Blog

Joseph Nelson

Roboflow cofounder and CEO. On a mission to transform every industry by democratizing computer vision. Previously founded and sold a machine learning company.

Latest Posts by Joseph Nelson

Training a TensorFlow Faster R-CNN Object Detection Model on a Custom Dataset

11 Mar 2020 • 9 min read

Training a TensorFlow Faster R-CNN Object Detection Model on a Custom Dataset

SUMMARY This tutorial trains a TensorFlow Faster R-CNN object detection model on the Blood Cell Count and Detection (BCCD) dataset, a 364-image microscopy set with 4,888 labels across red blood cells, white blood cells, and platelets. It covers preparing images and annotations with Roboflow, generating TFRecords and

Why to Add Noise to Images for Machine Learning

9 Mar 2020 • 3 min read

Why to Add Noise to Images for Machine Learning

Learn why adding noise can be effective as an image augmentation in computer vision modeling.

types

27 Feb 2020 • 4 min read

How to Select the Right Computer Vision Model Architecture

SUMMARY Choosing a computer vision model architecture for object detection involves trading off speed, accuracy, and deployment constraints. This post compares three architectures: YOLOv3, a single-shot detector optimized for speed at 60+ FPS with lower accuracy; MobileNet SSD, a single-shot detector slightly slower than YOLOv3 but stronger on

Introducing an Improved PlantDoc Dataset for Plant Disease Object Detection

25 Feb 2020 • 4 min read

Introducing an Improved PlantDoc Dataset for Plant Disease Object Detection

SUMMARY PlantDoc is a public dataset of 2,598 images spanning 13 plant species and 27 classes (17 disease, 10 healthy), created by researchers at the Indian Institute of Technology for plant disease classification and object detection. Roboflow has hosted an improved version on Roboflow Universe with corrected annotations: over

Why and How to Implement Random Crop Data Augmentation

21 Feb 2020 • 5 min read

Why and How to Implement Random Crop Data Augmentation

Learn how to apply a random crop data augmentation to images for use in training computer vision models.

Releasing an Improved Blood Count and Cell Detection (BCCD) Dataset

14 Feb 2020 • 2 min read

Releasing an Improved Blood Count and Cell Detection (BCCD) Dataset

SUMMARY The Blood Count and Cell Detection (BCCD) dataset, a widely used object detection benchmark with 364 microscope images across three classes (WBC, RBC, and Platelets), had significant annotation gaps in its original release. The Roboflow team reviewed each image and added 187 missing labels, 183 of them red blood

boilerplate

12 Feb 2020 • 4 min read

Eliminating Boilerplate Code with Roboflow to Monitor Security Camera Footage

SUMMARY Data scientist Alaa Senjab built a real-time gun detection model for security camera footage using a 2,973-image handgun dataset from the University of Grenada, and reported that Roboflow cut roughly half of his project code by handling annotation validation, preprocessing, augmentation, and format conversion automatically. Roboflow

Training a TensorFlow MobileNet Object Detection Model with a Custom Dataset

9 Feb 2020 • 7 min read

Training a TensorFlow MobileNet Object Detection Model with a Custom Dataset

Change two lines of code and have a custom trained object detection model leveraging the TensorFlow 1.5 API.

public

27 Jan 2020 • 2 min read

Introducing Public Datasets

SUMMARY Getting access to clean, labeled data is one of the hardest parts of starting a computer vision project. Roboflow Public Datasets (public.roboflow.com) addresses this by hosting free, downloadable datasets covering domains from board games to aerial drone imagery, each available in formats including VOC XML, COCO JSON,

Training a YOLOv3 Object Detection Model with a Custom Dataset

9 Jan 2020 • 11 min read

Training a YOLOv3 Object Detection Model with a Custom Dataset

A walkthrough of building chess piece object detection model, easily adapted to your own dataset.

Stay Connected

Get the Latest in Computer Vision First