The development of a decision support system for evaluating a fashionable image of a person is described. This is done by selecting a set of visual attributes from an image and comparing this set with "fashionable" patterns. Fashion patterns are set by the user himself. These are images that are defined in the system as reference images. This paper provides an overview of decision-making methods, analyzes the relevance of decision-making systems in different spheres of society. The algorithm of the program and the tools with which the image is first preprocessed are considered, then the visual attributes are highlighted. The method of making decisions for different types of attributes is given. The comparison of colors in HSL notation is considered.

Keywords: decision support system, decision making methods, machine learning, Python, model learning, image, fashion, information and analytical system, k-means method

The article discusses the developed model for recognizing a clothing brand by image. The model not only predicts the type and brand of clothing, but can also determine their similarity. At the initial stage, a dataset was collected containing images of clothing from various brands with a total volume of 9,000 images. In this work, the ViT (Vision Transformer) neural network architecture was used, a model for working with images, which was presented by experts from Google Brain. The vit-base-patch16-224 model acted as a representative of the transformer architecture. Before training, all images were converted to black and white, and data augmentation was also used: image rotation by a random angle, mirror transformation. All photos have been normalized – pixel coordinates have been adjusted to the interval [0,1].

Keywords: neural network, model, machine learning, Vision Transformer, fashion industry, clothing brand prediction, clothing type prediction, brand similarity determination