Blog

We remembered the algorithms that were actively researched in the 80s and 90s as a part of a structural texture rendering and are rarely brought up when it comes to digital image processing these days.

Today we’ll add one more article to our classic collection of articles about the methods of image processing and image recognition and how these methods are applicable in practice. We’ll be discussing the price tag recognition problem (just the regular price tags that we see in the stores all the…

Today we’d like to delve into a very interesting problem that we’ve been working on since we started researching document recognition in a video stream — the problem of finding the optimal stopping point. Figure 1. Images of ID-document text field in video frames As many of you know, one…

Nowadays, artificial neural networks are at the core of various AI methods. At the same time, thanks to a huge number of distributed computing frameworks, data sets and other how-tos, new neural network learning models are in great request and researchers worldwide easily build new effective, secure algorithms without delving…

Smart ID Engine 1.0.0 New recognition engine for identity documents. Standing on the shoulders of Smart IDReader, and looking far beyond. * Introducing Face matching AI; * Introducing document liveness detection; * Introducing Indo-Arabic language family recognition (Arabic, Persian, Urdu, and more); * Modular structure of the recognition engine which…

Today we’d like to talk about optical recognition again. A simple recognizer model of a cascade classifier will be the main subject of our article. The cascade classifier is used in the popular Viola-Jones framework. The sad part is that despite the vast amount of articles, no one studied cascade…

In this article, we give a brief description of the design of our identity document optical character recognition system and the algorithms that are used at different stages of the process. If you’d like to know how the Smart ID Engine system works, please keep reading. The idea of using a mobile…

Binarization is a classic image processing problem. Oftentimes it is used to simplify the data and speed up the subsequent processing which doesn’t seem vital nowadays. However, when analyzing porous materials, binarization becomes essential because in this case, a data model doesn’t involve an intermediate state between a hollow pore…

How the lack of an entrance tickets scanner slows the queue It is common knowledge that the biggest challenge public events at large open areas are facing today is the inevitable queues at the entrance. The queue usually occurs when a large number of visitors pass through narrow turnstiles and checkpoints, where…