Graph-based image gradients aggregated with random forests

Almeida, Raquel; Kijak, Ewa; Malinowski, Simon; Patrocínio, Zenilton Kleber G. do; Araújo, Arnaldo A.; Guimarães, Silvio Jamil Ferzoli

doi:10.1016/j.patrec.2022.08.015

Cited by 5 publications

(3 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The pipeline takes the colored images and computes the graph gradient (GIG [26]) without any additional preprocessing. Next, a structured grid obtains the adjacency relation 4adjacency.…”

Section: Experiments Main Results and Discussionmentioning

confidence: 99%

“…We list the main contributions in terms of publications: (i) Learning framework on graph attributes for image processing (Published in SIBGRAPI'22 -Awarded as best paper [34]) (ii) Extended formalism on graphs attributes exploring more extensive input areas through region adjacency graphs and changes driven by the model mechanics (Published in PRL [26]). (iii) Learning framework operating directly on the hierarchical data, focusing the formulations solely on the structural components of the hierarchies (submitted).…”

Section: B Main Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

Learning on graphs and hierarchies

Almeida,

Kijak,

Malinowski

et al. 2023

Anais Estendidos Da XXXVI Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2023)

View full text Add to dashboard Cite

Hierarchies, as described in mathematical morphology, represent nested regions of interest that facilitate high-level analysis and provide mechanisms for coherent data organization. Represented as hierarchical trees, they have formalisms intersecting with graph theory and applications that can be conveniently generalized. However, due to the deterministic algorithms, the multiform representations, and the absence of a direct way to evaluate the hierarchical structure, it is hard to insert hierarchical information into a learning framework and benefit from the recent advances in the field. This work aims to create a learning framework that can operate with hierarchical data and is agnostic to the input and the application. The idea is to study ways to transform the data to a regular representation required by most learning models while preserving the rich information in the hierarchical structure. The methods in this study use edgeweighted image graphs and hierarchical trees as input, evaluating different proposals on the edge detection and segmentation tasks. The model of choice is the Random Forest, a fast, inspectable, scalable method. The experiments in this work are an outline of the original study in the related Ph.D. thesis. They demonstrate that it is possible to create a learning framework dependent only on the hierarchical data that performs well in multiple tasks.

show abstract

“…The pipeline takes the colored images and computes the graph gradient (GIG [26]) without any additional preprocessing. Next, a structured grid obtains the adjacency relation 4adjacency.…”

Section: Experiments Main Results and Discussionmentioning

confidence: 99%

Section: B Main Contributionsmentioning

confidence: 99%

Learning on graphs and hierarchies

Almeida,

Kijak,

Malinowski

et al. 2023

Anais Estendidos Da XXXVI Conference on Graphics, Patterns and Images (SIBRAPI Estendido 2023)

View full text Add to dashboard Cite

show abstract

“…In [16] the authors used a gradient calculation method based on weighted graphs combined with a Random Forest algorithm. Paper shows that the image gradients constructed with the method proposed can be used as an alternative to the edge maps methods and described an interesting approach of training Random Forest algorithm on gradient-based information.…”

Section: Related Workmentioning

confidence: 99%

Image Classification of Leukemic Cells Using Invariants of Triangle-Free Graphs as Synthetic Features

Muzalevskiy,

Torshin

2024

IEEE Access

View full text Add to dashboard Cite

Development of efficient methods of the cellular image processing is an important avenue for practical application of modern artificial intelligence techniques. In particular, practical hematology requires automatic classification of images with or without leukemic (blast) cells in peripheral blood smears. This paper presents a new approach to the problem of classification of such cellular images based on graph theory, XGBoost algorithm and convolutional neural networks (CNN). Firstly, each image is transformed into a weighted graph using gradient of intensity. Secondly, a number of graph invariants are computed thus producing a set of synthetic features that is used to train machine learning model based on XGBoost. Combining XGBoost with CNN further increases the accuracy of leukemic cell classification. Sensitivity (TPR) and Specifity (TNR) of the XGBoost-based model were 95% and 97% accordingly; ResNet-50 model showed TPR of 95% and TNR of 98%. Combined use of the XGBoost-based and the ResNet-50 models demonstrated TPR of 99% and TNR of 99%.

show abstract

Random forest clustering for discrete sequences

Jiang,

Wang,

et al. 2023

Pattern Recognition Letters

View full text Add to dashboard Cite

Graph-based image gradients aggregated with random forests

Cited by 5 publications

References 23 publications

Learning on graphs and hierarchies

Learning on graphs and hierarchies

Image Classification of Leukemic Cells Using Invariants of Triangle-Free Graphs as Synthetic Features

Random forest clustering for discrete sequences

Contact Info

Product

Resources

About