Sold by: NavInfo Europe B.V.
Deployed on AWS
Free Trial
Detection and blurring of faces and license plates.
4.3
Overview
NavInfo Europe's face and license plate anonymizer detects and blurs recognisable faces and license plates in images. The blurring of faces and license plates helps to reach global privacy standards. The models are trained using images taken from a dashcam. For any specific solution, contact us to create a model to solve your needs
The average precision, average recall and F1-score for License Plates are 98.5, 99.42 and 98.96 respectively when testing on public datasets (CCPD). For faces these are 95.59, 98.05 and 96.80 respectively (IJB-C). Training set that was used was created by Navinfo Europe.
Highlights
- NavInfo Europe Face and License Plate Anonymizer can use a number of different models for detecting license plates and faces. All models that were used are available under MIT license or Apache License. The models were trained using a dedicated training set that was developed by Navinfo Europe. Images in this dataset were created by Navinfo Europe or used under license. Latency metrics: measured on g4dn.xl : 41fps measured on g4dn.12xl : 77fps
- The models and the training data for this pipeline can be used commercially.
- Navinfo Europe has created these models using more than 5 years of experience in the area of machine learning and AI.
Details
Sold by
Delivery method
Latest version
Deployed on AWS
New
Introducing multi-product solutions
You can now purchase comprehensive solutions tailored to use cases and industries.
Features and programs
Financing for AWS Marketplace purchases
AWS Marketplace now accepts line of credit payments through the PNC Vendor Finance program. This program is available to select AWS customers in the US, excluding NV, NC, ND, TN, & VT.
Pricing
Free trial
Try this product free for 5 days according to the free trial terms set by the vendor.
Pricing is based on actual usage, with charges varying according to how much you consume. Subscriptions have no end date and may be canceled any time.
Additional AWS infrastructure costs may apply. Use the AWS Pricing Calculator to estimate your infrastructure costs.
Dimension | Description | Cost/host/hour |
|---|---|---|
ml.p3.2xlarge Inference (Batch) Recommended | Model inference on the ml.p3.2xlarge instance type, batch mode | $0.50 |
ml.g4dn.xlarge Inference (Real-Time) Recommended | Model inference on the ml.g4dn.xlarge instance type, real-time mode | $0.50 |
ml.p2.xlarge Inference (Batch) | Model inference on the ml.p2.xlarge instance type, batch mode | $0.50 |
ml.p3.8xlarge Inference (Batch) | Model inference on the ml.p3.8xlarge instance type, batch mode | $0.50 |
ml.p2.8xlarge Inference (Batch) | Model inference on the ml.p2.8xlarge instance type, batch mode | $0.50 |
ml.p2.16xlarge Inference (Batch) | Model inference on the ml.p2.16xlarge instance type, batch mode | $0.50 |
ml.p3.16xlarge Inference (Batch) | Model inference on the ml.p3.16xlarge instance type, batch mode | $0.50 |
ml.p2.xlarge Inference (Real-Time) | Model inference on the ml.p2.xlarge instance type, real-time mode | $0.50 |
ml.g4dn.4xlarge Inference (Real-Time) | Model inference on the ml.g4dn.4xlarge instance type, real-time mode | $0.50 |
ml.m5.4xlarge Inference (Real-Time) | Model inference on the ml.m5.4xlarge instance type, real-time mode | $0.50 |
Dimensions summary
You pay by the hour for the compute instance running the anonymization model, which blurs faces and license plates in your images. Pricing splits into two modes: batch inference for processing stored datasets, and real-time inference for on-demand requests. Within each mode, you choose an AWS machine learning instance type. Larger or GPU-backed instances carry higher hourly rates, so cost scales with the compute power you select. Batch mode covers several instance sizes, while real-time mode offers a wider range, including GPU and general-purpose types. You are billed only for the host hours you use.
Top-of-mind questions for buyers
One HostHrs unit is one hour that a single compute instance runs the anonymization model. You are billed per active host hour on the instance type you select. The count reflects running time, not the number of images processed or files uploaded.
Batch inference meters host hours while processing stored datasets in bulk. Real-time inference meters host hours while the instance stays available to answer on-demand requests. Both bill per host hour, but real-time accrues time whenever the endpoint runs, even between requests.
Yes. Each instance type carries its own hourly rate. GPU-backed instances and larger sizes cost more per host hour than general-purpose or smaller types. Your bill scales with the compute power of the instance you choose, multiplied by the hours it runs.
navinfo.eu
Helpful?
Vendor refund policy
Currently we do not support refunds, but you can cancel your subscription to this service at any time.
Legal
Vendor terms and conditions
Upon subscribing to this product, you must acknowledge and agree to the terms and conditions outlined in the vendor's End User License Agreement (EULA) .
Content disclaimer
Vendors are responsible for their product descriptions and other product content. AWS does not warrant that vendors' product descriptions or other product content are accurate, complete, reliable, current, or error-free.
Delivery details
Amazon SageMaker model
An Amazon SageMaker model package is a pre-trained machine learning model ready to use without additional training. Use the model package to create a model on Amazon SageMaker for real-time inference or batch processing. Amazon SageMaker is a fully managed platform for building, training, and deploying machine learning models at scale.
Deploy the model on Amazon SageMaker AI using the following options:
Version release notes
This solution is based on the Nanodet and HardNet68 models which have been improved by Navinfo Europe B.V. Other variations also exist (Yolo, SSD, …) and are available on request.
Additional details
Inputs
- Summary
Upload the images you want to anonymize by blurring, we support the most common formats.
- Limitations for input type
- Each image should not exceed 5 MB. Maximum image resolution: 4096 x 2048.
- Input MIME type
- image/jpeg, image/png, image/x-ms-bmp, image/x-portable-pixmap, image/x-portable-anymap, image/tiff, image/jp2
https://github.com/Navinfo-Europe/anonymizer/tree/main/data/input/new
https://github.com/Navinfo-Europe/anonymizer/tree/main/data/input/new
Resources
Vendor resources
Support
Vendor support
Navinfo Europe provides support upon request by the customer. Please contact our support engineers or sales representatives using the following e-mail address: awssupport@navinfo.eu
AWS infrastructure support
AWS Support is a one-on-one, fast-response support channel that is staffed 24x7x365 with experienced and technical support engineers. The service helps customers of all sizes and technical abilities to successfully utilize the products and features provided by Amazon Web Services.
Similar products
The BlurIt On-Premise solution offers businesses the ability to deploy the BlurIt service directly on their own infrastructure with an AWS AMI image. This solution provides full control over data processing, and includes a web manager for file uploads, zip archive support for batch processing, and S3 compatibility, ensuring complete autonomy and security.
To protect individuals’ privacy, personal identifiable information (PII) has to be removed for the from the recorded data in many countries e.g. General Data Protection Regulation (GDPR) specifies the rules for anonymization in Europe. For the tra...
Hugging Face Neuron Deep Learning AMI (DLAMI) makes it easy to use Amazon EC2 Inferentia & Trainium instances for training and inference of Hugging Face Transformers and Diffusers models, offering up to 50% cost-to-train savings over comparable GPU-based DLAMIs.
The Hugging Face Hub is the leading open platform for AI builders.
This model blurs the faces of people in an image to preserve privacy
Consulting service with access to leading experts in ML to support your AWS projects
This product has charges associated with it for pre-configuration by Intuz Inc. This AMI comes with Hugging Face Transformers, Jupyter Notebook, and popular NLP models like GPT, BERT, and T5-ready to use for machine learning and natural language processing tasks.
Customer reviews
Ritik R.
Anonymizer helps in Maintaining Privacy
Reviewed on Jun 01, 2023
Review provided by G2
What do you like best about the product?
Anonymizer helps to maintain the privacy of the people in the videos I use.
What do you dislike about the product?
It's a little slow for me sometimes, but overall it's good.
What problems is the product solving and how is that benefiting you?
It is helping me creating videos with exploiting anyone's data.
Nadeem P.
Face and License plate anonymizer review
Reviewed on Apr 06, 2023
Review provided by G2
What do you like best about the product?
The best thing about Face and License plate Anonymizer is data privacy.
What do you dislike about the product?
I didn't find personally any fact that makes Face and License plate anonymizer to dislike.
What problems is the product solving and how is that benefiting you?
For building a multi model.