scholarly journals Fault Condition Recognition Based on Multi-scale Texture Features and Embedding Prior Knowledge K-means for Antimony Flotation Process

2015 ◽  
Vol 48 (21) ◽  
pp. 864-870 ◽  
Author(s):  
Lin Zhao ◽  
Tao Peng ◽  
Lu Zhao ◽  
Peng Xia ◽  
Yongheng Zhao ◽  
...  
Keyword(s):  
Prior Knowledge ◽  
Texture Features ◽  
Flotation Process ◽  
Multi Scale ◽  
Condition Recognition

Fault condition recognition based on multi-scale co-occurrence matrix for copper flotation process

2014 ◽  
Vol 47 (3) ◽  
pp. 7091-7097 ◽  
Author(s):  
Lu Zhao ◽  
Tao Peng ◽  
Hua Han ◽  
Wei Cao ◽  
Yangge Lou ◽  
...  
Keyword(s):  
Flotation Process ◽  
Multi Scale ◽  
Occurrence Matrix ◽  
Copper Flotation ◽  
Condition Recognition

scholarly journals Multi-scale characterizations of colon polyps via computed tomographic colonography

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Weiguo Cao ◽  
Marc J. Pomeroy ◽  
Yongfeng Gao ◽  
Matthew A. Barish ◽  
Almas F. Abbasi ◽  
...  
Keyword(s):  
Area Under The Curve ◽  
Texture Features ◽  
Learning Model ◽  
Colon Polyps ◽  
Texture Descriptor ◽  
Operating Characteristics ◽  
Computed Tomographic ◽  
Multi Scale ◽  
Definition Of ◽  
Occurrence Matrix

AbstractTexture features have played an essential role in the field of medical imaging for computer-aided diagnosis. The gray-level co-occurrence matrix (GLCM)-based texture descriptor has emerged to become one of the most successful feature sets for these applications. This study aims to increase the potential of these features by introducing multi-scale analysis into the construction of GLCM texture descriptor. In this study, we first introduce a new parameter - stride, to explore the definition of GLCM. Then we propose three multi-scaling GLCM models according to its three parameters, (1) learning model by multiple displacements, (2) learning model by multiple strides (LMS), and (3) learning model by multiple angles. These models increase the texture information by introducing more texture patterns and mitigate direction sparsity and dense sampling problems presented in the traditional Haralick model. To further analyze the three parameters, we test the three models by performing classification on a dataset of 63 large polyp masses obtained from computed tomography colonoscopy consisting of 32 adenocarcinomas and 31 benign adenomas. Finally, the proposed methods are compared to several typical GLCM-texture descriptors and one deep learning model. LMS obtains the highest performance and enhances the prediction power to 0.9450 with standard deviation 0.0285 by area under the curve of receiver operating characteristics score which is a significant improvement.

A Tracking Window Adaptive Compressive Tracking Algorithm

2019 ◽  
Vol 33 (14) ◽  
pp. 1959045 ◽  
Author(s):  
Wenhao Wang ◽  
Mingxin Jiang ◽  
Xiaobing Chen ◽  
Li Hua ◽  
Shangbing Gao
Keyword(s):  
Texture Features ◽  
Candidate Region ◽  
Tracking Algorithm ◽  
Experimental Results ◽  
Scale Invariant ◽  
Compressive Tracking ◽  
Multi Scale ◽  
Feature Normalization ◽  
Object Region ◽  
Candidate Regions

In the original compression tracking algorithm, the size of the tracking box is fixed. There should be better tracking results for scale-invariant objects, but worse tracking results for scale-variant objects. To overcome this defect, a scale-adaptive compressive tracking (CT) algorithm is proposed. First of all, the imbalance of the gray and texture features in the original CT algorithm is balanced by the multi-feature method, which makes the algorithm more robust. Then, searching different candidate regions by using the method of multi-scale search along with feature normalization makes the features extracted from different scales comparable. Finally, the candidate region with the maximum discriminate degree is selected as the object region. Thus, the tracking-box size is adaptive. The experimental results show that when the object scale changes, the improving CT algorithm has higher accuracy and robustness than the original CT algorithm.

scholarly journals Improved GSO Optimized ESN Soft-Sensor Model of Flotation Process Based on Multisource Heterogeneous Information Fusion

2014 ◽  
Vol 2014 ◽  
pp. 1-12 ◽  
Author(s):  
Jie-sheng Wang ◽  
Shuang Han ◽  
Na-na Shen
Keyword(s):  
Principal Component ◽  
Texture Features ◽  
Soft Sensor ◽  
Kernel Principal Component Analysis ◽  
Real Time Control ◽  
Inertia Moment ◽  
Flotation Process ◽  
Time Control ◽  
Sensor Model ◽  
Froth Image

For predicting the key technology indicators (concentrate grade and tailings recovery rate) of flotation process, an echo state network (ESN) based fusion soft-sensor model optimized by the improved glowworm swarm optimization (GSO) algorithm is proposed. Firstly, the color feature (saturation and brightness) and texture features (angular second moment, sum entropy, inertia moment, etc.) based on grey-level co-occurrence matrix (GLCM) are adopted to describe the visual characteristics of the flotation froth image. Then the kernel principal component analysis (KPCA) method is used to reduce the dimensionality of the high-dimensional input vector composed by the flotation froth image characteristics and process datum and extracts the nonlinear principal components in order to reduce the ESN dimension and network complex. The ESN soft-sensor model of flotation process is optimized by the GSO algorithm with congestion factor. Simulation results show that the model has better generalization and prediction accuracy to meet the online soft-sensor requirements of the real-time control in the flotation process.

scholarly journals Histopathological Classification of Breast Cancer Images Using a Multi-Scale Input and Multi-Feature Network

Cancers ◽  
2020 ◽  
Vol 12 (8) ◽  
pp. 2031 ◽  
Author(s):  
Taimoor Shakeel Sheikh ◽  
Yonghee Lee ◽  
Migyung Cho
Keyword(s):  
State Of The Art ◽  
Texture Features ◽  
Feature Maps ◽  
Histopathological Classification ◽  
Multi Scale ◽  
Machine Learning Methods ◽  
Proposed Model ◽  
Benchmark Datasets ◽  
Histopathological Images

Diagnosis of pathologies using histopathological images can be time-consuming when many images with different magnification levels need to be analyzed. State-of-the-art computer vision and machine learning methods can help automate the diagnostic pathology workflow and thus reduce the analysis time. Automated systems can also be more efficient and accurate, and can increase the objectivity of diagnosis by reducing operator variability. We propose a multi-scale input and multi-feature network (MSI-MFNet) model, which can learn the overall structures and texture features of different scale tissues by fusing multi-resolution hierarchical feature maps from the network’s dense connectivity structure. The MSI-MFNet predicts the probability of a disease on the patch and image levels. We evaluated the performance of our proposed model on two public benchmark datasets. Furthermore, through ablation studies of the model, we found that multi-scale input and multi-feature maps play an important role in improving the performance of the model. Our proposed model outperformed the existing state-of-the-art models by demonstrating better accuracy, sensitivity, and specificity.

Texture Extraction and Identification of 3D Engineering Surfaces

2005 ◽  
Vol 295-296 ◽  
pp. 453-458
Author(s):  
W. Zeng ◽  
X. Jiang ◽  
Y. Gao ◽  
T. Xie
Keyword(s):  
Spectrum Analysis ◽  
Texture Features ◽  
Angular Spectrum ◽  
Gabor Wavelet ◽  
Directional Characteristic ◽  
Multi Scale ◽  
Differential Operation ◽  
Complex Engineering ◽  
Gabor Wavelet Transformation ◽  
Texture Extraction

For linear textures, widely exist on 3D engineering surfaces, a method for characterization based on the spectrum analysis is proposed. Through an angular spectrum analysis of the power spectrum of 3D surface signals, the directional characteristic parameters of the linear texture distribution on the surface are extracted. By using the directional parameters, the engineering surface can be roughly identified. A texture detector based on the directional Gabor wavelet transformation is used to detect the texture signals. The linear texture features of different directions and scales on a complex engineering surface can be decomposed. A weighting multi-scale correlative analyzing method is presented. The correlation analysis results of the texture features of different scales are weighted according to the significance and summed to obtain the final correlation results. Through Laplacian differential operation of the correlative output, a sharper correlative peak is obtained. This method has been successfully used to extract and identify bullet marks.

Sign in / Sign up

Export Citation Format

Share Document