This is an extremely versatile technology, which according to a study1 conducted by Panasonic on a sample of 300 professionals working in digital transformation and the implementation of AI and Computer Vision, is employed in many business areas and applications. Repairs and maintenance (34%), production monitoring (33%), and quality checks (32%) are the areas where computer vision is most commonly adopted, followed by sales and marketing (31%), logistics and distribution (28%), back-office and administrative departments (25%), security (24%), and healthcare (22%).
According to the study, computer vision proves to be the preferred technology for many companies to increase productivity. Computer vision has indeed reached a much higher level of maturity compared to other AI solutions. Precisely for this reason, most respondents expect an average productivity increase of 42% after three years from the implementation and integration of computer vision solutions in their company, with peaks of 52% for the manufacturing sector and 45% for the public and service sectors.
What really matters, however, is the ability to identify the areas where this technology can have the greatest impact on business processes and to skillfully integrate these tools within the company. To this end, as highlighted by another Microsoft study2, it is essential to start with the workforce: the goal is not to eliminate employees but to empower them by relieving them of repetitive and time-consuming activities. The companies that are gaining the most advantages from these technologies are those that have understood how to increase their staff’s productivity by enhancing them with AI. A successful example is the insurance sector. An insurance company like Generali3 handles over 90 million images of vehicles involved in claims each year. Without image analytics tools, employees spend 50% of their time analyzing these images to extract relevant information. This is a tedious, repetitive, and time-consuming process that Generali has managed to automate, significantly speeding it up. Here, computer vision is used to automatically detect and locate damages and data such as license plate numbers or vehicle identification numbers (VIN), estimate the extent of damages, or show the operator images of similar damages.
Despite the enormous potential of this technology, development costs and the lack of skills represent the two main barriers to adoption reported by most companies surveyed. Being particularly recent technologies, finding a qualified team is often very difficult. Additionally, 37% of respondents report difficulties in finding support in development and maintenance outsourcing with third-party providers.
At Synapsi, we offer precisely this service. Every development and integration activity is always preceded by a preliminary study of business processes and the impact these technologies can have on the company. By involving all stakeholders, we ensure the development of solutions that bring measurable value and returns on investment. Budget and time constraints outline the path to follow, but it’s always important to have a clear destination. Only afterward do we move on to the phases of development, integration, and maintenance of computer vision solutions.
Lastly, data security and privacy are another major obstacle to the adoption of these technologies. To overcome this, it is always important to adopt solutions compliant with current regulations like GDPR and that ensure secure data storage and management. In this sense, it can be advantageous to choose hybrid solutions between cloud and edge computing or completely isolated (air-gapped) ones.
Computer Vision is, as the study reveals, one of the most mature applications of artificial intelligence, and it is quietly but significantly revolutionizing the way companies in almost every sector work. However, this revolution is only at the beginning, and the trajectory is clear. More than a third of the companies surveyed (37%) have stated that they have already implemented and are benefiting from generative and agentic AI, with an additional 34% in the implementation phase of this technology and 17% still evaluating its adoption.
And this is where the potential of computer vision reaches its peak. Through its integration with AI agents, this technology enables a further step: it’s no longer just about extracting information from images but about automating decisions. By enhancing AI agents with visual perception of the physical world, it is indeed possible to automate complex tasks involving the extraction and interpretation of visual data. If you too want to understand how to integrate AI into your company, I invite you to schedule a meeting with our team to explore how we can help revolutionize your business processes.
At the core of automatic recognition systems is computer vision, a branch of artificial intelligence (AI) that enables machines to interpret and make decisions based on images and videos. To automatically recognize license plates, the AI analyzes images from cameras and for each vehicle reads the corresponding plate through a process called Optical Character Recognition (OCR). Thanks to this process, each character on the plate detected in the image is transcribed into text format. The information can then be saved in a database or displayed on software in real time.
These readings can also be combined with other automatic recognition tools such as, for example, vehicle type classification and tracking, nationality, or automatic speed estimation.
With automatic license plate recognition, it’s possible to actively monitor a very large number of vehicles. Consider, for example, a highway section traveled by millions of vehicles every year. Manually processing these transits would be unthinkable due to the time and costs this process would entail. An automatic system can process images in the order of milliseconds, offering scalability and operational efficiency without equal, but that’s not all. In some contexts, it may not be necessary to monitor a large number of plates, and automation can still bring advantages, such as in automated parking lots, where a camera can autonomously monitor vehicle parking even in the absence of a dedicated operator.
Processing speed is not the only advantage of an automated system. In addition to speed, these systems must also be reliable. The question that may arise is therefore: how accurate are these systems? The answer to this question is not trivial. The system’s accuracy can indeed depend on various operational conditions, such as the quality of the cameras capturing the images, the frequency with which they do so, the distance, lighting conditions, and visibility, which in some cases may be compromised. The only way to answer this question precisely is to test the system in the field, under various weather and lighting conditions. Despite this, to give a qualitative answer, we can state that a sufficiently robust system will be able to maintain performance very close to human levels even in more difficult visibility conditions. To give you a concrete example, at Synapsi we developed and tested a transit recognition system for a client in the highway sector. Comparing the performance of an automatic system with human operators under poor visibility conditions, we found that the latter tended to make mistakes in almost 20% of the readings, while our system made mistakes in only 2.2% of the same sample.
Automatic license plate recognition opens the door to multiple applications.
Often, parking spaces need to be monitored automatically without having to install a parking meter. This is the case in many supermarkets or other commercial activities, where spaces reserved for customers are often abused and used as long-term parking. In such cases, surveillance cameras can also be repurposed to automatically charge a fee for stays exceeding a certain duration. Similarly, an automatic monitoring system allows for counting the number of parked vehicles and available parking spaces.
License plate recognition also enables automatic verification of authorized access. Consider, for example, limited traffic zones (ZTL) or other restricted access areas. In such cases, a reliable automatic monitoring system can drastically reduce monitoring costs by automatically reporting violations.
In smart cities, automatic license plate recognition systems allow for automatic monitoring of passing vehicles, analyzing traffic, speed in real time, or enabling authorities to quickly find suspicious vehicles. They are often used in free-flow highway sections for transit recognition or in municipalities for monitoring busier areas.
In the insurance sector, automatic license plate recognition speeds up claims management processes. By combining automatic plate extraction with other vehicle information such as the VIN (Vehicle Identification Number), body components, miles traveled, and damages, processes can be accelerated, reducing management costs and ensuring faster service for clients.
At Synapsi, we have developed license plate recognition systems in various contexts, ranging from the insurance sector to highways, from prototyping to industrialization. We are well aware of the challenges and results that can be achieved and can assist you in developing and integrating these systems within other corporate systems. If you need our support, don’t hesitate to schedule a free consultation with our team!
]]>Working alongside corporations in various sectors (highway, insurance, food & beverage, agritech, infrastructure and transportation, and manufacturing), at Synapsi we have developed a structured process in 5 fundamental steps that helps us avoid these mistakes.
Imagine being a company that produces electric drills and wants to revolutionize the market. Knowing the sector well, you understand that most customers look for a new drill when the previous one breaks. You decide to invest in developing a new titanium-coated drill bit to make it 40% more durable than those on the market. Sales increase for a while, until the launch of a new product starts eating into your revenue. This product is 3M’s adhesive strips for hanging pictures, which allow your potential customers to solve the problem of hanging a picture without the hassle of drilling a hole in the wall. You have just learned one of the most famous lessons in marketing, elaborated by Theodore Levitt.
“People don't want to buy a drill with a 6mm bit. They want a 6mm hole in the wall.”
It’s a simple concept, yet often overlooked by those proposing innovation and technology to businesses: SMEs are not looking for chatbots, algorithms, or generative models as ends in themselves. What they really need is to ensure operational continuity, reduce errors, serve customers faster, and manage costs effectively. Artificial intelligence can certainly be a valuable tool to achieve these goals, but it is never the starting point. When this fundamental dynamic is lost sight of, the risk is that AI becomes yet another generic promise, a budget cost with no real return on investment.
The challenge is not to be the first to apply artificial intelligence. The real challenge is to understand where you are employing people to perform tasks that a machine could do better, faster, or with fewer errors? Only from here can a true reasoning about AI adoption begin. Otherwise, you end up integrating technologies that no one needed, just to avoid seeming late. AI cannot replace people, but it can empower them by making them more productive.
Imagine being a company in the insurance sector that employs assessors to analyze images of claims. Each time the operator analyzes a new claim, they must look at multiple images to verify the license plate and chassis number of the car. They must then assess the damage and manually enter the data into the system. Imagine this process repeated dozens or hundreds of times a day. How does this impact the business? Now imagine being able to extract all this information automatically, so that the processing time for a claim is more than halved. This is a reduction in annual costs and process efficiency that allows for faster service to customers. This example, inspired by a use case from one of our previous clients, is a clear example of how AI can have a real positive impact on business.
A false myth to debunk is that artificial intelligence can solve any problem. Too many think that simply feeding any input into these systems will make them learn to solve our problems. This is absolutely not the case; in fact, among experts in the field, a mantra often prevails: “garbage in, garbage out.” If we input any kind of data into an AI system without ensuring quality and without a structured process, we will get a system that returns answers of the same quality. If you have identified a business process to work on, the first goal is to understand whether the data you have is usable for training an AI algorithm or if you can use one already trained on your data. If the answer is no, you must start from the basics. A well-structured data acquisition process can bring enormous benefits. In this case, you can identify areas for improvement to obtain cleaner data. For example, imagine having videos captured by a camera installed on a fleet of vehicles. In an initial phase, the cameras were installed inside the vehicles. Analyzing the data, you notice that most videos have reflections, image quality that is too low, and an extremely limited field of view. If you think AI can work miracles by detecting even the minutest details, know that you will likely only waste your budget. Rather than immediately starting an automation project, you could invest part of that budget to relocate the cameras outside the vehicles or replace them with higher-quality cameras. With quality data, you will certainly achieve better results.
Once you understand this first fundamental step, the next step is to set clear and measurable goals. What performance must the system achieve to have a tangible impact on your business? Which processes does it affect? Without KPIs, you will navigate in the dark. Whether it’s improving customer satisfaction, reducing operational costs, or increasing employee productivity, ensure these KPIs reflect the impact you expect from each AI integration. If you don’t know where to start, you could develop a benchmark of AI solutions already on the market or open-source. Alternatively, you can take human performance in the activity you want to automate as the value the system should aim for.
The adoption of artificial intelligence is a journey, not a destination. You don’t need to reach the goal in one go. Every AI project is unique and should always be characterized by an experimental process. Our suggestion is to always start with the development of a Proof of Concept (PoC), a pilot project that allows teams to work toward clear goals in a limited context. The goal of a PoC is not to integrate AI from day zero, but rather to understand its limitations. It is an iterative process, where you experiment, identify areas for improvement, and test the real potential of an AI system in an operational context. It may seem like a useless waste of time, but AI is not a magic box and will not work as you expect from the moment you apply it. A pilot project helps you understand how to best leverage it and paves the way for more conscious adoption in business processes.
Returning to the example of the insurance company, instead of aiming to extract all the information you need from the start, you could focus your energy on developing an AI system capable of reading the license plates of damaged vehicles. Start with European vehicles and measure the system’s performance. After an initial testing phase, you might discover, for example, that the system struggles to distinguish certain characters. For instance, the system might frequently confuse similar characters like “D” and “B”, “0” and “O”, or “C” and “G”. This is a common problem in this type of task. Focus on this aspect and improve the system’s performance. Once the KPIs are reached, you can easily make the system capable of recognizing license plates from non-EU countries. The PoC serves to structure the system in the right configuration and identify a series of actions to make it robust. Only once you have verified the effectiveness of artificial intelligence can you integrate it into business processes.
Before automating the current process with AI, ensure that it maintains good performance over time. Like a new employee, AI will need a training period where you can monitor the system’s performance in a real-world scenario for a sufficiently representative period. For example, if you are a highway company and your goal is to analyze traffic, you should ensure that the new AI system is paired for a period long enough to cover “normal” traffic periods and busier periods like holidays. This phase ensures that the system remains reliable in every operational scenario and corrects any unexpected behaviors.
Once the system has been sufficiently tested, you can finally integrate it into business processes. In this final step, it is crucial to remember that AI is a tool, and like any other tool integrated into your company, it must have an impact on the business. In this phase, it is essential to constantly monitor the KPIs you defined in step 2. Conduct periodic review sessions to evaluate the use and effectiveness of the tools. It’s not just about monitoring metrics; the goal is to understand the story behind the numbers. How are AI tools reshaping workflows, decision-making, and customer interactions? Are they meeting, exceeding, or falling short of expectations? This continuous evaluation cycle will help you identify success patterns, areas for improvement, and opportunities for further AI exploration.
If you’re still reading these lines, you will have understood that integrating AI into your business is an iterative process, where at each step you can measure the impact it is having on your company. It is certainly a complex process that can be intimidating, but it leads to concrete and tangible results. We at Synapsi know this well, and if you want, we can guide you through this process step by step.
]]>