Kestrel Vision | Tiama: From initial development to a strategic roadmap

Discover how Tiama and Neovision are revolutionizing hollow glass inspection. Using Deep Learning, they achieve zero-defect standards for pharma and cosmetics

Computer Vision · Deep Learning · Industrie

bioMérieux | Uropathogens detection with AI

Neovision and bioMérieux facilitate the detection of uropathogens, a crucial societal issue in the fight against antibiotic resistance.

Computer Vision · Deep Learning · Machine learning · Santé

STMicroelectronics

Detection of defects on silicon wafers

STMicroelectronics is a global leader in the production of semiconductors used in various sectors such as automotive, industry, Internet of Things and communication infrastructure. The manufacturing process requires highly technological facilities, such as automated clean rooms, to prevent contamination of electronic chips. To guarantee the quality of the products, the human presence in these factories is limited to the maximum.

Cloud · Computer Vision · Deep Learning · Industrie

MICHELIN

Optimization of end-of-life tire diagnostics

When a tyre is at the end of its life, it is sent to a handling center. Depending on the characteristics of the tyre, it may or may not be retreaded. The procedures are very precise and the diagnosis must be perfectly objective.

Cloud · Computer Vision · Deep Learning · Industrie

Preoperative planning – orthopedic surgery

Preoperative Planning in Orthopedic Surgery: Discover our innovative project of preoperative planning assistance for orthopedic surgery based on machine learning and deep learning. Explore how our solution provides medical professionals with surgical assistance, including the type of operation, prosthesis selection, and implant placement.

Computer Vision · Deep Learning · Imagerie 3D · R&D · Santé

Lain Pharma, Emball’ISO

Packaging optimization based on thermal parameters

Discover the technology developed for Lain Pharma and Emball'ISO, two innovative players in the thermal supply chain industry.

Analyse prédictive · Deep Learning · Pharma

TEXTIL’IA

Textile scanning, search, and identification of patterns

Counterfeit Detection: Discover our innovative project for textile pattern counterfeit detection based on machine learning and deep learning. Explore how our solution enables simple comparison of textile patterns and detects counterfeit instances.

Cloud · Computer Vision · Deep Learning · Industrie

MODJAW

Dental diagnostic assistance and aligners generation

Dental Diagnostic Assistance and Custom Aligner Generation: Introducing our innovative project for custom dental aligner generation based on machine learning and deep learning. Discover how our solution enables medical professionals to create prosthetics that take into account patients' anatomical characteristics.

Computer Vision · Deep Learning · Imagerie 3D · Machine learning · R&D · Santé

PARKIZE, MBACITY

Optimized parking plan generation

Génération de plan de parking optimisés : Découvrez notre projet innovant de génération de plan de parking optimisé basé sur l'apprentissage automatique et profond. Explorez comment notre solution permet de proposer aux architectes des solutions optimisées tout en garantissant le respect des normes en vigueur.

Generative design · Machine learning · R&D · Recherche opérationnelle · Smart Cities

WRIGHT MEDICAL

Surgical planning assistance

Orthopedic Surgery Optimization: Discover our innovative project of preoperative planning based on machine learning and deep learning. Explore how our solution guides surgeons in their technical choices, providing personalized recommendations for interventions, prostheses, and optimal implantation.

Computer Vision · Deep Learning · Imagerie 3D · Machine learning · R&D · Santé

LOVIS

Dental pre-diagnosis and formalization of reports

Neovision designed and developed an artificial intelligence solution able to establish dental pre-diagnosis but also to formalize reports.

Computer Vision · Deep Learning · Imagerie 3D · Santé

SCHNEIDER ELECTRIC INDUSTRIES

Circuit breaker detection and recognition – embedded Deep Learning

Neovision designed and developed an artificial intelligence solution able to detect and recognize circuit breaker while running on a smartphone.

Application Mobile · Computer Vision · Deep Learning · IA embarquée · Industrie · R&D

LYNRED

Pedestrian detection – autonomous vehicle

Neovision built a database of previously unpublished data (infrared RGB and composite images) and then exploited this dataset. Subsequently, Neovision designed and developed Deep Learning algorithms capable of detecting pedestrians in all lighting conditions.

Computer Vision · Deep Learning · Environnement · R&D · Smart Cities

PELLENC ST

Automated plastic wastes sorting with Deep Learning

Neovision designed and developed an artificial intelligence solution able to automate plastic wastes sorting running on NVIDIA GPU.

Computer Vision · Deep Learning · Environnement · GPU · On Premise · R&D

STREET ART FEST

Street art recognition

Neovision designed and developed an artificial intelligence solution capable of recognizing works of art from the Street Art Fest Grenoble Alpes. This technology makes it possible to recognize work of art from a photo taken with a smartphone in Grenoble streets.

Application Mobile · Cloud · Computer Vision · Culture

TRANSARC

Route optimization

Neovision designed and developed an artificial intelligence solution able to detect and recognize circuit breaker while running on a smartphone.

Cloud · Environnement · Recherche opérationnelle · Transport

MICHELIN Business Aviation

Damage recognition on aircraft tires

Neovision designs and develops tire damage recognition technology. This technology, available via a smartphone or tablet application, allows the technician to diagnose the damage and then send the procedure to be followed. At the same time, the damage is recorded as part of the tire's life tracking.

Application Mobile · Cloud · Computer Vision · Deep Learning · Industrie

STMICROELECTRONICS

People detection on infrared images

After advising STMicroelectronics in the design of a neural network gas pedal, Neovision developed an algorithm for detecting and counting people embedded on a low-power microcontroller. The solution was then demonstrated at Mobile World Congress 2018 in Barcelona at the STMicroelectronics booth.

Computer Vision · Deep Learning · Energie · IA embarquée · R&D

CTC

Automatic laser engraving reader – OCR

Neovision designed and developed an OCR technology capable of reading laser engravings on calf skins. This robust technology remains capable of reading characters despite significant deformation.

Computer Vision · Deep Learning · Industrie · R&D

WINEADVISOR

Wine bottle recognition

Neovision developed an image recognition technology to accurately identify a bottle. To do this, simply take a picture of the bottle label via the application. This photo is then compared with more than a million references and the application retrieves all the information about the photographed bottle.

Application Mobile · Cloud · Computer Vision · Machine learning · Retail

SCHNEIDER ELECTRIC

Presence detection and recognition of human activity

After dimensioning the project and conducting a feasibility study, Neovision then designed computer vision and machine learning algorithms to detect human presence and activity. These algorithms were then embedded on a low-power microcontroller.

Computer Vision · Energie · Environnement · IA embarquée · Machine learning

BOTANIC

Flower recognition

Neovision designed and developed an artificial intelligence solution capable of recognizing the species of flowers marketed by the company. This technology makes it possible to recognize a flower from a photo taken with a smartphone.

Computer Vision · Deep Learning · Retail

ENLAPS

Panoramic time-lapse & object detection

Neovision has developed algorithms to merge image pairs to obtain a panoramic image. This panorama problem, very classic in photography, becomes much more complex in the case of a video. This solution allows the automatic merging of images, without the merging area being visible on the final video.

Computer Vision · Deep Learning