Image classification based on bag of visual graphs

Silva, Fernanda B.; Goldenstein, Siome; Tabbone, Salvatore; Torres, Ricardo da Silva

doi:10.1109/icip.2013.6738888

Cited by 21 publications

(17 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [4], the authors propose the bag of visual graphs (BoVG), a paradigm to describe the spatial relations of visual words using a codebook of visual-word layouts, in the form of graphs. This representation provides a vector for encoding imagse which includes both the frequency of the occurrence of visual words and their spatial relationships.…”

Section: Related Workmentioning

confidence: 99%

Bag of ARSRG Words (BoAW)

Manzo

Pellino²

2019

MAKE

View full text Add to dashboard Cite

In recent years researchers have worked to understand image contents in computer vision. In particular, the bag of visual words (BoVW) model, which describes images in terms of a frequency histogram of visual words, is the most adopted paradigm. The main drawback is the lack of information about location and the relationships between features. For this purpose, we propose a new paradigm called bag of ARSRG (attributed relational SIFT (scale-invariant feature transform) regions graph) words (BoAW). A digital image is described as a vector in terms of a frequency histogram of graphs. Adopting a set of steps, the images are mapped into a vector space passing through a graph transformation. BoAW is evaluated in an image classification context on standard datasets and its effectiveness is demonstrated through experimental results compared with well-known competitors.

show abstract

Section: Related Workmentioning

confidence: 99%

Bag of ARSRG Words (BoAW)

Manzo

Pellino²

2019

MAKE

View full text Add to dashboard Cite

show abstract

“…However, those approaches consider the extracted features used to describe images (e.g., Bags-of-Visual-Words / BoWs) as spatially independent from each other. The problem of using bag-of-graphs instead of BoWs has already been mentioned in [2,18,21] for satellite image classification and biological applications. However, none of these papers provide a general graph representation nor a graph mining algorithm to extract the patterns.…”

Section: Related Workmentioning

confidence: 99%

GriMa: A Grid Mining Algorithm for Bag-of-Grid-Based Classification

Deville

Fromont

Jeudy

et al. 2016

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. General-purpose exhaustive graph mining algorithms have seldom been used in real life contexts due to the high complexity of the process that is mostly based on costly isomorphism tests and countless expansion possibilities. In this paper, we explain how to exploit gridbased representations of problems to efficiently extract frequent grid subgraphs and create Bag-of-Grids which can be used as new features for classification purposes. We provide an efficient grid mining algorithm called GriMA which is designed to scale to large amount of data. We apply our algorithm on image classification problems where typical Bagof-Visual-Words-based techniques are used. However, those techniques make use of limited spatial information in the image which could be beneficial to obtain more discriminative features. Experiments on different datasets show that our algorithm is efficient and that adding the structure may greatly help the image classification process.

show abstract

“…In both cases, produced images are relatively “heavy.” Wang and Oates discuss time series representation based on Gramian Angular Field and Markov Transition Field are considered. Nima Hatami apply Recurrence Plots. In both cases, images are colored.…”

Section: Introductionmentioning

confidence: 99%

Lagged encoding for image‐based time series classification using convolutional neural networks

Jastrzębska

2020

Statistical Analysis

View full text Add to dashboard Cite

Time series classification is a thriving area of research in machine learning. Among many applications, it is frequently applied to human activity analysis. Time series describing a human in motion are ubiquitously collected via omnipresent mobile devices and can be subjected to further processing. In this paper, we propose a novel, deep learning approach to time series classification. It is based on a lagged time series representation stored as images andConvolutional Neural Network used to image classification. We present a comparative study on different variants of lagged time series representation and we evaluate their effectiveness in a series of empirical experiments. We show that the developed method provides satisfying classification accuracy. The proposed image-based time series encoding is less resource-consuming than encodings used in other image-based approaches to time series classification. It is worth to emphasize that the proposed time series encoding conceals original time series values. Images are saved without scales and the order of observations cannot be reconstructed. Thus, the method is particularly suitable for systems that need to store sensitive information. K E Y W O R D S classification, convolutional neural network, image recognition, time series 1 Stat Anal Data Min: The ASA Data Sci Journal. 2020;13:245-260. wileyonlinelibrary.com/sam

show abstract

Image classification based on bag of visual graphs

Cited by 21 publications

References 22 publications

Bag of ARSRG Words (BoAW)

Bag of ARSRG Words (BoAW)

GriMa: A Grid Mining Algorithm for Bag-of-Grid-Based Classification

Lagged encoding for image‐based time series classification using convolutional neural networks

Contact Info

Product

Resources

About