• 6 min read
Launch: Deploy Florence-2 with Roboflow
Learn how to deploy a Florence-2 model with Roboflow.
• 5 min read
How to Augment Images for Keypoint Detection
Learn how to augment images for use in keypoint detection datasets with Roboflow.
![Top 7 Open Source Object Tracking Tools [2025]](/content/images/size/w640/2024/07/Blog-Image-Template---2024-07-17T151324.948.jpg)
• 8 min read
Top 7 Open Source Object Tracking Tools [2025]
Object tracking is a computer vision task that can identify various objects and track them through the frames of a video.
0:00
/0:05
1×
Knowing where an object is in a video has many real-life applications, especially in manufacturing and logistics. For example, object tracking can be used
• 8 min read
What is the Open Images Dataset? A Deep Dive.
The Open Images Dataset was released by Google in 2016, and it is one of the largest and most diverse collections of labeled images. Since then, Google has regularly updated and improved it. The latest version of the dataset, Open Images V7, was introduced in 2022.
Globally, researchers and developers
• 5 min read
How to Augment Images for Image Classification
Learn how to generate augmented images for use in image classification datasets.
• 5 min read
How to Augment Images for Object Detection
Learn how to generate augmented images for use in object detection datasets.
• 3 min read
Document Understanding with Multimodal Models
Learn how to use the PaliGemma multimodal model to ask questions about the contents of a document.
• 3 min read
Visual Question Answering with Multimodal Models
Learn how to use the PaliGemma multimodal model to ask questions about images.
• 4 min read
Understand Website Screenshots with a Multimodal Vision Model
Learn how to use the Florence-2 multimodal model to generate rich descriptions of website screenshots.
• 4 min read
How to Caption Images with a Multimodal Vision Model
Learn how to caption images using a multimodal vision model.
• 11 min read
How to Train RT-DETR on a Custom Dataset with Transformers
RT-DETR, short for "Real-Time DEtection TRansformer", is a computer vision model developed by Peking University and Baidu. In their paper, "DETRs Beat YOLOs on Real-time Object Detection" the authors claim that RT-DETR can outperform YOLO models in object detection, both in speed and accuracy. The model
• 12 min read
Build Computer Vision Applications with Roboflow and Gradio
Learn how to build computer vision applications with Roboflow and Gradio.
• 16 min read
What is Thresholding in Image Processing? A Guide.
Learn what image thresholding is and the thresholding strategies you can use in computer vision applications.
![The Guide to AI OCR [2025]](/content/images/size/w640/2024/07/Copy-of-Blog-Image-Template.png)
• 6 min read
The Guide to AI OCR [2025]
Learn what AI OCR is and how it is used in computer vision.
• 5 min read
How to Use Florence-2 for Optical Character Recognition
Learn how to use the Florence-2 model for Optical Character Recognition tasks.
• 4 min read
What is Dense Image Captioning?
Learn what dense image captioning is and how to use the MIT-licensed Florence-2 model to generate dense image captions.
• 5 min read
What is FPS? A Computer Vision Guide.
Learn what FPS is and what FPS considerations you should keep in mind when working on computer vision projects.
• 7 min read
What is 4M? Apple's Massively Multimodal Masked Modeling
4M: Massively Multimodal Masked Modeling, released by Apple in 2024, is a leap forward in the field of multimodal machine learning. This model, building upon the growing capabilities of large language models, addresses critical challenges in vision models which have traditionally been highly specialized and limited to a single modality
• 5 min read
How to use Florence-2 for Instance Segmentation
Florence-2 is a lightweight model licensed under the MIT license. Although it has significantly fewer parameters than competing models like LLaVA 1.5, Florence-2 remains state-of-the-art due to the high-quality data it was trained on.
Florence-2 is capable of a variety of tasks, including visual question answering, captioning, image detection,
• 5 min read
How to Use GPT-4 To Extract Handwritten Text from Images
This guide walks you through the process of building, training, and deploying a custom computer vision workflow using OpenAI and Roboflow. The process is broken down into three steps:
* Building the model
* Connecting the model to a Workflow
* Writing code to get the outputs
0:00
/0:07
1×
Through
• 4 min read
Computer Vision Solutions for Steel Manufacturing with Roboflow
Learn how computer vision can be used in steel manufacturing facilities.
• 19 min read
How to Monitor Productivity with Eye Tracking
Focusing is hard. In recent years, the amount of distractions available to us has been increasing, and we often lose track of how much we are distracted.
To help myself stay engaged, I created a project that accurately tracks how many times I'm distracted in a certain period
• 2 min read
Launch: Roboflow Project Folders
Learn how to use Roboflow's Project Folders to organize projects in your account workspaces.
• 4 min read
How to Set Up a Basler Camera on a Jetson
Learn how to set up a Basler camera on an NVIDIA Jetson for use in running computer vision models.
Stay Connected