Design of Art Style Classification Algorithm for Soft Furnishings Based on Deep Learning

Soft decoration is an indispensable part of interior design and decoration at this stage, which can give new life to indoor space to a certain extent, enrich the layering of space and play a good role in adjusting mood. Based on DL(Deep Learning), this paper designs an art style classification algorithm for soft furnishings. The research results show that the three algorithms have good performance on a variety of different data sets. The algorithm in this paper is applied to multiple sub-class data sets instead of a whole data set, which avoids the operation of largescale data sets and saves some time. The adaptive optimization process of the algorithm in this paper takes up a lot of time and classifier learning time. In the future, the optimization algorithm should be improved to further improve the efficiency of the classifier. According to the characteristics of neural network, it is assumed that the output of the encoder is the same as the input, and the hidden layers of neural network are obtained by adjusting parameters, which are regarded as compressed representations of input data, thus achieving the purpose of reducing the dimension of sample data.