Application of Graph Structures in Computer Vision Tasks

Abstract

On the one hand, the solution of computer vision tasks is associated with the development of various kinds of images or random fields mathematical models, i.e., algorithms, that are called traditional image processing. On the other hand, nowadays, deep learning methods play an important role in image recognition tasks. Such methods are based on convolutional neural networks that perform many matrix multiplication operations with model parameters and local convolutions and pooling operations. However, the modern artificial neural network architectures, such as transformers, came to the field of machine vision from natural language processing. Image transformers operate with embeddings, in the form of mosaic blocks of picture and the links between them. However, the use of graph methods in the design of neural networks can also increase efficiency. In this case, the search for hyperparameters will also include an architectural solution, such as the number of hidden layers and the number of neurons for each layer. The article proposes to use graph structures to develop simple recognition networks on different datasets, including small unbalanced X-ray image datasets, widely known the CIFAR-10 dataset and the Kaggle competition Dogs vs Cats dataset. Graph methods are compared with various known architectures and with networks trained from scratch. In addition, an algorithm for representing an image in the form of graph lattice segments is implemented, for which an appropriate description is created, based on graph data structures. This description provides quite good accuracy and performance of recognition. The effectiveness of this approach based, on the descriptors of the resulting segments, is shown, as well as the graph methods for the architecture search.