Abstract

Within the confines of this article, we advocate for the utilisation of wavelet transforms in teleconferencing environments as a means of improving the overall video quality. This can be accomplished by increasing the number of participants in the conference. The fundamental concept behind this is to use a collection of high-quality, professionally captured facial images as examples for the purposes of training, and the collection should include as many unique faces as is practically feasible. Images are often changed to make the skin tones and contrast of the facial regions more appealing to the viewer gaze. Adjustments are made to the colouring of a new picture so that the colour distribution in the face region will be comparable to that of the training pictures. This method is very effective when it comes to computation, and it also makes it much simpler to automate the process of making enhancements. The results of user research experiments are presented here, which demonstrate how the suggested method can improve the viewer perception of the video overall quality. The experiments were carried out to determine how the suggested method can accomplish this.