Wavelet-like selective representations of multidirectional structures: a mammography case

Jasionowska, Magdalena; Przelaskowski, Artur

doi:10.1007/s10044-018-0698-z

“…The recognition and classification of texture images, either in isolated conditions or "in the wild" is one of the most important tasks in computer vision, with numerous applications in material sciences [51], medicine [38], remote sensing [65], agriculture [56], etc.…”

Section: Introductionmentioning

confidence: 99%

Texture image classification based on a pseudo-parabolic diffusion model

Vieira

¹

,

Abreu

²

,

Florindo

³

2022

Multimed Tools Appl

6

0

View full text Add to dashboard Cite

This work proposes a novel method based on a pseudo-parabolic diffusion process to be employed for texture recognition. The proposed operator is applied over a range of time scales giving rise to a family of images transformed by nonlinear filters. Therefore each of those images are encoded by a local descriptor (we use local binary patterns for that purpose) and they are summarized by a simple histogram, yielding in this way the image feature vector. Three main novelties are presented in this manuscript: (1) The introduction of a pseudo-parabolic model associated with the signal component of binary patterns to the process of texture recognition and a real-world application to the problem of identifying plant species based on the leaf surface image. (2) We also introduce a simple and efficient discrete pseudo-parabolic differential operator based on finite differences as texture descriptors. While the work in [ 26 ] uses complete local binary patterns, here we use the original version of the local binary pattern operator. (3) We also discuss, in more general terms, the possibilities of exploring pseudo-parabolic models for image analysis as they balance two types of processing that are fundamental for pattern recognition, i.e., they smooth undesirable details (possibly noise) at the same time that highlight relevant borders and discontinuities anisotropically. Besides the practical application, the proposed approach is also tested on the classification of well established benchmark texture databases. In both cases, it is compared with several state-of-the-art methodologies employed for texture recognition. Our proposal outperforms those methods in terms of classification accuracy, confirming its competitiveness. The good performance can be justified to a large extent by the ability of the pseudo-parabolic operator to smooth possibly noisy details inside homogeneous regions of the image at the same time that it preserves discontinuities that convey critical information for the object description. Such results also confirm that model-based approaches like the proposed one can still be competitive with the omnipresent learning-based approaches, especially when the user does not have access to a powerful computational structure and a large amount of labeled data for training.

show abstract

“…The recognition and classification of texture images, either in isolated conditions or "in the wild" is one of the most important tasks in computer vision, with numerous applications in material sciences (Naik and Khan, 2019), medicine (Jasionowska and Przelaskowski, 2019), remote sensing (Tu et al, 2019), agriculture (Safdar et al, 2019), etc.…”

Section: Introductionmentioning

confidence: 99%

Texture image classification based on a pseudo-parabolic diffusion model

Vieira¹,

Abreu²,

Florindo³

2020

Preprint

View full text Add to dashboard Cite

This work proposes a novel method based on a pseudo-parabolic diffusion process to be employed for texture recognition. The proposed operator is applied over a range of time scales giving rise to a family of images transformed by nonlinear filters. Therefore each of those images are encoded by a local descriptor (we use local binary patterns for that purpose) and they are summarized by a simple histogram, yielding in this way the image feature vector. The proposed approach is tested on the classification of well established benchmark texture databases and on a practical task of plant species recognition. In both cases, it is compared with several state-of-the-art methodologies employed for texture recognition. Our proposal outperforms those methods in terms of classification accuracy, confirming its competitiveness. The good performance can be justified to a large extent by the ability of the pseudo-parabolic operator to smooth possibly noisy details inside homogeneous regions of the image at the same time that it preserves discontinuities that convey critical information for the object description. Such results also confirm that model-based approaches like the proposed one can still be competitive with the omnipresent learningbased approaches, especially when the user does not have access to a powerful

show abstract