AI-GO blister inspection. Image Credit: Antares Vision Group
Antares Vision Group, a provider of track-and-trace systems for several fields including the life sciences, and Oròbix, an artificial intelligence (AI) service company that’s part of Antares, have launched AI-GO, an AI-powered visual inspection platform that is expected to boost standards that span multiple key performance indicators.1 Essentially, the branded platform is intended to address the demand for both quicker and more accurate inspection processes.
Enhanced defect detection improves product quality and reduces waste
According to Antares, one of the new system’s essential features is its boosted analysis accuracy. Reportedly, a differentiator is that AI-GO is able to identify complex anomalies, including cosmetic flaws, chromatic impurities, glass fragments, and foreign objects, which can not only result in a decrease in false rejections, but an improvement in overall production quality.
AI as a strategic lever for competitive manufacturing
With the help of optical character recognition (OCR), the system can automatically create models for classification, segmentation, and optical character recognition (OCR). With specialized operator skills and nominal training data, this can be done at a fairly quick pace. The key element is deep learning, allowing the models to be simply modified to apply to various formats and product types, which, from a manufacturing standpoint, lowers setup time, while augmenting production lines’ effectiveness.
“Today, artificial intelligence has become a fundamental strategic lever for industrial competitiveness. Integrated in a secure, transparent and verifiable way, it enables us to offer our customers better performing inspection machines, able to improve product quality, reduce false rejects, and increase production efficiency,” noted Gianluca Mazzantini, CEO of Antares Vision Group.
The goal of AI-GO is to become a system that processes, self-adapts, and constantly evolves, allowing for more resilient and sustainable manufacturing. With this new solution, Antares Vision Group aims to support companies in transitioning to advanced production models, where quality is driven by objective data, predictive analytics, and digitally managed processes.
“AI applied to visual inspection represents a turning point for the manufacturing industry,” said Pietro Rota, CEO of Oròbix. “With solutions like AI-GO, we are bringing an intelligence to production processes able to understand real data and dynamically adapt itself to the variability frequently seen in production. At Oròbix, we are working tirelessly to make AI a real ally of quality and of industrial production.”
Key Takeaways
- Antares Vision Group’s AI-powered platform significantly improves defect detection, reducing false rejects and boosting overall production quality in pharmaceutical manufacturing.
- Using deep learning, AI-GO enables rapid creation and adaptation of classification and OCR models without the need for specialized skills, cutting setup time and increasing operational efficiency.
- The platform’s evolution includes integrating Vision Language Models, allowing users to control complex inspection tasks using simple natural language, making quality control more accessible.
Dual-component architecture
The system consists of two parts. One is AI-GO Studio, a cloud environment that collects images and train models. Meanwhile, AI-GO Runtime is an edge module that allows for independent execution of models directly into production lines, even when they’re offline. Down the road, Antares Vision Group aims to encompass vision language models into its proprietary platform.
“Vision language models are innovative models that combine the understanding of images and language, enables complex tasks to be performed through simple instructions in natural language,” commented Luca Antiga, CTO of Oròbix. “We are working to render AI-GO increasingly intuitive and powerful: the native integration of VLMs will enable quality controls to be set up faster and in a more accessible way, even without technical skills.”
In other Antares news, the company recently grew its solutions portfolio to include precision labeling equipment.2 The company is collaborating with Siempharma, a manufacturer of packaging machines, by welcoming the ETF-300.
This machine is capable of working with containers ranging from 40-180 mm in height, and 22-80 mm in diameter. It can apply labels as tall as 100 mm at speeds of up to 80 meters per minute. The unit is also able to switch between various container and label sizes; changeover only takes 15-30 minutes.
References
1. Antares Vision Group Debuts AI-Powered Visual Inspection Platform. Antares Vision Group. June 19, 2025. Accessed June 20, 2025. Press release sent via email.
2. Saraceno N. Antares Vision Group, Siempharma Strike Up Pharma Labeling Equipment Collaboration. Antares Vision Group. May 8, 2025. Accessed June 20, 2025. https://www.pharmaceuticalcommerce.com/view/antares-vision-group-siempharma–pharma-labeling-equipment-collaboration