A novel method for clustering cellular data to improve classification

Many fields,such as neuroscience,are experiencing the vast prolife ration of cellular data,underscoring the need fo r organizing and interpreting large datasets.A popular approach partitions data into manageable subsets via hierarchical clustering,but objective methods to determine the appropriate classification granularity are missing.We recently introduced a technique to systematically identify when to stop subdividing clusters based on the fundamental principle that cells must differ more between than within clusters.Here we present the corresponding protocol to classify cellular datasets by combining datadriven unsupervised hierarchical clustering with statistical testing.These general-purpose functions are applicable to any cellular dataset that can be organized as two-dimensional matrices of numerical values,including molecula r,physiological,and anatomical datasets.We demonstrate the protocol using cellular data from the Janelia MouseLight project to chara cterize morphological aspects of neurons.

Performance evaluation of wavelet scattering network in image texture classification in various color spaces

The optimized color space is searched by using the wavelet scattering network in the KTH_TIPS_COL color image database for image texture classification. The effect of choosing the color space on the classification accuracy is investigated by converting red green blue （RGB） color space to various other color spaces. The results show that the classification performance generally changes to a large degree when performing color texture classification in various color spaces, and the opponent RGB-based wavelet scattering network outperforms other color spaces-based wavelet scattering networks. Considering that color spaces can be changed into each other, therefore, when dealing with the problem of color texture classification, converting other color spaces to the opponent RGB color space is recommended before performing the wavelet scattering network.

Texture classification based on EMD and FFT

Empirical mode decomposition (EMD) is an adaptive and approximately orthogonal filtering process that reflects human’s visual mechanism of differentiating textures. In this paper, we present a modified 2D EMD algorithm using the FastRBF and an appropriate number of iterations in the shifting process (SP), then apply it to texture classification. Rotation-invariant texture feature vectors are extracted using auto-registration and circular regions of magnitude spectra of 2D fast Fourier transform (FFT). In the experiments, we employ a Bayesion classifier to classify a set of 15 distinct natural textures selected from the Brodatz album. The experimental results, based on different testing datasets for images with different orientations, show the effectiveness of the proposed classification scheme.

Genetic Feature Selection for Texture Classification

This paper presents a novel approach to feature subset selection using genetic algorithms. This approach has the ability to accommodate multiple criteria such as the accuracy and cost of classification into the process of feature selection and finds the effective feature subset for texture classification. On the basis of the effective feature subset selected, a method is described to extract the objects which are higher than their surroundings, such as trees or forest, in the color aerial images. The methodology presented in this paper is illustrated by its application to the problem of trees extraction from aerial images.

Multiwavelets domain singular value features for image texture classification

A new approach based on multiwavelets transformation and singular value decomposition (SVD) is proposed for the classification of image textures. Lower singular values are truncated based on its energy distribution to classify the textures in the presence of additive white Gaussian noise (AWGN). The proposed approach extracts features such as energy, entropy, local homogeneity and max-min ratio from the selected singular values of multiwavelets transformation coefficients of image textures. The classification was carried out using probabilistic neural network (PNN). Performance of the proposed approach was compared with conventional wavelet domain gray level co-occurrence matrix (GLCM) based features, discrete multiwavelets transformation energy based approach, and HMM based approach. Experimental results showed the superiority of the proposed algorithms when compared with existing algorithms.

Classification of wood surface texture based on Gauss-MRF Model

The basal theory of Gauss-MRF is expounded and 2-5 order Gauss MRF models are established. Parameters of the 2-5 order Gauss-MRF models for 300 wood samples＇ surface texture are also estimated by using LMS. The data analysis shows that： 1） different rexture parameters have a clear scattered distribution, 2） the main direction of texture is the direction represented by the maximum parameter of Gauss-MRF parameters, and 3） for those samples having the same main direction, the finer the texture is, the greater the corresponding parameter is, and the smaller the other parameters are; and the higher the order of Gauss-MRF is, the more clearly the texture is described. On the condition of the second order Gauss MRF model, parameter B1, B2 of tangential texture are smaller than that of radial texture, while B3 and B4 of tangential texture are greater than that of radial texture. According to the value of separated criterion, the parameter of the fifth order Gauss-MRF is used as feature vector for Hamming neural network classification. As a result, the ratio of correctness reaches 88%.

Deep learning classification of coastal wetland hyperspectral image combined spectra and texture features: A case study of Huanghe(Yellow) River Estuary wetland

This paper develops a deep learning classification method with fully-connected 8-layers characteristics to classification of coastal wetland based on CHRIS hyperspectral image. The method combined spectral feature and multi-spatial texture feature information has been applied in the Huanghe(Yellow) River Estuary coastal wetland.The results show that:(1) Based on testing samples, the DCNN model combined spectral feature and texture feature after K-L transformation appear high classification accuracy, which is up to 99%.(2) The accuracy by using spectral feature with all the texture feature is lower than that using spectral only and combing spectral and texture feature after K-L transformation. The DCNN classification accuracy using spectral feature and texture feature after K-L transformation was up to 99.38%, and the outperformed that of all the texture feature by 4.15%.(3) The classification accuracy of the DCNN method achieves better performance than other methods based on the whole validation image, with an overall accuracy of 84.64% and the Kappa coefficient of 0.80.(4) The developed DCNN model classification algorithm ensured the accuracy of all types is more balanced, and it also greatly improved the accuracy of tidal flat and farmland, while kept the classification accuracy of main types almost invariant compared to the shallow algorithms. The classification accuracy of tidal flat and farmland is up to 79.26% and 56.72%respectively based on the DCNN model. And it improves by about 2.51% and 10.6% compared with that of the other shallow classification methods.

Texture image classification using multi fractal dimension

This paper presents a supervised classification method of sonar image, which takes advantages of both multi-fractal theory and wavelet analysis. In the process of feature extraction, image transformation and wavelet decomposition are combined and a feature set based on multi-fractal dimension is obtained. In the part of classifier construction, the Learning Vector Quantization (LVQ) network is adopted as a classifier. Experiments of sonar image classification were carried out with satisfactory results, which verify the effectiveness of this method.

Remote Sensing Image Classification Algorithm Based on Texture Feature and Extreme Learning Machine

With the development of satellite technology,the satellite imagery of the earth’s surface and the whole surface makes it possible to survey surface resources and master the dynamic changes of the earth with high efficiency and low consumption.As an important tool for satellite remote sensing image processing,remote sensing image classification has become a hot topic.According to the natural texture characteristics of remote sensing images,this paper combines different texture features with the Extreme Learning Machine,and proposes a new remote sensing image classification algorithm.The experimental tests are carried out through the standard test dataset SAT-4 and SAT-6.Our results show that the proposed method is a simpler and more efficient remote sensing image classification algorithm.It also achieves 99.434%recognition accuracy on SAT-4,which is 1.5%higher than the 97.95%accuracy achieved by DeepSat.At the same time,the recognition accuracy of SAT-6 reaches 99.5728%,which is 5.6%higher than DeepSat’s 93.9%.

Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor

This paper introduces a comparative analysis of the proficiencies of various textures and geometric features in the diagnosis of breast masses on mammograms.An improved machine learning-based framework was developed for this study.The proposed system was tested using 106 full field digital mammography images from the INbreast dataset,containing a total of 115 breast mass lesions.The proficiencies of individual and various combinations of computed textures and geometric features were investigated by evaluating their contributions towards attaining higher classification accuracies.Four state-of-the-art filter-based feature selection algorithms(Relief-F,Pearson correlation coefficient,neighborhood component analysis,and term variance)were employed to select the top 20 most discriminative features.The Relief-F algorithm outperformed other feature selection algorithms in terms of classification results by reporting 85.2%accuracy,82.0%sensitivity,and 88.0%specificity.A set of nine most discriminative features were then selected,out of the earlier mentioned 20 features obtained using Relief-F,as a result of further simulations.The classification performances of six state-of-the-art machine learning classifiers,namely k-nearest neighbor(k-NN),support vector machine,decision tree,Naive Bayes,random forest,and ensemble tree,were investigated,and the obtained results revealed that the best classification results(accuracy=90.4%,sensitivity=92.0%,specificity=88.0%)were obtained for the k-NN classifier with the number of neighbors having k=5 and squared inverse distance weight.The key findings include the identification of the nine most discriminative features,that is,FD26(Fourier Descriptor),Euler number,solidity,mean,FD14,FD13,periodicity,skewness,and contrast out of a pool of 125 texture and geometric features.The proposed results revealed that the selected nine features can be used for the classification of breast masses in mammograms.

A Method of Soil Salinization Information Extraction with SVM Classification Based on ICA and Texture Features

Salt-affected soils classification using remotely sensed images is one of the most common applications in remote sensing,and many algorithms have been developed and applied for this purpose in the literature.This study takes the Delta Oasis of Weigan and Kuqa Rivers as a study area and discusses the prediction of soil salinization from ETM +Landsat data.It reports the Support Vector Machine(SVM) classification method based on Independent Component Analysis(ICA) and Texture features.Meanwhile,the letter introduces the fundamental theory of SVM algorithm and ICA,and then incorporates ICA and texture features.The classification result is compared with ICA-SVM classification,single data source SVM classification,maximum likelihood classification(MLC) and neural network classification qualitatively and quantitatively.The result shows that this method can effectively solve the problem of low accuracy and fracture classification result in single data source classification.It has high spread ability toward higher array input.The overall accuracy is 98.64%,which increases by10.2% compared with maximum likelihood classification,even increases by 12.94% compared with neural net classification,and thus acquires good effectiveness.Therefore,the classification method based on SVM and incorporating the ICA and texture features can be adapted to RS image classification and monitoring of soil salinization.

The Properties of Expected Scattering and Averaged Scattering and Their Applications to Texture Classification

In order to further improve the effectiveness of image processing,it is necessary that an efficient invariant representation is stable to deformation applied to images.This motivates the study of image representations defining an Euclidean metric stable to these deformation.This paper mainly focuses on two aspects.On the one hand,in this paper,two properties of expected scattering and averaged scattering,i.e.,Lipschitz continuity and translation invariance,are proved in detail.These properties support that excepted scattering and averaged scattering are invariant,stable and informative representations.On the other hand,the issue of texture classification based on expected scattering and averaged scattering has been analyzed respectively in this study.Energy features,which are based on expected scattering and averaged scattering,are calculated and used for classification.Experimental results show that starting with the seventh feature,the two approaches can achieve good performance in texture image classification.

Texture Image Classification Based on Gabor Wavelet

For a texture image, by recognizining the class of every pixel of the image, it can be partitioned into disjoint regions of uniform texture. This paper proposed a texture image classification algorithm based on Gabor wavelet. In this algorithm, characteristic of every image is obtained through every pixel and its neighborhood of this image. And this algorithm can achieve the information transform between different sizes of neighborhood.Experiments on standard Brodatz texture image dataset show that our proposed algorithm can achieve good classification rates.

Energy enhanced tissue texture in spectral computed tomography for lesion classification

Tissue texture reflects the spatial distribution of contrasts of image voxel gray levels,i.e.,the tissue heterogeneity,and has been recognized as important biomarkers in various clinical tasks.Spectral computed tomography(CT)is believed to be able to enrich tissue texture by providing different voxel contrast images using different X-ray energies.Therefore,this paper aims to address two related issues for clinical usage of spectral CT,especially the photon counting CT(PCCT):(1)texture enhancement by spectral CT image reconstruction,and(2)spectral energy enriched tissue texture for improved lesion classification.For issue(1),we recently proposed a tissue-specific texture prior in addition to low rank prior for the individual energy-channel low-count image reconstruction problems in PCCT under the Bayesian theory.Reconstruction results showed the proposed method outperforms existing methods of total variation(TV),low-rank TV and tensor dictionary learning in terms of not only preserving texture features but also suppressing image noise.For issue(2),this paper will investigate three models to incorporate the enriched texture by PCCT in accordance with three types of inputs:one is the spectral images,another is the cooccurrence matrices(CMs)extracted from the spectral images,and the third one is the Haralick features(HF)extracted from the CMs.Studies were performed on simulated photon counting data by introducing attenuationenergy response curve to the traditional CT images from energy integration detectors.Classification results showed the spectral CT enriched texture model can improve the area under the receiver operating characteristic curve(AUC)score by 7.3%,0.42%and 3.0%for the spectral images,CMs and HFs respectively on the five-energy spectral data over the original single energy data only.The CM-and HF-inputs can achieve the best AUC of 0.934 and 0.927.This texture themed study shows the insight that incorporating clinical important prior information,e.g.,tissue texture in this paper,into the medical imaging,such as the upstream image reconstruction,the downstream diagnosis,and so on,can benefit the clinical tasks.

SAR Image Classification Based on Its Texture Features

SAR images not only have the characteristics of all-ay, all-eather, but also provide object information which is different from visible and infrared sensors. However, SAR images have some faults, such as more speckles and fewer bands. The authors conducted the experiments of texture statistics analysis on SAR image features in order to improve the accuracy of SAR image interpretation. It is found that the texture analysis is an effective method for improving the accuracy of the SAR image interpretation.

Texture Classification of 3D Surface Textures Via Directional Quincunx Lifting

This thesis presents a new approach to classify 3D surface textures by using lifting transform with quincunx subsampling. Feature vectors are generated from eight different lifting prediction directions. We classify 3D surface texture images based on minimum Euclidean distance between the test images and the training sets. The feasibility and effectiveness of our proposed approach can be validated by the experimental results.

Combinations of Feature Descriptors for Texture Image Classification

Texture recognition and classification is a widely applicable task in computer vision. A key stage in performing this task is feature extraction, which identifies sets of features that describe the visual texture of an image. Many descriptors can be used to perform texture classification;among the more common of these are the grey level co-occurrence matrix, Gabor wavelets, steerable pyramids and SIFT. We analyse and compare the effectiveness of these methods on the Brodatz, UIUCTex and KTH-TIPS texture image datasets. The efficacy of the descriptors is evaluated both in isolation and by combining several of them by means of machine learning approaches such as Bayesian networks, support vector machines, and nearest-neighbour approaches. We demonstrate that using a combination of features improves reliability over using a single feature type when multiple datasets are to be classified. We determine optimal combinations for each dataset and achieve high classification rates, demonstrating that relatively simple descriptors can be made to perform close to the very best published results. We also demonstrate the importance of selecting the optimal descriptor set and analysis techniques for a given dataset.

Achieving high ductility and low in-plane anisotropy in magnesium alloy through a novel texture design strategy

Texture regulation is a prominent method to modify the mechanical properties and anisotropy of magnesium alloy.In this work,the Mg-1Al-0.3Ca-0.5Mn-0.2Gd(wt.%)alloy sheet with TD-tilted and circular texture was fabricated by unidirectional rolling(UR)and multidirectional rolling(MR)method,respectively.Unlike generating a strong in-plane mechanical anisotropy in conventional TD-tilted texture,the novel circular texture sample possessed a weak in-plane yield anisotropy.This can be rationalized by the similar proportion of soft grains with favorable orientation for basalslip and{10.12}tensile twinning during the uniaxial tension of circular-texture sample along different directions.Moreover,compared with the TD-tilted texture,the circular texture improved the elongation to failure both along the rolling direction(RD)and transverse direction(TD).By quasi-in-situ EBSD-assisted slip trace analysis,higher activation of basal slip was observed in the circular-texture sample during RD tension,contributing to its excellent ductility.When loading along the TD,the TD-tilted texture promoted the activation of{10.12}tensile twins significantly,thus providing nucleation sites for cracks and deteriorating the ductility.This research may shed new insights into the development of formable and ductile Mg alloy sheets by texture modification.

Point Cloud Classification Using Content-Based Transformer via Clustering in Feature Space

Recently, there have been some attempts of Transformer in 3D point cloud classification. In order to reduce computations, most existing methods focus on local spatial attention,but ignore their content and fail to establish relationships between distant but relevant points. To overcome the limitation of local spatial attention, we propose a point content-based Transformer architecture, called PointConT for short. It exploits the locality of points in the feature space(content-based), which clusters the sampled points with similar features into the same class and computes the self-attention within each class, thus enabling an effective trade-off between capturing long-range dependencies and computational complexity. We further introduce an inception feature aggregator for point cloud classification, which uses parallel structures to aggregate high-frequency and low-frequency information in each branch separately. Extensive experiments show that our PointConT model achieves a remarkable performance on point cloud shape classification. Especially, our method exhibits 90.3% Top-1 accuracy on the hardest setting of ScanObjectN N. Source code of this paper is available at https://github.com/yahuiliu99/PointC onT.

Combining Spectral with Texture Features into Objectoriented Classification in Mountainous Terrain Using Advanced Land Observing Satellite Image

Most existing classification studies use spectral information and those were adequate for cities or plains. This paper explores classification method suitable for the ALOS （Advanced Land Observing Satellite） in mountainous terrain. Mountainous terrain mapping using ALOS image faces numerous challenges. These include spectral confusion with other land cover features, topographic effects on spectral signatures （such as shadow）. At first, topographic radiometric correction was carried out to remove the illumination effects of topography. In addition to spectral features, texture features were used to assist classification in this paper. And texture features extracted based on GLCM （Gray Level Co- occurrence Matrix） were not only used for segmentation, but also used for building rules. The performance of the method was evaluated and compared with Maximum Likelihood Classification （MLC）. Results showed that the object-oriented method integrating spectral and texture features has achieved overall accuracy of 85.73% with a kappa coefficient of 0.824, which is 13.48% and o.145 respectively higher than that got by MLC method. It indicated that texture features can significantly improve overall accuracy, kappa coefficient, and the classification precision of existing spectrum confusion features. Object-oriented method Integrating spectral and texture features is suitable for land use extraction of ALOS image in mountainous terrain.