12 Hits in 2.2 sec

Tool Wear Classification Using LBP-based Descriptors Combined with LOSIB-based Enhancers

O. García-Olalla, E. Alegre, J. Barreiro, L. Fernández-Robles, M.T. García-Ordás
2015 Procedia Engineering  
Two different methods based on Local Binary Pattern (LBP) were evaluated combined with the LOSIB texture booster (Local Oriented Statistical Information Booster).  ...  The results show that when combining LBP with LOSIB, all the other methods are outperformed featuring an 80.58% of accuracy in the binary classification and a 67.76% in the ternary classification.  ...  Local Oriented Statistical Information Booster (LOSIB) The main purpose of the Local Oriented Statistical Information Booster (LOSIB) proposed by García-Olalla et al. in [16] is to enhance the performance  ... 
doi:10.1016/j.proeng.2015.12.582 fatcat:ldypi5jh35azro4frthasuw5n4

Texture features in the Shearlet domain for histopathological image classification

Sadiq Alinsaif, Jochen Lang
2020 BMC Medical Informatics and Decision Making  
In our study, four texture-based descriptors are extracted from the Shearlet coefficients: co-occurrence texture features, Local Binary Patterns, Local Oriented Statistic Information Booster, and segmentation-based  ...  Each set of these attributes captures significant local and global statistics.  ...  Acknowledgements We would like very much to thank the reviewers from the Biomedical and Health Informatics Workshop in the IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2019 for  ... 
doi:10.1186/s12911-020-01327-3 pmid:33323118 fatcat:sab63twg4ff3lemkbgwj52gbbi

On using periocular biometric for gender classification in the wild

Modesto Castrillón-Santana, Javier Lorenzo-Navarro, Enrique Ramón-Balmaseda
2016 Pattern Recognition Letters  
Gender information may serve to automatically modulate interaction to the user needs, among other applications.  ...  Within the Computer Vision community, gender classification (GC) has mainly been accomplished with the facial pattern.  ...  [13] ), and • Local Oriented Statistics Information Booster (LOSIB by [19] .  ... 
doi:10.1016/j.patrec.2015.09.014 fatcat:d4hi455sfndkvov6uzmlfpxkju

Local descriptors fusion for mobile iris verification

N. Aginako, J.M. Martinez-Otzerta, B. Sierra, M. Castrillon-Santana, J. Lorenzo-Navarro
2016 2016 23rd International Conference on Pattern Recognition (ICPR)  
The final step fuses the classifier outputs obtained for 5 different local descriptors, to compute the dissimilarity measure for a pair of iris images.  ...  A classifier is obtained for each descriptor, and the best ones are combined in a multi-classifier system.  ...  . • Local Oriented Statistics Information Booster (LOSIB) [18] . Texture enhancer based on LBP, that computes the local oriented statistical information in the whole cell.  ... 
doi:10.1109/icpr.2016.7899627 dblp:conf/icpr/AginakoMSSL16 fatcat:myhzqccu3fhexgu3jngjgwwsje

Fusion of Holistic and Part Based Features for Gender Classification in the Wild [chapter]

Modesto Castrillón-Santana, Javier Lorenzo-Navarro, Enrique Ramón-Balmaseda
2015 Lecture Notes in Computer Science  
Gender classification (GC) in the wild is an active area of current research.  ...  Those regions are selected for being relevant to the human system according to the psychophysics literature: the ocular and the mouth areas.  ...  -Local Oriented Statistics Information Booster (LOSIB) [12].  ... 
doi:10.1007/978-3-319-23222-5_6 fatcat:fk6n2yj5wjclbhage2pcmlfj4q

Texture analysis using deterministic partially self-avoiding walk with thresholds [article]

Lucas Correia Ribas, Wesley Nunes Gonçalves, Odemir Martinez Bruno
2016 arXiv   pre-print
Experimental results indicate that the proposed method presents a good texture discrimination, overcoming traditional texture methods.  ...  To compose the feature vector, deterministic walks are performed with different thresholds and its statistics are concatenated. Thus, this approach can be considered as a multi-scale analysis.  ...  ACKNOWLEDGMENT The authors gratefully acknowledge support from Coordination for the Improvement of Higher Education Per  ... 
arXiv:1611.08629v1 fatcat:sp6dod3qtrge3jarfps2bmpyly

Space and Contourlet Domains Texture Image Retrieval Algorithm

Xinwu Chen, Jingjing Xue, Li Zhang, Shuangbo Xie, Peng Wang
2017 Proceedings of the 2017 6th International Conference on Measurement, Instrumentation and Automation (ICMIA 2017)   unpublished
In this work, we combine features from traditional approaches with local oriented statistics information booster (LOSIB) to improve the texture image retrieval rates.  ...  Many other methods like local binary patterns are often used to construct texture image retrieval systems.  ...  The second kind feature comes from local oriented statistics information booster.  ... 
doi:10.2991/icmia-17.2017.72 fatcat:27yttlxq2nffplqdxkrpkagnnq

Face Gender Recognition in the Wild: An Extensive Performance Comparison of Deep-Learned, Hand-Crafted, and Fused Features with Deep and Traditional Models

Alhanoof Althnian, Nourah Aloboud, Norah Alkharashi, Faten Alduwaish, Mead Alrshoud, Heba Kurdi
2020 Applied Sciences  
Further, we used T-tests to assess the statistical significance of the differences in performances with respect to the accuracy, f-score, and area under the curve.  ...  In this work, we perform a comprehensive comparative study to analyze the classification performance of two widely used learning models (i.e., CNN and SVM), when they are combined with seven features that  ...  information booster (LOSIB) 86.65% Local salient patterns (LSP) 85.58% HOG + LBP + LOSIB 94.28% CNN + HOG + LBP + LOSIB 97.23% [32] Gabor response CNN Adience 89.20% Webface 91.00%  ... 
doi:10.3390/app11010089 fatcat:dil2nz5tjzbcdfdnbb3yzt5ii4

Fusion of complex networks and randomized neural networks for texture analysis [article]

Lucas C. Ribas, Jarbas J. M. Sa Junior, Leonardo F. S. Scabini, Odemir M. Bruno
2020 arXiv   pre-print
This paper presents a high discriminative texture analysis method based on the fusion of complex networks and randomized neural networks.  ...  complex networks and its topological properties as well as the image pixels are used to train randomized neural networks in order to create a signature that represents the deep characteristics of the texture  ...  Frequency Descriptor (LFD) [40] , Binarized Statistical Image Features (BSIF) [35] , Local Oriented Statistics Information Booster (LOSIB) [25] , Adaptive Hybrid Pattern (AHP) [67] , Complex Network  ... 
arXiv:1806.09170v2 fatcat:wgmnsxiqmvcljc4ly4whdlonpe

The FG 2015 Kinship Verification in the Wild Evaluation

Jiwen Lu, Junlin Hu, Venice Erin Liong, Xiuzhuang Zhou, Andrea Bottino, Ihtesham Ul Islam, Tiago Figueiredo Vieira, Xiaoqian Qin, Xiaoyang Tan, Songcan Chen, Shahar Mahpod, Yosi Keller (+7 others)
2015 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition (FG)  
Booster (LOSIB) [44] .  ...  (HOG) [34] , Local Binary Patterns (LBP) [33] , Local Salient Patterns (L-SP) [42] , Local Directional Patterns (LDP) [43] , Local Phase Quantization (LPQ) [36] , Local Oriented Statistics Information  ... 
doi:10.1109/fg.2015.7163159 dblp:conf/fgr/LuHLZBIVQTCMKZI15 fatcat:o63i5zfqjfha5eg2jkzkmbfv2m

Facial Soft Biometrics: Extracting demographic traits

Salah Eddine Bekhouche
2019 Figshare  
Also, the databases used for age estimation, gender classification or ethnicity classification are exploited. Moreover, the different evaluation terms are mentioned.  ...  These features are extracted either by a holistic method or by a local method.  ...  Abdelkrim Ouafi for his support and guidance throughout this work.  ... 
doi:10.6084/m9.figshare.11378958.v1 fatcat:vwtczj4czva2zkpgvbahtmhc64

Shearlet-Based Descriptors and Deep Learning Approaches for Medical Image Classification

Sadiq Al-Insaif, University, My
Handcrafted techniques based on texture analysis are used for the classification task.  ...  First, we propose a combined texture-based feature representation that is computed in the complex shearlet domain for histopathological image classification.  ...  Local Oriented Statistic Information Booster (LOSIB) In this study, we propose one more novel technique that combines LOSIB [67] with the shearlet transform to capture intrinsic statistical information  ... 
doi:10.20381/ruor-26480 fatcat:xayoo6ek4bfq7fxjx5al6sbeyu