---
license: gpl-3.0
tags:
- ultralytics
- yolo
- object-detection
- ui-detection
- computer-vision
- agent
---

# deki-yolo: Mobile UI Element Detection Model

This is a YOLO model trained to identify common UI elements in mobile
screenshots. It is the core detection model for the [deki huggingface space](https://huggingface.co/spaces/orasul/deki) 
or [deki github](https://github.com/RasulOs/deki)

## Model Description

The model is trained to detect the following four classes of UI elements:
*   `View`: General-purpose containers.
*   `ImageView`: Icons and images.
*   `Text`: Text elements.
*   `Line`: Separators and lines.

This model can be used as a foundational component for applications that need
to understand screen layouts, such as AI agents for mobile automation,
accessibility tools, and UI code generation.

---

## YOLO examples

Bounding boxes with classes for bb_1:

<img src="./res/bb_1_yolo.jpeg" alt="example1" width="60%">

Bounding boxes with classes for bb_2:

<img src="./res/bb_2_yolo.jpeg" alt="example2" width="60%">

---

## YOLO model accuracy

The model was trained on 486 images and was tested on 60 images.

Current YOLO model accuracy:
![example3](./res/YOLO_accuracy.png)