Adaptive pattern spectrum image description using Euclidean and Geodesic distance without training for texture classification

González-Castro, V́ıctor; Alegre, Enrique; García-Olalla, Oscar; Fernández-Robles, Laura; Garcí­a-Ordás, María Teresa

doi:10.1049/iet-cvi.2012.0098

Cited by 10 publications

(8 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Textures in this database are taken from different materials and divided into several categories. Within some of them there are different sub-categories, so they have been divided as it was done in [14].…”

Section: A Texture Databasementioning

confidence: 99%

Pixel Classification Using General Adaptive Neighborhood-Based Features

González-Castro

Debayle

Curie

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

Abstract-This paper introduces a new descriptor for characterizing and classifying the pixels of texture images by means of General Adaptive Neighborhoods (GANs). The GAN of a pixel is a spatial region surrounding it and fitting its local image structure. The features describing each pixel are then regionbased and intensity-based measurements of its corresponding GAN. In addition, these features are combined with the graylevel values of adaptive mathematical morphology operators using GANs as structuring elements. The classification of each pixel of images belonging to five different textures of the VisTex database has been carried out to test the performance of this descriptor. For the sake of comparison, other adaptive neighborhoods introduced in the literature have also been used to extract these features from: the Morphological Amoebas (MA), adaptive geodesic neighborhoods (AGN) and salience adaptive structuring elements (SASE). Experimental results show that the GAN-based method outperforms the others for the performed classification task, achieving an overall accuracy of 97.25% in the five-way classifications, and area under curve values close to 1 in all the five "one class vs. all classes" binary classification problems.

show abstract

Section: A Texture Databasementioning

confidence: 99%

Pixel Classification Using General Adaptive Neighborhood-Based Features

González-Castro

Debayle

Curie

2014

2014 22nd International Conference on Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Therefore, morphological operations are adapted to the local features of each point with no need of a priori information about the images. This method has been used to compute the Adaptive Pattern Spectrum of textures with the goal of characterizing them [4].…”

Section: Adaptive Geodesic Pattern Spectrum (Agps)mentioning

confidence: 99%

Adaptive Texture Description and Estimation of the Class Prior Probabilities for Seminal Quality Control

González-Castro¹

2014

ELCVIA

View full text Add to dashboard Cite

Motivation of the PhD thesisSemen quality assessment is a crucial task in artificial insemination processes, both for humans and animals. Animal artificial insemination allows farmers to save time and money (e.g. working with a limited number of animals). They purchase semen samples to companies devoted to their production and commercialization, but they need these samples to be optimal for fertilization. As a result, semen production centers have to carry out rigorous quality control procedures to guarantee good standards A semen sample with a high proportion of (i) dead spermatozoa, or (ii) sperm heads with damaged acrosomes * will have low fertilization potential. Therefore, sperm vitality and acrosome integrity are two of the parameters evaluated by veterinaries in semen quality control processes. Currently, both are assessed manually, by means of a visual process which entails expensive equipment, such as stains and fluorescence microscopes. Moreover, they may be a source of errors, as any manual process is.The goal is to develop an automatic system to estimate the proportions of damaged acrosomes and dead spermatozoa using just a computer and a digital camera connected to a phase contrast microscope, which is affordable by any laboratory. The contributions made on this PhD thesis in the fields of Image Processing and Machine Learning [1] can be helpful for this goal. Concretely, several texture description approaches have been evaluated for this task. Furthermore, a new intelligent segmentation process, an adaptive texture description method, and two robust approaches for estimating class proportions of unlabeled datasets have been proposed. All these methods are applied to automatic boar semen quality estimation. Contributions Intelligent boar sperm segmentation using thresholding and WatershedA bad segmented sperm head could lead to further errors in description and classification stages. Therefore, it is necessary to minimize the number of bad segmentations and to detect when a head is not well segmented, thus avoiding its further processing. To accomplish that, in this thesis an approach which combined (i) classical Otsu Correspondence to: Recommended for acceptance by ELCVIA

show abstract

“…Image classification has shown to be a useful tool to categorize images automatically. Many descriptors can be found in the literature, such as texture descriptors [3], shape descriptors [4], adaptive texture descriptors [5] or color descriptors [6]. The Bag of Visual Words (BoVW) model has shown an excellent performance to carry out image classification [7,8].…”

Section: Introductionmentioning

confidence: 99%

Color Sift Descriptors to Categorize Illegal Activities in Images of Onion Domains

Matilla¹,

González-Castro²,

Fernández-Robles³

et al. 2020

Actas De Las XXXIX Jornadas De Automática, Badajoz, 5-7 De Septiembre De 2018

View full text Add to dashboard Cite

Dark Web, i.e. the portion of the Web whose content is not indexed either accessible by standard web browsers, comprises several darknets. The Onion Router (Tor) is the most famous one, thanks to the anonymity provided to its users, and it results in the creation of domains, or hidden services, which hosts illegal activities. In this work, we explored the possibility of identifying illegal domains on Tor darknet based on its visual content. After crawling and filtering the images of 500 hidden services, we sorted them into five different illegal categories, and we trained a classifier using the Bag of Visual Words (BoVW) model. In this model, SIFT (Scale Invariant Feature Transform) or dense SIFT were used as the descriptors of the images patches to compute the visual words of the BoVW model. However, SIFT only works with gray-scale images; thus the information given by color in an image is not retrieved. To overcome this drawback, in this work we implemented and assessed the performance of three different variants of SIFT descriptors that can be used in color images, namely HSV-SIFT, RGB-SIFT and Opponent-SIFT, in the BoVW model for image classification. The obtained results showed the usefulness of using color-SIFT descriptors instead of SIFT, whereas in our experiments the latter achieved an accuracy of 57.52%, the HSV-SIFT descriptor achieved an accuracy up to 59.44%.

show abstract

Adaptive pattern spectrum image description using Euclidean and Geodesic distance without training for texture classification

Cited by 10 publications

References 19 publications

Pixel Classification Using General Adaptive Neighborhood-Based Features

Pixel Classification Using General Adaptive Neighborhood-Based Features

Adaptive Texture Description and Estimation of the Class Prior Probabilities for Seminal Quality Control

Color Sift Descriptors to Categorize Illegal Activities in Images of Onion Domains

Contact Info

Product

Resources

About