[vc_row row_type=”3″ blox_image=”21421″ align_center=”aligncenter” page_title=”page-title-x” blox_dark=”true” parallax_speed=”8″][vc_column]

---

---

[vc_column_text]

NSFW content detection in images and video streams

[/vc_column_text]

---

---

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

---

---

[/vc_column][vc_column width=”1/2″]

---

[vc_column_text]Social networking startup based in Silicon Valley had a rapid increase in their number of users and they encountered unwanted problems. Users started reporting NSFW issues in user-generated content that slowed down their growth. They needed to find a solution really fast as they were afraid of a potential ban from different partners.[/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=”21423″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21422″ img_size=”550×350″][/vc_column][vc_column width=”1/3″][vc_single_image image=”21424″ 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

Our client wanted to have a tool that detects nudity in the images uploaded by users on their social networking mobile app. We gave them Neural Network as a solution that achieved high accuracy in detecting nudity in images and videos in real-time. Our client used our model to filter unwanted content from its users. We have used more than 2 million images and 300 hours of video content for creating the model.[/vc_column_text][/vc_column_inner][vc_column_inner width=”1/2″][vc_column_text]Technologies:

• PyTorch to train models.
• Scrapy to collect the dataset.

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

---

[/vc_column][/vc_row]