L’spin-off del CVC AllRead crea una nova tecnologia de detecció i digitalització d’imatges

Investigadors del Centre de Visió per Computador (CVC-UAB) han creat AllRead Machine Learning Technologies (AllRead MLT), una nova spin-off especialitzada en detectar textos en imatges i digitalitzar-los. El seu objectiu és portar al mercat una tecnologia pròpia innovadora, basada en el deep learning, que es pot aplicar a la identificació i seguiment de contenidors en ports i aeroports.

La solució disruptiva que ofereix la nova empresa permet localitzar un text numèric o codi de qualsevol part d’una imatge sense haver-la de segmentar. A més, segons els seus impulsors, és més fàcil d’implementar i utilitzar que altres propostes del mercat.

La nova tecnologia segueix un model de xarxa neuronal, que es pot entrenar i adaptar a diferents escenaris operatius o industrials. Els algoritmes que han creat són capaços d’aprendre dels errors i de millorar, la qual cosa fa que l’extracció de dades sigui molt precisa. “Processem les imatges i n’extraiem la informació rellevant i que té valor per al client. Fem una selecció utilitzant el big data, que amb la implementació de la xarxa 5G guanyarà en velocitat“, explica el cofundador i conseller delegat, Miguel Silva-Constenla.

Prova pilot amb el Port de Barcelona

ALLRead MLT ja ha fet diferents proves pilot amb el Port de Barcelona i amb empreses de diferents sectors, com Suez, Comsa i International Airlines Group, en les quals s’han agilitzat processos logístics que requereixen obtenir informació ràpida i precisa. “Amb una infraestructura tan simple com una càmera de seguretat i un programa informàtic es pot llegir la informació dels contenidors d’un port o dels comptadors de l’aigua”, afirma Silva-Constenla. El seu programari de visió informàtica s’adapta a qualsevol escenari de lectura: números de sèrie, codis de barres malmesos, lectures de sensors, dates de caducitat, etc.

De la UAB al Mobile World Capital

El projecte d’AllRead MLT es va començar a gestar el 2016 al Programa de Generació d’Idees del Parc de Recerca UAB. L’impuls definitiu el van tenir amb la participació al programa The Collider de la Mobile World Capital Barcelona, en el qual es van posar en contacte tres desenvolupadors del Centre de Visió per Computador que treballaven en un sistema de lectura intel·ligent -Dimosthenis Karatzas, Marçal Rossinyol i Lluís Gómez- amb dos executius per escalar el negoci – Miguel Silva-Constenla i Adriaan Landman-. El passat mes de març van aconseguir una inversió de 50kc, el principal inversor de la qual és el Mobile World Capital. El seu objectiu és tancar noves rondes de finançament durant el 2020.



ICAR: automatically verifying identity

Everyone of us has a digital identity. This identity is configured in a compilation of all a person’s shared information on the web: personal data, images, news, comments, hobbies, contacts and friendships, among others. However, identity can be easily stolen and used in order to gain financial advantages or obtain benefits in another person’s name.

Although identity theft has been happening now for many years, even before the digital era, it is a fact that this crime has increased its rates considerably with the proliferation of the Internet, becoming one of the fastest spreading crimes. According to a study made by the Statistical Office of the European Union (Eurostat), 7% of Spanish internet-users were victims of identity theft in 2017, almost doubling  the European Community average (4%). Moreover, this means annual losses of 1.600 million euros in Spain and 80.000 million euros all over the world.

Accessing bank accounts, obtaining loans, hiring products and services or denigrating someone’s image are the main reasons that lead cyber-delinquents to forge identity. In order to curb this type of crimes, several entrepreneurs founded Icar, a CVC spin-off, providing solutions for identity validation and user verification.

The beginnings

Icar’s name comes from the ‘Identity Card Access Reading’. Established in 2002, its very first client was a familiar business, the Peralada Group, active in several sectors such as leisure, culture, viticulture and industry. They needed a system that could control access to their casinos. Icar designed a solution that provided the lecture and the interpretation of identity documents by means of computer vision with which the family business could automatically identify its customers. “The good news was that it worked very well and thanks to that, Icar was making a niche in the market”, as explained by Manolo López, Icar’s Marketing Director.

Different solutions for different sectors

Currently, Icar’s solutions are mainly focused on the hospitality sector. For security reasons, receptionists must compile personal information of guests at check ins. Icar provides a scanner that automatically extracts the information contained in an identity document and transferring it immediately into the hotel’s internal database.  It’s this solution which has given Icar the lead within the travel sector, its technology being used in almost every hotel in Spain.

Fintechs and online banks are also part of their target public and one of the most affected sector by identity fraud. To mitigate this problem, Icar provides them with a document authenticity validation, verifying identity in financial documents in a very agile, effortless and secure process.

Validation can happen at any place and at any time, with the use of a smartphone, tablet or computer. This is highly useful in tasks that are usually done from their phone and can be easily forged:  a hotel or a flight check-in, opening a bank account, making online payments, asking for credits or contracting products and services. For this reason, telecommunication, insurance and energy companies are also common consumers of this solution.

And so came Mitek

Today Icar is now part of Mitek. Mitek Systems, with its headquarters in San Diego, California, acquired Icar in October 2017 by 12,75 million euros. Mitek is one of the pioneers worldwide in mobile capture and identity verification.

As Manolo Lopez explained, Icar had already been a world reference in identity validation before Mitek’s purchase in 2017 with presence in international markets such as Spain, France, Mexico, Colombia, Brazil, Argentina, Costa Rica, Portugal and Poland: “Icar’s advantage was that there wasn’t any competitor offering the same services and it was the most powerful in terms of positioning and market share. This was one of the main reasons Mitek became interested in Icar; they knew that we were a consolidated company, not only for the number of clients but also for the quality of the technology”.

Since then, both companies have changed a considerably. Mitek was operating mainly in the US, Canada, Holland and the United Kingdom, and has now opened a whole new geographic scope. In addition, Manolo Lopez explains that the purchase and Mitek’s growth strategy has meant an increase in its personnel for Icar. In fact, Icar started as a team of five people; today they are over 30.

Future steps

The current aim of the company is to expand through Latin America, where they don’t have presence yet. Manolo Lopez puts it: “the demand still exists. There are many countries, especially in Latin America, in which we have not entered yet, but that have the need and are looking for this technology.”.

Nevertheless, between this halo of growth and expansion, there are also great challenges that Icar has to face. First of all, they have to ensure that customers don’t lose the trust they had with Icar after Mitek’s purchase: “Icar was already a leader in many countries where Mitek was not so renowned. Our challenge now is to maintain that confidence and also transfer it to Mitek”, Manolo Lopez affirmed.  

Another challenge is what to do to integrate all solutions adequately. Icar and Mitek have very similar solutions, but it is inefficient to maintain them all: “Both companies are still selling their own solutions but we are working in an integration plan to solve this. The idea is to take the best of each one in order to create a technology capable of taking advantage of the experience, the information and the benefits of both”.

For more information: https://www.icarvision.com/

Vintra: AI for effective video surveillance

To solve a home invasion crime, the Police Services of Dublin (California) would had to review 70 hours of video obtained from a security camera from a neighbour’s home. This amount of footage would have meant more than three days of intense review for the team. Instead of that, they tested Vintra’s solution, which removed idle frames from static footage and showed them the crucial scenes. As a result, these 70 hours became 24 helping detectives to identify the suspect’s vehicle faster.

Although 24 hours meant an important reduction, Vintra’s founders assured that nowadays, this could be reduced to 6 hours due to the improvements the technology has experienced.

Vintra at its beginning

Vintra was born as a company at the end of 2016. It was founded by Brent Boekestein and CVC researchers Dr. Angel Sappa and Dr. Ariel Amato. They all presented certain concerns about the new deep learning techniques in the field of video analytics and therefore, starting with this first idea, they decided to create a prototype and a previous product which was successfully validated by final users.

Vintra was not the first business that these two CVC researchers set up. They first co-founded a CVC spin-off called Crowdmobile S.L together with Dr. Felipe Lumbreras; in that company they developed Knowxel, which is a kind of social network where users work in different tasks. These tasks need to be solved by a large team in a short period of time and are usually related to the need of companies and organisms to collect, analyse and process large amounts of data. With Knowxel, not only were companies able to complete their tasks swiftly but users were receiving money for the work done.

Back to Vintra, it is an AI software that helps security professionals get their job done. Vintra works with footage from all kinds of cameras and is capable to identify a wide array of key attributes within a video, including descriptive, definitive, scene and object attributes.

As this technology reduces the amount of attention required by people in charge of monitoring, it allows an improvement in terms of efficiency getting investigators to focus on other higher value tasks and money and resources spent in better analysis and resolution of cases. In fact, in the first example mentioned, the analysis of multiple day footage, allowed Dublin’s police to discover that the suspect had been casing the house with the same car three days prior to the robbery, and were also able to connect his vehicle with multiple cases in the surrounding areas. This would have been impossible without the help of this intelligent device.

The inaccuracy of manual reviews  

Cameras have a great presence in multiple cities around the globe. They are used to monitor streets and traffic, to generate a sense of security and are key to crime solving.  Cameras provide a vast amount of footage that plays a main role in the fight against delinquency.

Nonetheless, the fact of having an extensive amount of hours of video available, can actually be a downfall when it comes to solving a crime hurriedly. In fact, a single investigator spends between 200 and 300 hours per year reviewing video footage looking for a specific person, object or event.

Humans are not well prepared to do this task efficiently because of our limited ability for long-term singular focus. After a few minutes of video review, fatigue and video blindness cause not only distractions but cancels the viewer’s visual perception.

As Vintra’s founders explain, the device is not designed with the intention of replacing the investigator’s job, but it seeks to be a complementary tool that allows them to work more efficiently and focus attention on higher value tasks.

The future of Vintra

Nowadays, Vintra is formed by a team of 13 people. However, as Dr. Angel Sappa explained, their intention is to increase this number in the near future: “The future of Vintra is to continue growing and break into new markets. In fact, in medium term, we are evaluating the incorporation of new professionals in the field of machine learning”.

Moreover, Artificial Intelligence gets smarter and is able to recognize smaller differences the more it is presented with examples. Because of this, the device will keep improving, so that anything, from types of clothing or bags, to behaviours and emotions will be quickly and accurately searchable. Further still, it will be possible to digitally search real-time video and create alerts for people, objects, vehicles and behaviour.

For more information: https://vintra.io/

ORAIN: from small talk to machine talk

Nowadays, humans are in continuous contact with all kinds of machines. Washing machines, ticket sellers or snack vending machines, for example, are produced to make our tasks effortless and thus solve ordinary problems. However, the majority of these devices are absolutely passive, human – machine interaction being unidirectional and limited. So, what if these machines could communicate just like humans? What about if you could complain to them that your coin just got stuck – again!- or that your coffee isn’t quite of your taste that day?

That is precisely what Orain is trying to achieve. Born in 2005, Orain is a CVC spin-off and its aim is to introduce intelligence in our everyday life machines so that we can talk to them. Xavier Sans, one of its founders, explains that Orain was created almost by chance: “it emerged due to the demand to change a sector which was outdated and in urgent need of evolution. Only two years ago, there was not even the idea of paying on a machine with your smartphone. That’s when we saw a market niche in which we could grow”.

Their beginnings were hand in hand with another company, taking care of all the possible risks. Today, the team is configured by 9 employees (and rapidly growing) with different professional profiles such as developers and computer vision experts along with people in marketing and finance.

How does it work?

Orain allows communication between a vending machine and a smartphone through an application. Users can find information about its products such as ingredients, nutritional values or allergen components. Moreover, they can pay for the product instantly solely with their phones, be it by credit card or PayPal, and maintain a control of their expenses, thus providing an easier, quicker and enhanced user experience.

The benefits of this technology are also for clients. Whereas users obtain a highly positive shopping experience, vending operators receive detailed information about the state of their machines and relevant analytics: habits and consumption patterns, helping them to design effective marketing strategies and increase user loyalty. Furthermore, with this information, they can set up special campaigns or individual promotions in order to boost sales.

The innovative future of Orain

The concept Orain has designed goes far beyond payment methods and consumption analytics. It is thought to become a recurrent system platform with which to pay daily services such as car cleaning, washing machines, tickets, or periodical supermarket purchases. For now, Orain’s technology is operating in almost 300 vending machines and in 50 Office Coffee Services; a number that is rapidly increasing. Its technology will also be implemented in other sectors­ within the near future: “This is Orain’s strength. We want to develop a transversal application that allows us to gain users. We want one sole application to be used everywhere”, as stated by Xavier Sans.

Nevertheless, there’s still much to do. The startup is currently working in improving its services, with a special focus on Natural Language Processing: users speaking to the machine and obtaining an answer: “When you have a human interlocutor you can complain and do certain things that, in any other way, are impossible with machines. For this, we are trying to get close to human interaction”, Mr. Sans explains.

Orain within a human-machine interaction scenario

One of the challenges that Orain has to face is society’s reaction when faced with a human-machine interaction scenario. Sometimes, innovation within the AI field causes controversial opinions and, in some cases, generates fear and insecurity. In this way, the public acceptance of common machines equipped with intelligence can be, at the least, intimidating. “We are trying to make this transition the plainest possible. We have started with simple implementations, such as vending and OCS, but the intention is adding new intelligence step by step. We can’t be disruptive at the beginning because we can lose clients”, as pointed out by Mr. Sans.   

Another way to solve it is normalizing this kind of applications. As Xavier Sans predicts: “The solution is being the standard, which means being implemented massively. If we reach that point, it will be easier for people to comprehend and engage with our technology”.

For more information: orain.io

VISUAL TAGGING: Visual listening for social networks

Over 95 million photos are uploaded every day in Instagram with an approximate 4.2 billion likes per day according to statistics made by Brandwatch. Visual content, such as photos and videos, is gaining more and more popularity in social media, being the most visual networks the ones which are experiencing the greatest growth of users in recent years.

The digital world has meant a revolution for marketing and business strategies. Having a satisfactory presence on the Internet requires following adequate strategies on social networks, which are, today, one of the most important corporate identity symbols. To calculate the impact of a brand on social media, posts are commonly analysed in search of the brand. But they are searched by text. Only 20% of the photos shared within the networks has an accompanying text that identifies the brand. The rest, gets lost.

Visual Tagging, a CVC spin-off, was born in 2012 with the aim of solving this problem. With intelligent information systems that allow object detection in images, Visual Tagging’s technology is capable of recognising objects from catalogues, films, TV programs and social media pictures.

The technology behind

Visual Tagging does what is called ’visual social listening’: the analysis and extraction of information from images. Its technology is able to recognise a brand or logo within photos and videos posted in social media and detect the conversation that spurs around the brand.

Visual Tagging is mainly focused on Twitter and Instagram: “Nowadays, there is a generation that lives and expresses itself through Instagram and Twitter. Analysing these networks, companies can detect in real time hundreds and thousands of images in which their products are shown”, as pointed out by Dr. Xavier Roca, Visual Tagging’s founder and CEO. With this information, the brand’s Community Manager can interact with its community by liking and commenting posts and can also detect Brand ambassadors by analysing the profiles that share images with the brand’s logo more regularly. Moreover, companies can detect bad uses of their logo such as forgeries, and thus take legal measures.

Visual Tagging’s main costumers are well-known brands of consumer products, especially those within the food and beverage sector. They receive detailed statistics of the brand’s presence in social media extracted from both quantitative and qualitative analysis. A quantitative analysis gives them data such as how many photos with the brand’s logo have been uploaded, when they’ve been shared, which hashtags are usually used along the brand, in which environments, gender, geolocation and age range of the people who post those images.

Qualitative analysis provides an added value: it allows market research based on the interpretation of consumption habits and it contributes in the detection of other possible uses of the brand’s product. As Dr. Xavier Roca puts it: “With the market surveys we made of an ice cream brand, we realised that people gave different uses to the product. They shared photos using the ice cream as a birthday cake and also many people shared photos of their pets eating the product. This information gives the brand some creative ideas or clues about how to approach its next marketing campaign”.

A great boost for small companies

Another Visual Tagging service is to increase the brand’s community in social networks. This option is especially thought for all those small companies and influencers whose main objective is to get more followers and popularity or for those who want to promote their products through social media. To achieve this, Visual Tagging takes some hashtags and key words related with the brand’s product and automatically delivers likes to some of these photos. Doing this, they catch the user’s attention and, most undoubtedly, a new follower: “Since the number of daily likes on Instagram is limited, it is essential to select correctly the ones that have more probabilities to be future followers when it comes to deliver likes”, Dr. Xavier Roca stated.

With this method the follower’s growth is gradual and steady, taking its time. Unlike the known as ‘click farms’, which offer the purchase of large amounts of bots that will increase immediately the number of followers, followers achieved with Visual Tagging will have followed the account by their own decision: “We probably don’t have a level of follower’s growth as fast as other technologies but we assure that the followers will be real users. The increase of followers with bots is totally impersonal and will not provide any interaction between the company and its audience. On the contrary, the followers reached with Visual Tagging will be people who are really interested in the brand’s products, which means that they are more likely to buy or rent them”, clarified Dr. Xavier Roca.

The still unknown power of social media

It’s a fact that the digital world has given new promotion channels to companies, big or small, and that it has provided them with more facilities when interacting with their customers. Because of this, according to a study carried out by SAGE, three out of four SMEs already are present in social networks.

As Dr. Xavier Roca explained, Visual Tagging team wants to maintain a close contact with their customers in order to have insights into what their main needs are and to know which are their opinions: “Our technology usually catches the attention and surprises our customers. They are very shocked when they realised all the things they can know with our statistics. Nevertheless, Visual Tagging is still a complex technology and sometimes it is difficult to understand the real importance of the information that social networks provide”.

Social networks, although not a novelty any more, aren’t exploited to their full potential by companies as a communication tool. As Dr. Xavier Roca cleverly exposes, a good strategy in social networks will allow companies to stand out from the lot: “The companies that analyse the trends of social networks and their position in them, are the ones that create strategies that will allow them to go one step ahead of the rest”.  

For more information, visit their website here: https://visual-tagging.com/