[vc_row row_type=”3″ blox_image=”21489″ align_center=”aligncenter” page_title=”page-title-x” blox_dark=”true” parallax_speed=”8″][vc_column]

---

---

[vc_column_text]

Georgian OCR (Open source project)

[/vc_column_text]

---

---

[/vc_column][/vc_row][vc_row][vc_column width=”1/4″]

---

---

[/vc_column][vc_column width=”1/2″]

---

[vc_column_text]A Startup Company[/vc_column_text]

---

[/vc_column][vc_column width=”1/4″][/vc_column][/vc_row][vc_row][vc_column width=”1/3″][vc_single_image image=”21490″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21491″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21492″ img_size=”550×350″][/vc_column][/vc_row][vc_row][vc_column]

---

[vc_column_text]

About this project

[/vc_column_text][vc_row_inner][vc_column_inner width=”1/2″][vc_column_text]Project Description

We have created Georgian OCR as an open-source project. Our model was trained on more than one million samples of synthetic datasets from the Georgian alphabet. We used computer vision algorithms for character segmentation and assembling scanned documents back.

Source Code:

https://github.com/m-learning/georgian-ocr-v2

[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/2″][vc_column_text]Technologies:

• Convolutional neural networks with Keras and Tensorflow.
• OpenCV for pre-processing and post-processing.

[/vc_column_text][/vc_column_inner][/vc_row_inner]

---

[/vc_column][/vc_row]