanian

32. EasyOCR-Dutch

33. EasyOCR-Danish

34. EasyOCR-Malay_lat

35. EasyOCR-Belarusian

36. EasyOCR-Urdu

37. EasyOCR-Hindi

38. EasyOCR-Kurdish

39. EasyOCR-Vietnamese

40. EasyOCR-Slovak

41. EasyOCR-French

42. EasyOCR-Russian

43. EasyOCR-Kabardian

44. EasyOCR-Chechen

45. EasyOCR-Hungarian

46. EasyOCR-Romanian_lat

47. EasyOCR-Indonesian

48. EasyOCR-Nagpuri

49. EasyOCR-Polish

50. EasyOCR-Newari

51. EasyOCR-Magahi

52. EasyOCR-Chinese_Simplified

53. EasyOCR-German

54. EasyOCR-Czech

55. EasyOCR-Adyghe

56. EasyOCR-Persian

57. EasyOCR-Albanian

58. EasyOCR-Spanish

59. EasyOCR-Serbian_lat

60. EasyOCR-Korean

61. EasyOCR-Welsh

62. EasyOCR-Lak

63. EasyOCR-Assamese

64. EasyOCR-Bulgarian

65. EasyOCR-Angika

66. EasyOCR-Italian

67. EasyOCR-Avar

68. EasyOCR-Dargwa

69. EasyOCR-Ukranian

70. EasyOCR-Latin

71. EasyOCR-Swahili_lat

72. EasyOCR-Japanese

73. EasyOCR-Lezgi

74. EasyOCR-Uzbek

75. EasyOCR-Bengali

76. EasyOCR-Tabarassan

77. EasyOCR-Nepali

78. EasyOCR-Bosnian

79. EasyOCR-Latvian

80. EasyOCR-Tagalog

81. EasyOCR-Thai

82. EasyOCR-Abaza

83. EasyOCR-English

84. East Tesseract

85. PMTD_ICDAR2015

86. PMTDICDAR2017MLT

87. Box_DN_ImageNet

How to create Annotations on an OCR Dataset with Pre-Trained Models

Steps to Follow

1. Login to the tool

2. Click on the Add button.

3. The Add Dataset Form will appear.

4. Fill in all the fields such as dataset name, dataset description, category-type, and categories.

4 a. Select category-type as OCR

4 b. Choose Pretrained Model from the available list.

4 c. Categories as "text_box" will appear for either of the Model.

5. Add data to NeuralMarker using the available options listed below:

Google Drive Link or S3 link
CSV File with Image URL's
Drag and Drop

To Learn More, Click Here.

6. Click on Submit Button

7. A New Dataset will be created.

8. After New Dataset is created:

The Dataset card will display the status "Pretrain Model running".
The brain symbol on hover will display "AI labeling in Progress".

9. After Pretrain Model stops running over the entire dataset:

The Dataset card will display the status "Pretrain Model done & ready for annotation".
The brain symbol on the card will display "AI labeling report".