From Pixels to Titles: Video Game Identification by Screenshots using Convolutional Neural Networks

arXiv:2311.15963v2 Announce Type: replace
Abstract: This paper investigates video game identification through single screenshots, utilizing five convolutional neural network (CNN) architectures (MobileNet, DenseNet, EfficientNetB0, EfficientNetB2, and EfficientNetB3) across 22 home console systems, spanning from Atari 2600 to PlayStation 5, totalling 8,796 games and 170,881 screenshots. Confirming the hypothesis, CNNs autonomously extract image features, enabling the identification of game titles from screenshots without additional features. Using ImageNet pre-trained weights as initial weights, EfficientNetB3 achieves the highest average accuracy (74.51%), while DenseNet169 …

abstract architectures arxiv cnn convolutional convolutional neural network convolutional neural networks cs.cv cs.ne five game games home identification mobilenet network networks neural network neural networks paper pixels playstation playstation 5 systems through type video video game