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.

Unveiling the Power of Graph Neural Network for Intelligent Analysis of Objects

“…Convolutional neural network has Weak variance and even with the change in brightness it affects the final output,graph overcomes this effect [3]. Graph attention network (GAT) is used to find hidden data concerning the relationship between objects' semantic contexts [9] By exploiting the data in the network itself, node features may be learned, and node representation can be transferred to the classification task to enhance model performance [7].…”

“…A new era in computer vision (CV) has emerged as a result of deep learning-based techniques, in which algorithms may be trained to carry out a variety of tasks, from object recognition to position detection. There are numerous CNN-based object identification techniques that have produced excellent results for feature extraction on a single item region when looking for items, followed by object detection [1][2] [3]. In other words, these techniques typically primarily focus on local information and disregard the relationships between the items and between objects and scenes.…”

Skew Class-Balanced Re-Weighting for Unbiased Scene Graph Generation

“…Of great interest are tasks related to classifying and detecting objects by classical neural networks [11][12][13][14][15]. With the development of computer vision, graph neural networks [16][17][18][19][20][21][22] and multimodal text and image models [23][24][25][26][27][28] have also been intensely investigated. However, there is less information on Scene Graph Generation (SGG) models in the literature.…”

Multicriteria Assessment Method for Network Structure Congestion Based on Traffic Data Using Advanced Computer Vision

“…Quantitative criteria include: distance, travel time, workload, cost of travel and safety. Qualitative criteria are determined subjectively based on expert opinions and relate to features or objects of the road [38][39][40][41][42][43][44].…”