Influence of normalization and color space to color texture classification

Cernadas, E.; Fernández-Delgado, Manuel; González-Rufino, E.; Carrión, P.

doi:10.1016/j.patcog.2016.07.002

Cited by 81 publications

(64 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…We also mention the best results achieved by the reviews of Mäenpää, T. and Pietikäinen, M. (2004) [12] and Cernadas et al (2017) [14]. It is important to notice that some of these works [12,14,55] do not consider leave-one-out cross-validation, so the comparison should be taken cautiously.…”

Section: Comparison With Other Methodsmentioning

confidence: 99%

“…The color information is usually ignored, or processed separately with non-spatial approaches such as color statistics (histograms, statistical moments, etc). Studies have been carried out showing the benefits of adding color for texture analysis [11,12,13,14]. However, most methods of color-texture analysis do not consider the spatial relation of pixels in different color channels.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multilayer complex network descriptors for color–texture characterization

Scabini

Condori

Gonçalves

et al. 2019

Information Sciences

View full text Add to dashboard Cite

A new method based on complex networks is proposed for color-texture analysis. The proposal consists on modeling the image as a multilayer complex network where each color channel is a layer, and each pixel (in each color channel) is represented as a network vertex. The network dynamic evolution is accessed using a set of modeling parameters (radii and thresholds), and new characterization techniques are introduced to capt information regarding within and between color channel spatial interaction. An automatic and adaptive approach for threshold selection is also proposed. We conduct classification experiments on 5 well-known datasets: Vistex, Usptex, Outex13, CURet and MBT. Results among various literature methods are compared, including deep convolutional neural networks with pre-trained architectures. The proposed method presented the highest overall performance over the 5 datasets, with 97.7 of mean accuracy against 97.0 achieved by the ResNet convolutional neural network with 50 layers. and its results, comparisons with literature methods and discussions; finally, on Section 5 we discuss the main findings and results of the work. Theoretical Concepts and ReviewOn this section, we present the theoretical concepts of color-texture and CN. Color-Texture AnalysisThe goal of texture analysis is to study how to measure texture aspects and employ it to image characterization. Although this approach has been explored for many years, most works approach gray-level images, i.e. a single color-channel representing the pixel luminance. On this case, the multispectral information is either discarded or is not present. However, nowadays images that derive from different sources are mostly colored, for instance from the internet, surveillance cameras, satellites, microscopes, personal cameras and much more. The recent increase in computer hardware performance also makes possible to analyze larger amounts of data, allowing to keep the color information for texture analysis.In general, color-texture methods found in the literature are mostly integrative, which separate color from texture. These methods usually compute traditional gray-level descriptors from each color-channel, separately. For that, various gray-level methods can be applied or combined into an integrative descriptor. There are many graylevel methods found in literature. Classical techniques can be divided into statistical, model-based and structural methods [15]. The statistical methods were one of the first approaches which considered texture as a property to characterize images. Among statistical methods, the most common ones are those based on gray-level co-occurrence matrices [16,17] and Local Binary Patterns (LBP) [18]. Model-based methods include descriptors such as Gabor filters [19], which explore texture in the frequency domain, and Markov random field models [20]. Structural methods consists on analyzing the texture as a combination of various smaller elements, that are spatially arranged to compose the overall texture pattern. This is achieved, for...

show abstract

Section: Comparison With Other Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multilayer complex network descriptors for color–texture characterization

Scabini

Condori

Gonçalves

et al. 2019

Information Sciences

View full text Add to dashboard Cite

show abstract

“…Colour constancy. We considered chromaticity representation ('chroma' in the remainder), grey-world normalisation ('gw') and histogram equalisation ('heq') [16]. In the experiments we used Jost van de Weijer's Color Constancy Toolbox (http://lear.inrialpes.fr/people/vandeweijer/research.html) and Matlab's histeq() function respectively for 'gw' and 'heq'.…”

Section: Colour Normalisationmentioning

confidence: 99%

Evaluation of Colour Pre-processing on Patch-Based Classification of H&E-Stained Images

Bianconi

Kather

Reyes-Aldasoro

2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

This paper compares the effects of colour pre-processing on the classification performance of H&E-stained images. Variations in the tissue preparation procedures, acquisition systems, stain conditions and reagents are all source of artifacts that can affect negatively computerbased classification. Pre-processing methods such as colour constancy, transfer and deconvolution have been proposed to compensate the artifacts. In this paper we compare quantitatively the combined effect of six colour pre-processing procedures and 12 colour texture descriptors on patch-based classification of H&E-stained images. We found that colour pre-processing had negative effects on accuracy in most cases -particularly when used with colour descriptors. However, some pre-processing procedures proved beneficial when employed in conjunction with classic texture descriptors such as co-occurrence matrices, Gabor filters and Local Binary Patterns.

show abstract

“…In the future, unsupervised feature selection [59] will be implemented to tackle the issue of the feature dimensionality and memory cost. In order to improve the robustness against illumination, the image normalization [60] will be exploited in the image pre-processing. In addition, manifold learning (ML) [61,62] and query expansion (QE) [63] will also be considered to further enhance the retrieval performance.…”

Section: Discussionmentioning

confidence: 99%

Local Ternary Cross Structure Pattern: A Color LBP Feature Extraction with Applications in CBIR

Feng

Wei

et al. 2019

Applied Sciences

View full text Add to dashboard Cite

With the advent of medical endoscopes, earth observation satellites and personal phones, content-based image retrieval (CBIR) has attracted considerable attention, triggered by its wide applications, e.g., medical image analytics, remote sensing, and person re-identification. However, constructing effective feature extraction is still recognized as a challenging problem. To tackle this problem, we first propose the five-level color quantizer (FLCQ) to acquire a color quantization map (CQM). Secondly, according to the anatomical structure of the human visual system, the color quantization map (CQM) is amalgamated with a local binary pattern (LBP) map to construct a local ternary cross structure pattern (LTCSP). Third, the LTCSP is further converted into the uniform local ternary cross structure pattern (LTCSPuni) and the rotation-invariant local ternary cross structure pattern (LTCSPri) in order to cut down the computational cost and improve the robustness, respectively. Finally, through quantitative and qualitative evaluations on face, objects, landmark, textural and natural scene datasets, the experimental results illustrate that the proposed descriptors are effective, robust and practical in terms of CBIR application. In addition, the computational complexity is further evaluated to produce an in-depth analysis.

show abstract

Influence of normalization and color space to color texture classification

Cited by 81 publications

References 51 publications

Multilayer complex network descriptors for color–texture characterization

Multilayer complex network descriptors for color–texture characterization

Evaluation of Colour Pre-processing on Patch-Based Classification of H&E-Stained Images

Local Ternary Cross Structure Pattern: A Color LBP Feature Extraction with Applications in CBIR

Contact Info

Product

Resources

About