By using the MaxinaAI solution, the customer was able to automate the extraction of food label data and confirm its compliance with country-specific regulations.

Challenge

Seeing various foreign products on the shelves of local stores may seem like a normal thing, but there is a complicated process behind it all. Before these products can be sold, their labels must meet specific requirements set by the destination country.

Since each country has different standards when it comes to food and food-related products, it is vitally important that food exporting companies comply with country-specific regulations. 

Most of the time this process requires an incredible amount of human resources and is usually very time-consuming. The traditional process is often very complex, labor-intensive, and error-prone. It includes dedicated staff who manually extracts data from product labels and manually verifies compliance with country regulations.

Our Swiss client, C-Labs SA, develops solutions to transform food regulatory compliance and was aware of the industry challenges mentioned above. To fight the complexity and time-consuming nature of this process, a customer decided to automate it with the help of the MaxinaAI team.

That is why they approached us and asked for a solution that would simplify obtaining information on food ingredients and their verification with the specific regulations of the country.

Solution 

At the core of our solution was computer vision, a technology that helps computers gain high-level understanding from digital images or videos, label images, and automate tasks that the human visual system can perform.

Let´s take a look at how we incorporated computer vision in our solution. For the start, we created a model that classified all nutritional labels from uploaded pictures and performed text extraction on them which was done directly from the food products’ nutritional label and the information on the ingredients was later compared with the desired country regulation. 

To identify the text on the product package, Optical Character Recognition (OCR) was used. OCR is a technology that helps the user transform desired documents (images from paper documents, scanned images, etc.) into searchable and editable data. 

This technology makes difficult data extraction possible. Some products (such as potato chip bags) have a softcover, which causes the text written on them to bend or, due to the light, the text does not show well, making it difficult to extract the text. However, OCR technology makes it possible and feasible.

Another benefit of OCR is accelerated information search and extraction. So for example, if a colleague sends you a photo of a document taken by the camera, it will be difficult for you to quickly search for the information or even more so, edit it. With the help of Optical Character Recognition, you can digitize the text contained in the document making searching and editing information easy and convenient.

The same benefit was acquired for our client. They did not have to manually extract all the information from the food package, as with our solution it was possible to extract the product information automatically from the user-uploaded image, including nutritional information, weight, and manufacturer name.

Before MaxinAI solution:

After MaxinAI solution:

A dedicated team has trained custom machine learning models using open-source dataset and product images from Amazon. In combination with several cloud OCR services, we managed to provide a high-quality API service. The multi-step pipeline was created to process large amounts of data in a scalable way.

To make this process easier, we also created a system with a user interface where the information was displayed in a structured and visual way that helped and simplified the work process for the end-user.

Technologies 

• Customized YOLO implementation on PyTorch
• spaCy + scikit-learn for NLP adjustment
• Dockers and Google Cloud for continuous delivery 
• Google OCR and AWS Textract
• Scrapy to collect data from different sources

Skip the boring manual work

The old-school data entry process includes manual labor done by people that has proven not only time-consuming but prone to inaccuracy and human error from time to time. With the MaxinAI solution, you can automate this process saving yourself time and trouble.

Today, no one should be burdened with mundane and repetitive tasks. With intelligent automation, you and your staff can take on more important tasks that have a greater impact on business performance.

Similar project in mind? We offer a free pilot project!

MaxinAI solution helped an Ireland-based customer automate livestock monitoring and tracking – improving farm operational efficiency and ultimately reducing costs.

Challenge

Agriculture is an ancient activity that researchers believe was “invented” around 12,000 years ago and has been present in daily human life ever since. 

Despite the fact that this sector is one of the leading occupations among the population in the countryside, it still lags behind other sectors in terms of underdeveloped methodologies and the use of obsolete techniques. More specifically, there is a demand for safer and more effective operations within this sector. 

Innovative solutions such as artificial intelligence, machine learning and computer vision have penetrated many sectors and demonstrated the untapped potential that can be achieved within the agricultural sector in terms of improving operational efficiency. 

Fortunately, more and more farms are starting to follow this positive trend. One of them is our client from Ireland that wanted to improve the operational and financial efficiency of its farm. 

What is computer vision?

Let’s start with the definition of computer vision, which is defined as the extraction and analysis of information from images or videos to be used in applications such as robotics, security systems and self-driving cars.  

Computer vision has several applications within large industrial areas such as manufacturing, surveillance and even medicine. 

An application that we will focus on is the use of computer vision in the agricultural sector, which has many benefits such as crop yield, cost and energy reduction.  

Solution 

Our solution is based on computer vision and acquires data on livestock from cameras installed in the facility. With the help of cameras, images and videos are automatically analyzed and meaningful insights are gained, without the need for human intervention.  

The solution recognizes and counts the livestock, as well as their activities such as how long the cattle are being milked. Livestock detection and recognition helps farms operate more efficiently for higher productivity and lower costs by controlling animal diseases and tracking livestock to ensure their safety.

In addition to livestock, the activities of human personnel are also being tracked and analyzed. The system also shows exactly when activities were carried out so that operations can be adjusted and changed according to the need. In this way, users can obtain details about cows that were previously difficult to identify, such as the reason for their illness and body condition. 

Another reason users get better and more accurate information on the condition of cattle is that in the presence of a human, cows have evolved to hide most of the early signs of lameness. In many cases, cows can go on for weeks with hurting legs before showing obvious signs of limping. The delay in injury identification negatively affects food intake, milk production, fertility, and longevity. 

However, when the injury becomes apparent, most of the time the damage worsens and the cow’s productivity is hampered for a considerable period of time. This can have catastrophic consequences for a farmer if it happens to several animals at the same time.

The advantage of our solution is that when cows are being monitored with smart cameras, they do not feel the human presence and their actions are not disguised, giving more genuine information about their health.

With our solution, the client was able to prevent the aforementioned incidents and optimize various operations such as energy savings, human resources savings and other costs, achieving the advantages of high efficiency and high precision. 

Technologies:

• PyTorch
• Python
• Deep learning 
• Computer vision algorithms  

Time for a change 

The opportunities are limitless when it comes to artificial intelligence in the agricultural industry. Replacing manual labor with automation, whenever possible, is important for reducing costs and improving productivity. However, it becomes especially important for farms, as livestock is an essential and significant part of the agricultural sector and the removal of the human factor can contribute to the early identification of injuries in livestock.

If you are a representative of the agricultural sector and you are interested in a similar solution, do not hesitate and schedule a call with our expert.

We will go over your specific use case and offer you a pilot project free of charge!

Drones are a hot topic these days. But what if these aerial vehicles were actually delivering more than just nice videos? What if they could help farmers ensure successful harvests and safer food supplies, too?

Actually, they can — and the agricultural industry is taking notice. Drones help the agricultural industry by increasing crop production and monitoring crop growth.

Who would have thought that drones, a tool originally built for military purposes, would come in handy for many industries? For some sectors such as agriculture, it has become so useful that it can help to carry out activities that could not have been done before.

In fact, agriculture is one of these sectors that is constantly looking for innovative solutions, as the population is expected to reach 9.1 billion by 2050 and the industry faces the challenge of boosting food production that meets the growing demand.

To overcome the challenges, more attention began to be paid to drones equipped with computer vision technology to help increase crop yields. These technologies have become so popular with the industry that they are projected to grow 5x and be worth $ 5.7 billion by 2025.

So what exactly do these unpiloted aircrafts offer to farmers?

AI-powered drones

Modern irrigation practices, livestock technology, fertilizer management, and various other tools have allowed farmers to improve different operations. But when it comes to crop production and growth monitoring, drones have established themselves as the best solution for farmers. 

The drones are equipped with GPS systems and cameras that allow them to fly over every part of the field that needs to be inspected and take images. So once the crops have been planted and started to grow, farmers implement this technology and give a certain flight path based on the area they want to survey.

So what’s new and innovative in flying camera drones? Well, the thing is, these cameras are not the normal ones. They are called multispectral imaging cameras that are so comprehensive that they are used for military purposes such as detecting landmines.

While landmine detection is useful for everyone, for farmers it is primarily used to improve crop, soil and fertilization management. The taken images are integrated with specific software that shows the image in different colors. For example, if the field shows green color, the crops in that area have good photosynthesis and their growth is healthy.

However, the areas showing the red and yellow color need attention, as the crops are not growing as they should. All of this information is vital as after looking at it, farmers can manually go and check what is causing the problem of unhealthy crops. Are the crops underwatered, insufficiently fed, are insects causing the issue or perhaps the plants are being overwatered?

This allows farmers to be proactive rather than reactive when the problem is already visible and damaging. The ability to be proactive is due to drones that make the crop monitoring process fast and effective.

Imagine farms of over a thousand acres. The human resource it would take to replace what drones effortlessly do would be immense. With flying technology, however, they not only save time but detect details that would be impossible to see with the naked eye, regardless of human resources.

Innovating the farming industry

Drones serve as a powerful tool to monitor the growth of crops. But this is not the only thing that these flying objects can help farmers with. In addition to supervision, they can also plant seeds, apply spray treatments, and even serve as a security tool to keep an eye on the area and make sure operations are going as planned.

With so many applications and benefits, it is not an enigma why this technology is experiencing such rapid growth and why so many farms are turning their attention to drones.

If you want to keep up with the trend using the technology described above or any other, you have come to the right place. Our experts offer a free consultation call to discuss your ideas and their tangibility.

From an early age, people knew that the health of crops was directly related to weather. Since crops are sensitive to low temperatures, heavy rains, thunderstorms, etc., bad weather conditions can be detrimental to the agricultural sector.

In the past, people have relied on their beliefs in superstitions like rituals, but fortunately today humanity found a more effective way to handle the problem.

New technologies are available to protect crops against bad weather conditions. One of these is artificial intelligence (AI), which provides forecasts that help farmers protect their fields from heavy rain or hail.

While we cannot completely change the climate for the desired environment for crops, Artificial Intelligence (AI) can still offer viable solutions that are transforming the practice of agriculture.

Today, specifically, we will talk about how farms can protect their crops from bad weather with the help of Machine Learning (ML) and AI.

Weather monitoring using IoT

IoT stands for Internet of Things, which includes all devices that are connected to each other, communicating and exchanging information with their sensors.

IoT sensors are a perfect solution for weather monitoring. One might think that these devices are not necessary as you can easily tell what the weather is like with the naked eye, however, the truth is that IoT devices measure details about the weather that can go unnoticed by a normal person. 

Yes, we can tell if it is getting cloudy, but IoT sensors monitor live details, such as temperature, humidity, CO levels, wind speed and direction, air pressure, etc.

All this data is sent to farmers for analysis and strategic decisions that are not based on a hunch. Thus, farmers will be able to prevent over or under watering, have vivid and accurate information on crop diseases, and more importantly, can take timely precautions such as covering and protecting crops in case weather conditions worsen.

Weather prediction with AI

When IoT and AI are put to work together, great things can happen. One of those things is predicting the weather. How exactly?

Available weather data from your IoT sensors can be fed into artificial intelligence algorithms, and together with analytics, statistics, and machine learning algorithms, you can get an upcoming weather forecast.

However, the more data there is, the more accurate the predictions will be, so you will also need to obtain historical weather data from other sources.

Weather forecasting is nothing new, however, by improving the process with AI algorithms, more accurate predictions are obtained. In fact, a recent research showed that the artificial intelligence system can give up to a year ahead of the weather forecast with maximum precision.

Conclusion

Climate has a serious impact on agriculture and food supply and with a growing demand for affordable, healthy and quality food, farmers are forced to seek innovative solutions and minimize risks related to agriculture.

Along with AI-powered automation tools, solutions like IoT weather monitoring and AI weather forecasting help farmers break through limitations and get the most accurate information.

Artificial intelligence and Machine Learning enable farmers to understand potentially dangerous weather conditions ahead, as well as current crop health state, such as their water level, overall temperature or humidity, which would otherwise be nearly impossible to detect.

If you want your farm operations to run smoothly, then you need to be proactive rather than reactive. Schedule a free consultation call with us and let’s discuss how we can make sure your crops stay healthy and safe.

[Schedule my free consultation call]

About 30% of fruits and vegetables are wasted during processing operations and, although some of them are damaged, a considerable amount is discarded only due to inefficient sorting practices. This is a huge amount of waste and also a huge monetary loss for businesses. 

As demand for food is expected to increase between 59% to 98% by 2050, the importance of minimizing food waste goes beyond economic concerns.

Sorting fruits and vegetables is a vital part of the supply chain, as it identifies foreign materials or fruits that do not meet the standards set by food safety organizations. So another important aspect of this process is making sure all unqualified produce is filtered out.

Food waste is not only bad for business but also bad for the environment. Food loss and waste accounts for 8% of all global greenhouse gas emissions, according to the FAO.

Since sorting is still mostly done manually, it leaves room for some human error. Not noticing foreign objects or spoiled products can have serious consequences for businesses, resulting in costly lawsuits and other complications.

However, some farms realized that instead of handling this process with traditional methods, innovative solutions like AI-powered sorting machines could be more effective and less expensive in the long run.

Let’s take a closer look at the solution and how effective it can really be for companies. 

AI-powered fruit sorting machines

As you may already know, artificial intelligence is a simulation of human intelligence in machines, and just as humans learn from past experiences, so does AI from historical data.

With the help of data, AI-powered systems can recognize patterns and make independent, intelligent decisions to get the best possible outcome.  

Machine vision is one of the many aspects that AI covers and is an important part that makes autonomous sorting possible. With the help of AI cameras and algorithms, machine vision can perform visual inspections of different things by detecting flaws, contaminants, or product defects.

Combine this technology with data about fruits and vegetables and you get yourself a produce sorting machine. But exactly what kind of data can be fed into the system?

It is important to provide your machine with a large amount of quality data for the best result, including various images of healthy and unhealthy fruits and vegetables. 

In this way, the machine will learn from the provided examples and quickly differentiate spoiled from healthy vegetables and classify them accordingly.

Let’s see what the automated process would be like with sorting machines powered by AI: 

• The harvested product will pass through the cameras and sensors of the machine
  
• Sensors and cameras will first identify the product type and move to the next phase only if the product will be identified as the desired fruit or vegetable (this step identifies if foreign bodies are present)
  
• Afterward, the machine with the help of a neural network analyzes the images of produce to identify its state: healthy or damaged
  
• The product is distributed in different containers according to its state
  
• Sorted vegetables and fruits are inspected by human agents for maximum precision

A better way of sorting

These types of sorting operations are useful for various businesses, they can be used to sort different items like computer parts or even waste. However, it is especially vital for food processing because ensuring a high-quality product is essential for this sector.

In today’s innovative world, finding smart solutions that increase efficiency and effectiveness is key to success, which is why more and more companies are starting to implement AI in their day-to-day operations.

Want to see how AI helped companies manage COVID and force a major crisis? Take a look at our article.