Cases. Digital processing of signals, images, audio and video
Highlight of words in audio signal is a part of large project. This task is the first step of speech recognition systems also known as speech-to-text systems. We needed to create algorithm which can be able to highlight words in audio stream. Algorithm should split the signal on parts, each of them represents one of words in English.
In most of our digital signal processing projetcs we use dinamic link libraries (DLLs) written on C++ or C#. It gives to us ability to build our systems using modules architecture. We've developed this software to test and explore additional digital signal processing libraries.
For one of our projects was needed tool which can determine type of shot on video frame (close-up/medium/long shot and etc). The main idea was in using OpenCV to detect faces and calculate space which they hold on image. We've developed own metric system to determine type of shot using information of number and space of faces on the image.
In previous article we wrote about tool which can determine type of shot on video frame (close-up/medium/long shot and etc) using OpenCV. But default settings was not enough to solve our tasks.
For one of our projects was needed algorithm which can process music audio signal to detect points where music changes (split music on segments).
We have developed several projects for video processing. In one of them needed dynamic link library (DLLs) written on C++ which can implement several video effects such as negative, swirl and some color filters.
In video processing algorithms sometimes needs to determine what type of motion was detected. We was need to classify two types of motion: motion of object and motion of camera.