Akademik Veri Yönetim Sistemi
JOURNAL OF POLYTECHNIC-POLITEKNIK DERGISI, cilt.27, sa.5, ss.1903-1911, 2024 (ESCI)
The furniture sector is developing and progressing rapidly today. The difficulty of choosing among many different designs and styles in the furniture industry poses a problem for consumers and sellers. The aim of the paper is to solve the problems faced by consumers and furniture industry professionals with the classification of furniture images. Based on this objective, this paper addresses the use of artificial intelligence techniques for the classification of furniture images. Machine learning algorithms and neural networks are used to automatically classify furniture images. In this paper, five different convolutional neural network architectures are used for the classification of furniture images: Alexnet, VGGNet-19, DenseNet-201, Squeezenet1.1 and ResNet-152. Using these architectures, VGG-19 and ResNet-152 achieved 98.87% classification accuracy. Five different furniture categories (bed, chair, sofa, swivel chair and table) are classified with VGGNet-19 and ResNet-152 architectures with an ROC (Receiver Operating Characteristic) value of 99.99%. In addition, it is reported that faster and more accurate results are obtained by using the transfer learning approach. SqueezeNet1.1 architectures provided an average classification accuracy of 97.07%, while the Alexnet model (94.15%) achieved the lowest accuracy. By using deep learning algorithms, the features of images are extracted and classified. This study shows that the technology has the potential to deliver a smarter and user-centered shopping experience. It also provides a furniture classification method that can provide a competitive advantage by increasing efficiency in furniture production and sales. The results obtained in the study show that CNN architectures used with transfer learning method are effective in analyzing and classifying furniture images.