Blog

Today we’ll be talking about an approach that can be used to improve the quality of panorama image stitching. There is a widely used method of panorama stitching for images of two-dimensional objects, but it has its disadvantages. That’s why we’d like to propose our own improved version of this…

As you already know, we specialize in image processing here, at Smart Engines. Not so long ago we published an article about binarization of fine-structure tomographic images where we attempted to explain what the x-ray tomography method is about. Today we’ll continue talking about the possible challenges that arise when…

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 our article will be focused on two of our favorite subjects: computed tomography (CT) and the Russian-made processor called Elbrus. We’ll talk about the difference between an X-ray and a CT scan result and explain why such a large and serious piece of machinery as a tomograph could really…

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…

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…