Research · Technology · 25 September 2026
By Elena Setaro
Dermaself is advancing its AI skin analysis technology through a research collaboration with Alta Scuola Politecnica, the joint honours programme of Politecnico di Milano and Politecnico di Torino. The project explores two complementary technologies designed to further enhance selfie-based AI skin analysis: image normalisation and 3D-based facial anonymisation
The collaboration was also covered by Cosmetics Business, which explored the project’s work on image normalisation and 3D-based facial anonymisation.
A smartphone selfie contains two different layers of information: visible characteristics of the skin and biometric features that can identify the person in the image.
The research explores how these two layers can be treated independently, allowing skin information to remain valuable for analysis while identity is protected through dedicated privacy-preserving technologies.
Dermaself and Alta Scuola Politecnica are exploring image normalisation and 3D-based facial anonymisation technologies designed to expand the capabilities of selfie-based AI skin analysis.
The research brings together expertise in computer vision, image processing and privacy with Dermaself’s experience in applied AI skin analysis.
The project was developed by five master’s students from Alta Scuola Politecnica, working directly with Dermaself to explore how advanced academic research can be translated into technologies with real-world applications in beauty tech.
Images captured with smartphones can vary depending on lighting, exposure, camera processing and the environment in which the selfie is taken. Image normalisation can create increasingly standardised inputs for AI skin analysis across different devices and contexts.
The research explores an additional image-processing layer designed to compensate for variations that naturally occur when users take selfies in real-world conditions.
During image acquisition, users can be guided towards suitable capture conditions. After capture, additional image processing can further compensate for variations in illumination.
The result is a more standardised representation of the image, designed to make selfies captured across different devices and environments increasingly comparable.
For Dermaself, this technology can complement its existing AI skin analysis ecosystem across multiple customer touchpoints.
Dermaself is exploring a privacy-preserving approach designed to separate identity-bearing facial information from the visual skin information required for skin assessment.
A facial image contains both biometric information and detailed visual characteristics of the skin. Conventional anonymisation methods such as masking or blurring can reduce identifiable information, but may also remove valuable visual skin information.
The research developed with Alta Scuola Politecnica therefore explores a different approach based on advanced 3D facial modelling and a proprietary computational framework.
Instead of simply removing or degrading facial information, the technology operates at the structural level of the facial representation, substantially altering its biometric signature while retaining high-fidelity skin characteristics.
The research treats identity and skin as computationally distinct information layers within the same facial image.
Using a proprietary 3D computational framework, identity-bearing facial information can be transformed while preserving visual signals relevant to skin assessment.
These include characteristics such as:
lesions
redness
pigmentation
spots
fine-grained skin texture
This approach introduces a different paradigm for facial anonymisation: protecting identity while preserving the richness of the skin information contained in the image.
The research was developed by a multidisciplinary team of five master’s students from Alta Scuola Politecnica, the joint honours programme of Politecnico di Milano and Politecnico di Torino, in collaboration with Dermaself.
The team included:
Andrea Germano - Computer Engineering, Politecnico di Torino
Adriano Giuliani - Computer Engineering, Politecnico di Torino
Federico Greppi - Biomedical Engineering, Politecnico di Torino
Edoardo Gribaldo - Computer Science and Engineering, Politecnico di Milano
Alessia Soccionovo - Management Engineering, Politecnico di Milano
The project was guided by Professor Elisabetta Raguseo of Politecnico di Torino, Director of Alta Scuola Politecnica, and Professor Federica Arrigoni of Politecnico di Milano.
Working directly with Dermaself, the multidisciplinary team combined academic research with real-world beauty tech applications.
The technologies developed through the Alta Scuola Politecnica project are designed to complement Dermaself’s AI skin analysis ecosystem and expand its technological capabilities.
Dermaself enables beauty brands and retailers to integrate selfie-based skin analysis into digital and physical customer experiences.
From a selfie, Dermaself analyses visible skin characteristics and connects the results with products from a brand’s or retailer’s own catalogue to create personalised skincare recommendations.
The platform can be integrated across:
Within this ecosystem, image normalisation provides an additional layer of standardisation across image-acquisition environments, while facial anonymisation creates new possibilities for privacy-preserving image processing.
Privacy-preserving AI skin analysis can create new opportunities for beauty technology by allowing valuable skin information to be used while placing greater emphasis on protecting the identity of the person represented in the image.
High-quality image datasets are increasingly valuable for organisations developing computer vision and AI technologies for skin analysis.
Facial images are particularly complex because they contain biometric information alongside the visual characteristics being studied.
Separating these layers creates new possibilities for privacy-conscious image datasets that can support research, technology development and AI model improvement.
For Dermaself, this represents another step towards an AI skin analysis ecosystem in which technological performance and privacy evolve together.
The collaboration between Dermaself and Alta Scuola Politecnica demonstrates how academic research can be translated into technologies designed for real-world beauty applications.
By combining Dermaself’s experience in applied AI skin analysis with the research expertise of Alta Scuola Politecnica, Politecnico di Milano and Politecnico di Torino, the project brings together computer vision, image processing, privacy and beauty technology.
The result is an expanding technological ecosystem designed around a simple principle: extracting value from skin information while developing increasingly sophisticated ways to protect facial identity.
Quick answers to common questions
AI skin analysis uses artificial intelligence and computer vision to analyse visible skin characteristics from an image, such as a smartphone selfie. The resulting information can support personalised skincare experiences and product recommendations.
Dermaself’s AI Skin Analysis analyses visible skin characteristics from a selfie and connects the results with product and ingredient information from a brand’s or retailer’s own catalogue. This enables brands to provide personalised skincare recommendations across digital and physical customer touchpoints.
Lighting, exposure and camera processing can influence how skin appears in a photograph. Image normalisation is designed to reduce these variations and create increasingly standardised inputs for computer vision systems, particularly when images are captured across different devices and environments.
Selfie image normalisation is the process of reducing variations in photographs caused by factors such as illumination, exposure and camera processing. The technology developed within the project provides an additional standardisation layer designed to make images captured in different environments increasingly comparable.
The technology developed by the Alta Scuola Politecnica team leverages advanced 3D facial modelling to transform the biometric signature of a face without sacrificing the richness of its skin data.
Through a proprietary computational process, identity-bearing facial information is altered at a structural level, while high-fidelity skin characteristics are preserved for potential clinical and research applications.
A facial image contains both visible information about the skin and biometric characteristics related to a person’s identity. Privacy-preserving image technologies explore ways of retaining useful visual information while reducing identifiable facial characteristics.
The research was developed by a multidisciplinary team of five master’s students from Alta Scuola Politecnica, the joint honours programme of Politecnico di Milano and Politecnico di Torino, in collaboration with Dermaself and under the guidance of academic tutors from both universities.
The anonymisation technology opens potential applications in the creation and management of privacy-preserving image datasets for beauty tech and digital dermatology research.
By separating skin information from facial identity, this approach could support future research, AI development and data-driven applications while placing greater emphasis on the protection of the individuals represented in the images.
Discover how Dermaself can integrate AI skin analysis and product recommendations into your e-commerce, retail, event or beauty experience.
Contact us →Tell us about your brand or project: our team will get back to you by email.
