Hierarchical Ensemble of Global and Local Classifier for Texture Classification

2014 ◽  
pp. 211-219
Author(s):  
Ming Chen
Keyword(s):  
Texture Classification ◽  
Local Classifier ◽  
Global And Local

scholarly journals Color–Texture Pattern Classification Using Global–Local Feature Extraction, an SVM Classifier, with Bagging Ensemble Post-Processing

2019 ◽  
Vol 9 (15) ◽  
pp. 3130 ◽  
Author(s):  
Navarro ◽  
Perez
Keyword(s):  
Feature Extraction ◽  
Pattern Classification ◽  
Texture Classification ◽  
Support Vector ◽  
Svm Classifier ◽  
Post Processing ◽  
Image Partition ◽  
Global And Local ◽  
Bagging Ensemble ◽  
Color Texture

Many applications in image analysis require the accurate classification of complex patterns including both color and texture, e.g., in content image retrieval, biometrics, and the inspection of fabrics, wood, steel, ceramics, and fruits, among others. A new method for pattern classification using both color and texture information is proposed in this paper. The proposed method includes the following steps: division of each image into global and local samples, texture and color feature extraction from samples using a Haralick statistics and binary quaternion-moment-preserving method, a classification stage using support vector machine, and a final stage of post-processing employing a bagging ensemble. One of the main contributions of this method is the image partition, allowing image representation into global and local features. This partition captures most of the information present in the image for colored texture classification allowing improved results. The proposed method was tested on four databases extensively used in color–texture classification: the Brodatz, VisTex, Outex, and KTH-TIPS2b databases, yielding correct classification rates of 97.63%, 97.13%, 90.78%, and 92.90%, respectively. The use of the post-processing stage improved those results to 99.88%, 100%, 98.97%, and 95.75%, respectively. We compared our results to the best previously published results on the same databases finding significant improvements in all cases.

Global and Local Oriented Edge Magnitude Patterns for Texture Classification

2017 ◽  
Vol 31 (03) ◽  
pp. 1750007 ◽  
Author(s):  
Jun Dong ◽  
Xue Yuan ◽  
Fanlun Xiong
Keyword(s):  
Texture Classification ◽  
Local Binary Patterns ◽  
Texture Descriptor ◽  
Oriented Edge ◽  
Rotation Invariant ◽  
Edge Information ◽  
Structure Information ◽  
Local Texture ◽  
Rotation Compensation ◽  
Global And Local

In this paper, we propose a gray-scale texture descriptor, name the global and local oriented edge magnitude patterns (GLOEMP), for texture classification. GLOEMP is a framework, which is able to effectively combine local texture, global structure information and contrast of texture images. In GLOEMP, the principal orientation is determined by Histogram of Gradient (HOG) feature, then each direction is respectively shown in detail by a local binary patterns (LBP) occurrence histogram. Due to the fact that GLOEMP characterizes image information across different directions, it contains very abundant information. The global-level rotation compensation method is proposed, which shifts the principal orientation of the HOG to the first position, thus allowing GLOEMP to be robust to rotations. In addition, gradient magnitudes are used as weights to add to the histogram, making GLOEMP robust to lighting variances as well, and it also possesses a strong ability to express edge information. The experimental results obtained from the representative databases demonstrate that the proposed GLOEMP framework is capable of achieving significant improvement, in some cases reaching classification accuracy of 10% higher than over the traditional rotation invariant LBP method.

Sunspot Groups as Tracers of Sub-Surface Processes

2000 ◽  
Vol 179 ◽  
pp. 155-160
Author(s):  
M. H. Gokhale
Keyword(s):  
Magnetic Flux ◽  
Indian Institute ◽  
Surface Processes ◽  
The Sun ◽  
Global And Local ◽  
Sunspot Groups

AbstractData on sunspot groups have been quite useful for obtaining clues to several processes on global and local scales within the sun which lead to emergence of toroidal magnetic flux above the sun’s surface. I present here a report on such studies carried out at Indian Institute of Astrophysics during the last decade or so.

Establishing global and local coherence in discourse processing: Evidence from fMRI

2009 ◽  
Author(s):  
Paul van den Broek ◽  
Ben Seipel ◽  
Virginia Clinton ◽  
Edward J. O'Brien ◽  
Philip Burton ◽  
...  
Keyword(s):  
Discourse Processing ◽  
Local Coherence ◽  
Global And Local

Coral husbandry for ocean futures: leveraging abiotic factors to increase survivorship, growth, and resilience in juvenile Montipora capitata

2021 ◽  
Vol 657 ◽  
pp. 123-133
Author(s):  
JR Hancock ◽  
AR Barrows ◽  
TC Roome ◽  
AS Huffmyer ◽  
SB Matsuda ◽  
...  
Keyword(s):  
Abiotic Factors ◽  
Larval Rearing ◽  
Abiotic Conditions ◽  
Montipora Capitata ◽  
Reef Restoration ◽  
Juvenile Corals ◽  
Bleaching Response ◽  
The Face ◽  
Survival And Growth ◽  
Global And Local

Reef restoration via direct outplanting of sexually propagated juvenile corals is a key strategy in preserving coral reef ecosystem function in the face of global and local stressors (e.g. ocean warming). To advance our capacity to scale and maximize the efficiency of restoration initiatives, we examined how abiotic conditions (i.e. larval rearing temperature, substrate condition, light intensity, and flow rate) interact to enhance post-settlement survival and growth of sexually propagated juvenile Montipora capitata. Larvae were reared at 3 temperatures (high: 28.9°C, ambient: 27.2°C, low: 24.5°C) for 72 h during larval development, and were subsequently settled on aragonite plugs conditioned in seawater (1 or 10 wk) and raised in different light and flow regimes. These juvenile corals underwent a natural bleaching event in Kāne‘ohe Bay, O‘ahu, Hawai‘i (USA), in summer 2019, allowing us to opportunistically measure bleaching response in addition to survivorship and growth. This study demonstrates how leveraging light and flow can increase the survivorship and growth of juvenile M. capitata. In contrast, larval preconditioning and substrate conditioning had little overall effect on survivorship, growth, or bleaching response. Importantly, there was no optimal combination of abiotic conditions that maximized survival and growth in addition to bleaching tolerances. This study highlights the ability to tailor sexual reproduction for specific restoration goals by addressing knowledge gaps and incorporating practices that could improve resilience in propagated stocks.

CNN performance dependence on linear image processing

2020 ◽  
Vol 2020 (10) ◽  
pp. 310-1-310-7
Author(s):  
Khalid Omer ◽  
Luca Caucci ◽  
Meredith Kupinski
Keyword(s):  
Image Processing ◽  
Texture Classification ◽  
Full Rank ◽  
Detection Performance ◽  
Ideal Observer ◽  
Training Data ◽  
Image Texture ◽  
Training Images ◽  
Analytic Expressions ◽  
Linear Compression

This work reports on convolutional neural network (CNN) performance on an image texture classification task as a function of linear image processing and number of training images. Detection performance of single and multi-layer CNNs (sCNN/mCNN) are compared to optimal observers. Performance is quantified by the area under the receiver operating characteristic (ROC) curve, also known as the AUC. For perfect detection AUC = 1.0 and AUC = 0.5 for guessing. The Ideal Observer (IO) maximizes AUC but is prohibitive in practice because it depends on high-dimensional image likelihoods. The IO performance is invariant to any fullrank, invertible linear image processing. This work demonstrates the existence of full-rank, invertible linear transforms that can degrade both sCNN and mCNN even in the limit of large quantities of training data. A subsequent invertible linear transform changes the images’ correlation structure again and can improve this AUC. Stationary textures sampled from zero mean and unequal covariance Gaussian distributions allow closed-form analytic expressions for the IO and optimal linear compression. Linear compression is a mitigation technique for high-dimension low sample size (HDLSS) applications. By definition, compression strictly decreases or maintains IO detection performance. For small quantities of training data, linear image compression prior to the sCNN architecture can increase AUC from 0.56 to 0.93. Results indicate an optimal compression ratio for CNN based on task difficulty, compression method, and number of training images.

The Indices of Creative Cities: the Global and Local Aspects

2015 ◽  
Vol 4 (1) ◽  
pp. 95 ◽  
Author(s):  
Tomas Kačerauskas
Keyword(s):  
High Tech ◽  
Melting Pot ◽  
Creative Cities ◽  
Global And Local

The paper deals with the indices of creative cities. Author analyses the different creativity indices suggested by both the followers and the critics of R. Florida. The author criticizes the Florida’s indices such as Bohemian, Melting pot, Gay, High tech, Innovation, Talent indices, as well as Minor integrative (diversity) and Major integrative indices. The indices of other authors presuppose the questions about the role of the region in defining certain creativity indices. The author makes conclusion that the uniform formula of creativity indices is impossible for two reasons. First, the creativity indices depend on the region of a city. Second, the very strategy to have the uniform creativity indices makes the cities similar to each other and no more unique, consequently, no more creative; as result, this strategy is anti-creative.

Sign in / Sign up

Export Citation Format

Share Document