Video compression by hybrid neural networks (CNN+RNN(LSTM)) algorithm and generative adversarial network (GAN) algorithm
Sabah Mohammed, Waleed Abdullah Araheemah · Al-Noor Journal of Engineering Management and Computer Science · 2025
As the need for high-quality video increases it has become necessary to develop smarter compression methods. Artificial neural networks (ANNs) have emerged as an effective tool in this field enabling them to extract the most important features from video and minimize temporal and spatial redundancy resulting in an efficient and high-quality compressed representation. Some of the most prominent models used are: Hybrid neural networks (CNN+RNN(LSTM)) Hybrid neural networks combine convolutional neural networks (CNNs), recurrent neural networks (RNNs), and especially long short-term memory (LSTM) units to extract spatial and temporal features from data, GAN, GANs compress video files while maintaining high perceptual quality. They encode each frame into a compressed latent representation, allowing for realistic reconstruction. This method is efficient, making it ideal for video transmission applications where perceptual accuracy is more important than perfect pixel accuracy. These techniques enable efficient compression without significant quality loss, representing a paradigm shift in modern video compression techniques. After analyzing the results the highest compression ratio (94.75) was achieved by compressing using the GAN algorithm. The highest PSNR (36.08) was achieved by CNN+RNN(LSTM) compression.