Dynamic Texture Classification Using Deterministic Partially Self-avoiding Walks on Networks

Ribas, Lucas Correia; Bruno, Odemir Martinez

doi:10.1007/978-3-030-30642-7_8

Cited by 4 publications

(1 citation statement)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is a classic line of research in the Scientific Computing Group where many texture recognition methods have been developed in the last decade. (16,19,131,154,(199)(200)(201)(202)(203)(204)(205)(206)(207) We discussed this approach in more detail in Chapter 2, Section 2.3.3.1. Here, we describe a new method focusing on one of the latest developments of the approach, (19) where a multilayer network is built for trichromatic (RGB) images.…”

Section: Spatio-spectral Network (Ssn)mentioning

confidence: 99%

Patterns and randomness in networks for computer vision: from graphs to neural networks

Scabini

View full text Add to dashboard Cite

To my parents, brothers, grandparents, uncles, and cousins for the familial love and occasional support.To Marilia for her love, companionship, and support, and for all the moments we shared through our journey together.To my advisor, Odemir Martinez Bruno, for the guidance, support, trust, and collaboration for the past seven years. Working together has been an incredible journey and a fundamental part of my professional development.To my co-advisor, Bernard De Baets, firstly for the supervision during my stay at Ghent University, and also for becoming part of the development of this thesis as a whole. It was a great pleasure meeting and working with such an esteemed scientist.Special thanks to my cats, Puck, Juanita, and Gwyn, for their active participation in developing this thesis by constantly walking over the keyboard. They deserve all the credit for any lost characters or weird typos in the text.To all colleagues, professors, and workers from the São Carlos Institute of Physics (IFSC-USP), the Institute of Mathematics and Computer Science (ICMC-USP), the Faculty of Bioscience Engineering (UGent), and the Scientific Computing Group (SCG), who contributed, directly or indirectly, to my academic education and the development of this thesis. I am deeply grateful for the discussions, knowledge exchange, and casual moments that were part of my life during the Ph.D.

show abstract

Section: Spatio-spectral Network (Ssn)mentioning

confidence: 99%

Patterns and randomness in networks for computer vision: from graphs to neural networks

Scabini

View full text Add to dashboard Cite

show abstract

Efficient bat-inspired block matching algorithm with novel motion energy directional histograms for dynamic texture fast recognition

Bida

Aouat

2023

Multimed Tools Appl

View full text Add to dashboard Cite

Dynamic Texture Classification Using Directional Binarized Random Features

Zhao

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Dynamic texture description has been studied extensively due to its wide applications in the field of computer vision. Local binary pattern (LBP) and its various variants account for a large part of dynamic texture description methods because of its advantages, such as good discriminability and low computational complexity. However, many LBP-based methods directly extract feature from pixel intensities and only use a proportion of pixels in a local neighborhood. And their good classification performance is usually achieved at the cost of high feature dimensionality, which would limit their application scenarios. We argue that extracting features from the gradient domain will capture more discriminative features due to the additional directional information, and that making use of all the pixels in a local neighborhood would improve performance. In this paper, we propose a simply but effective dynamic texture descriptor that inherits the advantages of LBP while excluding its disadvantages. The proposed method consists of four stages of data processing: 1) gradients extraction; 2) random feature extraction from gradients; 3) binary hashing of directional random features; and 4) histogramming. Gaussian first-order derivatives are used as gradient filters such that stable gradients could be generated. Then random projection is applied to extract random features from each gradients. Both the above two stages are conducted via 3D filtering, and thus they are efficient. Thirdly, the random features from each gradient are binarized and encoded into integer codes, from which a histogram is built. Finally, the histograms from each gradient are concatenated into a feature vector. Because we use 8-bit codes, The feature dimensionality is very low. We evaluate the proposed method on three benchmark dynamic texture datasets with various test protocols. The results demonstrate its effectiveness and efficiency when comparing to many state-of-the-art methods.

show abstract

Dynamic Texture Classification Using Deterministic Partially Self-avoiding Walks on Networks

Cited by 4 publications

References 27 publications

Patterns and randomness in networks for computer vision: from graphs to neural networks

Patterns and randomness in networks for computer vision: from graphs to neural networks

Efficient bat-inspired block matching algorithm with novel motion energy directional histograms for dynamic texture fast recognition

Dynamic Texture Classification Using Directional Binarized Random Features

Contact Info

Product

Resources

About