Development of the Image Recognition Application - Computools

hello world

Screen 1

Development
of the Image Recognition
Application

industry: Software & Hi-Tech

One of the most interesting properties of the human brain is the ability to respond to an infinite number of environmental stimuli through unique reactions. Perhaps, for precisely this perception allowed people were able to achieve the highest level of living matter existence, which is expressed in the ability to think and actively reflect on the objective world in the form of images, concepts, judgments, etc. That’s why our customer decided to discover a new truth: not only humans can recognize external incentives and respond to them. With the help of our team of developers, he proved that even smartphones have excellent perception.

Machine Learning in the innovative project

To demonstrate how modern technologies can percept real objects, we developed a special project based on Machine Learning. It’s an Android application which recognizes meters, and captures readings and serial numbers via a mobile phone camera. A system captures the readings and a serial number, and then tries to find a pre-registered user in the database to add a record about fixation of the readings to the user's history. Using this application, it’s possible to make a registry of subscriber’s readings just in a few simple steps. All you need is a mobile phone with a camera which can distinguish the details in poor lighting.

Slide 1

How does this app work?

Phone 1
  • The application recognizes the readings and serial numbers of any types of meters by editing configuration files.
  • One of the main features is that a system performs the recognition process in real time. In other words, you don’t need to take photos, just run the application and point a camera (just like QR code). This ensures that during recognition process the application determines the same readings on the meter for each frame.
  • There is the ability to view a detailed history of fixing the readings for each user. According to the history, you can create a histogram of the use of electricity between the the registry of the readings.

Additional features

  • The app supports geolocation services for confirming a location of "shooting" in order to avoid falsification of results.
  • All cut out image frames with the actual photo of the readings and a serial number are stored.
  • The project has a unique design with a great variety of custom components.

Machine Learning Engineering Challenges

The process of perception is very complex and not fully understandable even for humans. So, try to imagine how difficult it is to learn a machine which hasn’t a brain. Our team of developers accepted a great challenge!

It was necessary to learn the networks to detect a recognition object and serial number on the image, and select the character area. Then, the app should confirm what each metric belongs to a particular person. The client also wanted to introduce a feature of app profiling to work with different meters.

Solutions

We used the method of contour analysis that narrows the number of meters, which the application can potentially work with, to presence of a key contour ("anchor"). It is an object that has a unique contour (in most cases, a black box) around the numbers with the readings.

Based on the geometry of the anchor, we implemented a technology which calculates the location of the serial number and accurately recognizes it.

Registering the location of a particular meter in the database, tracking the shooting location, and comparing all known meter data, the app can easily determine the owner of a certain meter.

We transferred all the parameters, which the recognition process may depend on, to the configuration file, and determined parameters for each supported meter with the possibility of choosing an operational meter. This procedure allowed us to introduce a useful app profiling feature.

Eventually, we overcame all the challenges thanks to our perseverance and usage of the most innovative technologies like Machine Learning!

Happy Customer

As you see, we developed a very useful Android application based on Machine Learning which can easily recognize meters, captures readings and serial numbers. Our customer provided a society with the ability to receive important data on various meters very quickly and precisely. Thanks to our effective cooperation, the truth about unlimited cognitive possibilities of machines, particularly in regards to their excellent perception, was discovered, and the client revenue was increased by 42%!

Screen 2

Project technology

Let’s turn your incredible idea into code right now!
The name can't contain symbols and digits

Our team is ready to help you!

The name can't contain symbols and digits

You can contact us right now:

Thank You!

Your message has been sent!

Computools managers will contact you within 24 hours

ok

Very Sorry!

Your message hasn't been sent!

Please, try to send email later

ok