Developers Club geek daily blog

Example of implementation of methods of processing and image understanding on Android

1 year ago
Being engaged in applications programming under Android OS there are interesting ideas which want to be tried, or there is some set of theoretical knowledge and they want to be put into practice, from set of these factors and there was an idea of the described project.

There are many articles about text recognition, about computer sight and about separate algorithms of recognition. In the same publication attempt of implementation of the task connected with finding of a key word on the image of the text that is able to afford to find, for example, the necessary place for reading any text in DjVu without recognition of the text is shown.

Example of implementation is presented in the form by application Android, and the source image is the text screenshot, with the entered key word, different algorithms of processing and image understanding are applied to a solution of a task.

Read more »


Work on design of space reptiloid: wandering on labyrinths of opportunities

1 year ago


The normal such reptiloidny race arising from abysses of deep space. Bang-bang from the laser weapon from all boards! Then rapprochement and a boarding, in completion of attack bloody slaughter onboard the seized vessel. Reptiloida – men of his word: told "all we will cut", means all will cut who would doubt. Also are dissolved in frosty blackness, only saw them.

However, investigation informed. If to open the game Encyclopedia, it will become clear:

Exact coordinates of basing of a civilization of Uchcha-Ta are unknown. It is considered to be that it is the planet Drro-Adda (so-called Planeta-Mat) of planetary system around the W-maiden (star accumulation TDD67, the "spread jellyfish" type, a spectral class is unknown).

So, the residence is set: after piracy attack on the peace ships of a reptiloida disappear on native Planetomateri.

And what it gives me as to the art director in sense of hints on design of the character? And anything.

Read more »


Intel RealSense SDK and Oculus Rift DK2

1 year, 1 month ago

In this article technical details and problems which developers can face during creation of the software solutions using Intel RealSense SDK for Windows * and points (typeface) of Oculus Rift* are described. We begin with the overview of a set Oculus Rift Development Kit 2 (DK2), then we will pass to some problems arising by applications programming, working with several infrared cameras. In this article the description of integration of Intel RealSense SDK and Oculus Rift is also provided in the Unity project * 5.

Read more »


Nonlocal algorithm for smoothing of images

1 year, 1 month ago
Disposal of the image of noise – one of fundamental operations of computer sight. Smoothing algorithms are applied almost everywhere: they can be both independent procedure for improvement of the photo, and the first step for more difficult procedure, for example, for object recognition on the image. Therefore there is a huge set of methods of smoothing, and I would like to tell about one of them differing from the others in good applicability on textures and images with a large number of identical parts.

Under a cat there are a lot of pictures, is accurater with traffic.

Read more »


As we made ABBYY FineReader, or the history which occurred 20 years ago

1 year, 1 month ago
ABBYY FineReader – the program for recognition of texts which in Russia is known to much since student's times. This year FineReader is performed 22 years, it is a little younger than our Lingvo dictionary. How so left that together with the dictionary young programmers from BIT Software (at that time ABBYY was called quite so) were engaged in recognition of texts? And what helped Fayn to become one of the programs which are most recognized in the market?

Actually, everything is very logical. If not Lingvo, FineReader'a could and not to be. Everything began with a large-scale and ambitious complex under the name Lingvo Systems. With its help the person could scan the text in one language, pass it through the program and get translation, however, draft, but for understanding of its sense was enough.

Read more »


How to squeeze a flat cat

1 year, 1 month ago
Once during an ice cold winter time … exactly a year ago, we had a nontrivial task. There is a screen on electronic ink, there is a MHz processor 16 (yes, in the built-in electronics, especially ultralow energy consumption, also such meet) and at all there is no memory. Well, i.e. kilobytes of 8 RAM and 256 Flash. Kilobytes, Carle. And it is necessary to push several images in these sad kilobytes 800х600 in four shades of gray. Having quickly multiplied in mind 800 on 600 and on 2 bits per pixel we receive 120 thousand bytes. Does not get a little. It is necessary to squeeze.

So we saw a task: "how to squeeze a flat cat"? Why cat? Yes because on cats tested on what to check black-and-white pictures. Not on dollar banknotes.

Read more »


Calibration of Kinect v2 by means of OpenCV on Python

1 year, 1 month ago
Not so long ago we began couple of projects in which the optical system with the channel of range is necessary, and decided to use Kinect v2 for this purpose. As projects are implemented on Python, for a start it was necessary to force to work Kinect from Python, and then to calibrate it as Kinect from a box enters some geometrical distortions to frames and gives centimetric errors in determination of depth.

Before I never dealt neither with computer sight, nor with OpenCV, nor with Kinect. The exhaustive instruction as to work with all this economy, I did not manage to find too so as a result it was necessary to tinker rather. And I decided that I not superfluous will systematize the got experience in this article. Perhaps, it will be reasonably useful for some sufferer, and still we need popular article for show in the reporting.

image

Read more »


Whether it is easy to recognize information on the cash card?

1 year, 1 month ago


When we communicate with our customers, being specialists in this area, actively we use the corresponding terminology, in particular the word "recognition". At the same time the listening audience which is brought up on Cuneiform and FineReader often puts in this term a problem of comparison of the cut image section to some number (a character code) which is solved neural network approach today and is not the first stage in a problem of recognition of information. At the beginning it is necessary to localize a card on the image, to find information fields, to execute segmentation on characters. Each listed subtask from the formal point of view is an independent problem of recognition. And if for training of neural networks there are proved approaches and tools, then in problems of orientation and segmentation every time is required an individual approach. If it is interesting to you to learn about approaches which we used at a solution of a problem of recognition of the cash card, then welcome under kat!

Read more »


Detailing, reflections and post-effects in GTA V

1 year, 1 month ago

From the translator:

This publication is continuation of the material "As There Is a Rendering of a Frame in GTA V"
. Now the author considers questions of detailing, lighting and post-processing of a frame. Pleasant reading.


Detail level


If we speak about absolute benefits of Rockstar over competitors, then indicators of the detail level of products of the company, definitely, above any praises. Los-Santos is the whole galaxy of various scenes of different extent of detailing / poligonalnosti, and all data are broadcast in real time and it for a minute does not block the loading screen. Just takes the breath away!

Fires of the night city


All sparks which are visible in the distance, real. You can closer approach and will see lamps which radiated light at distance.

With such statement Aaron Garbut, one of founders and art directors of Rockstar North, acted shortly before game release on PS3.

Whether so it? Let's consider here such night scene:

image
Sparks "Before"
Carefully! Traffic!

Read more »


News called to the road: the superfast power effective optical coprocessor for big data

1 year, 1 month ago


Last week Phys.org burst in news: the startup of LightOn offered alternative to central processors (CPU) and graphic processors (GPU) of a solution of tasks of the analysis of big data. The group of authors is based in Pierre and Marie Curie University, Sorbonne and all other correct places in France. The solution is based on optical analog data handling "with light speed". Sounds interestingly. As in the press release there were no scientific and technical details, it was necessary to look for information in patent databases and on the websites of universities. Results of investigation under a cat.

Read more »