Face & license plate anonymization: all you need to know before choosing the right solution for your business
How to choose the right software solution for image and video blurring
You’re considering including an anonymizer tool for faces and license plates. You are not sure if it makes sense to build a solution in-house, do it manually, outsource it, or, more simply, don’t do it at all. Or even purchasing a software solution for this process.
You aren’t sure you have the time, budget, or capacity to figure out yet another tool that’s supposed to help your company succeed.
To answer these questions and help you choose the right solution for your business, we’ve put together this guide. Here, you’ll learn about the benefits and implications of each option.
What does Image and Video Anonymization mean?
Anonymization is the process of removing personal from images and videos, to protect people's privacy.
For data to be truly anonymized, the anonymization must be irreversible. This means that it should not be possible to retrieve the original data.
Benefits of Image & Video Anonymization
Anonymized data is not subjected to the major data protection laws. Therefore, anonymization preserves privacy while drastically reducing operational costs. It can free your company from a series of duties (data subject consent, data transfer limitations, etc).
Data breaches (from outside) and leaks (from inside)are a constant threat. As proved in the past, even the highest cybersecurity measures might not prevent data leaks, with disastrous consequences when personal data is involved. While anonymization cannot prevent such events, you can however reduce the risk of exposing sensitive data.
Image and Video Anonymization Methods
There are different possibilities to perform image and video anonymization:
- In-house semi-automated/automated solution
- External software solution
Manual anonymization means that people manually check whether personal data (e.g. people, vehicles, etc.) are present. By using an image manipulation tool (e.g. Photoshop), they’ll apply a filter on these objects.
Such a solution is very time-consuming (especially with large amounts of data or multiple objects). Consequently, it can become costly - for instance, the average hourly rate in e.g. Austria is more than EUR 36.7 per hour.
To avoid such high labor costs, companies could outsource this process to lower-wage countries. However, the GDPR enforces strict rules when it comes to data transfers outside the EU. In general, a transfer is only possible in countries where an ‘Adequacy Decision’ was granted (Andorra, Argentina, Canada, Faroe Islands, Guernsey, Israel, Isle of Man, Japan, Jersey, New Zealand, Republic of Korea, Switzerland , the United Kingdom, and Uruguay).
In the absence of an Adequacy Decision, a series of legal, contractual and security limitations apply. In addition, it could expose a company to higher risks of data breaches during these transfers (via the cloud or physical storage).
Furthermore, manual labor is not scalable for large volumes of data. For example, we estimate that a person could anonymize ca. 600-700 images per hour. For a dataset of 1 million images, it would take between 178 and 208 days (8 hours/working day). In comparison, a cloud-based solution would anonymize between 5,000-10,000 images per hour at the same costs of an outsourcing company in lower-income countries.
In-house semi-automated/automated solution
To build an anonymization solution that meets regulatory requirements, you will need to utilize human resources from Software Development (Productive hourly rate - EUR 55) and Machine Learning (Productive hourly rate - EUR 70).
Once that is established, the following tasks need to be considered and done:
- Data strategy, (data acquisition, labeling, etc)
- Machine learning (training, testing, model optimization, etc)
- Requirement engineering
- Software development (backend, user interface)
- Bug fixing
- Maintenance and Support
With that being said, we estimate that it can cost ca. EUR 66,000 worth of software developers and ML engineers work. Even then, there is no guarantee of achieving acceptable quality, speed, and computation efficiency, as well as the need to invest resources in maintaining and improving the model.
For these reasons, the cost of developing such a solution in-house is not worth the effort, as it requires financial and human resources and therefore distracts the company from its core business.
What I should consider for choosing an Image & Video Anonymization Solution
Quality of anonymization
Two important factors determine the quality: false negative, i.e. an object is not detected, and false positive, i.e. the background or an irrelevant object is wrongly marked as a relevant object. For anonymization, a false negative is in most cases more severe than a false positive: not detecting an identifiable person poses a larger problem than, say, mistaking a construction container for a car. However, depending on the use case, blurring a traffic sign because it is falsely identified as a number plate can be equally problematic.
What needs to be anonymized?
In principle, you should remove all personal data. The level of acceptable anonymization depends on the context. In most cases, only faces and number plates are required for anonymization. In other cases, it might be necessary to anonymize other objects (e.g. persons, text, etc).
Data protection and security due diligence
If you or your customer is an EU-based company, they should have up-to-date documentation such as:
- Technical and organizational measures (TOM)
- Records of Processing Activities
- Dedicated Data Protection Officer (DPO)
- GDPR-compliant data centers
- Data encryption
On-premises software (e.g. Docker container) is installed and runs on the local computer or cloud infrastructure (public or private) of the person or organization using the software. This is often considered the preferred option for enterprises because it solves several internal security issues. In fact, for the local machine and private cloud deployments, no data is transferred to third parties, as well as overcoming the internet throughput bottleneck.
Reversely, hardware and knowledge requirements can represent an obstacle, especially for small-medium enterprises or companies that process a limited number of images/videos that do not justify
Embedded software is a specialized solution for the particular hardware that it runs on and has time and memory constraints. From a speed and security standpoint, embedded anonymization software is the ideal option, because the non-transfer of data to a different data storage reduces significantly data breach risks and throughput.
On the other hand, such software works by nature only for particular hardware. Hence, it is not a scalable solution if you use multiple camera suppliers. In addition to that, embedded development could be more complex and expensive than classical software development.
How Celantur can help you
Starting with anonymization and choosing the best option for your business might be complex. But, we are here to help you with this.
Celantur offers a fully-automated anonymization solution for images & videos. Our technology automatically blurs faces, license plates, persons, and vehicles:
- We offer a cloud-based SaaS solution, container deployable on your local machine or own cloud infrastructure (public or private). Embedded options might be available as a custom project.
- Industry-grade anonymization quality with a detection rate up to 99%.
To make sure that you have the right legal basis within your company and related partners, we ensure the highest data protection measures. Take a look at all our data protection measurements here.
Ask us anything. We'll get back to you shortly