Artificial Intelligence (AI) technologies have been used in digital forensic science to resolve disputed documents where one or more human experts would normally be contacted. The purpose of intelligent systems based on printer identification is determined printer created a specific document. Most solutions based on a text-dependent approach may be insufficient in certain scenarios. No study on text-independent based on various word images printed from various laser printer models has been done, as far as the researchers are knowledgeable. As a result, we classify the laser printer models based on the various gray scale word images. 40000-word images of four laser printer models are included in the collection. To classify the different laser printer models, the LBP (Local Binary Pattern) with KNN (K-Nearest Neighbors) and the cubic SVM (Support Vector Machine) classifiers are employed. The deep learning CNN (Convolution Neural Network) model is also used to determine the laser printer models. The experimental results of textural features and the CNN architecture are compared to recent work from a literature survey. We obtained high accuracy from K-NN and cubic SVM classifiers of 97.2% and 97.9%, respectively, and 94.3% accuracy in the CNN model.