[vc_row row_type=”3″ blox_image=”21482″ align_center=”aligncenter” page_title=”page-title-x” blox_dark=”true” parallax_speed=”8″][vc_column]

---

---

[vc_column_text]

Create Bitmoji from profile pictures

[/vc_column_text]

---

---

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

---

---

[/vc_column][vc_column width=”1/2″]

---

[vc_column_text]US-based startup building a social networking site. [/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=”21483″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21484″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21485″ 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

The goal of our experiment was to create a solution that generates bitmoji (cartoon avatar) from a face image uploaded by the user. Deep face-scan – extract hair, beard, eyebrows, eyes, nose, lips, face color, and shape, together with different accessories: glasses, earrings, piercings, etc. Based on these features we extract similar shapes and colors from the database using deep content-based image retrieval and assemble the bitmoji.[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/2″][vc_column_text]Technologies:

• OpenCV for classical computer vision routines.
• PyTorch based deep CNN models for face scan (segmentation) and representation (vectorization).
• Faiss for fast shape similarity search.
• Scrapy for data collection.

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

---

[/vc_column][/vc_row]