11,092 Hits in 3.6 sec

Conformity-Based Transfer AdaBoost Algorithm [chapter]

Shuang Zhou, Evgueni N. Smirnov, Haitham Bou Ammar, Ralf Peeters
2013 IFIP Advances in Information and Communication Technology  
This paper proposes to consider the region classification task in the context of instance-transfer learning.  ...  The proposed solution consists of the conformal algorithm that employs a nonconformity function learned by the Transfer AdaBoost algorithm.  ...  Thus by employing region classification we can control the error in a long run which however has practical sense if the class regions are efficient; i.e., small.  ... 
doi:10.1007/978-3-642-41142-7_41 fatcat:mjp7kn4v45bdzle4lt4pyxk2kq

Improvements of Object Detection Using Boosted Histograms

I. Laptev
2006 Procedings of the British Machine Vision Conference 2006  
We present a method for object detection that combines AdaBoost learning with local histogram features.  ...  AdaBoost learning AdaBoost [6] is a popular machine learning method combining properties of an efficient classifier and feature selection.  ...  In the context of visual object recognition it is attractive to define f in terms of local image properties over image regions r and then use AdaBoost for selecting features maximizing the classification  ... 
doi:10.5244/c.20.97 dblp:conf/bmvc/Laptev06 fatcat:c2djtqmq3vbfbjhfgbb5um47ue

Fast and Robust Classification using Asymmetric AdaBoost and a Detector Cascade

Paul A. Viola, Michael J. Jones
2001 Neural Information Processing Systems  
We propose a new variant of AdaBoost as a mechanism for training the simple classifiers used in the cascade.  ...  Experimental results in the domain of face detection show the training algorithm yields significant improvements in performance over conventional AdaBoost.  ...  Given the constraint that the search over features is greedy, AdaBoost efficiently selects the feature which minimizes x ¡ § ¡ , a surrogate for overall classification error.  ... 
dblp:conf/nips/ViolaJ01 fatcat:qjtvmmerfbfhlo4ngrvxd2ex6e

Application of Multi-Class AdaBoost Algorithm to Terrain Classification of Satellite Images

Ngoc-Hoa Nguyen, Dong-Min Woo
2014 Journal of IKEEE  
Also, the AdaBoost algorithm selects only critical features and generates an extremely efficient classifier.  ...  Experimental result indicates that the classification accuracy of AdaBoost classifier is much higher than that of the conventional classifier using back propagation algorithm.  ...  of dark regions and the sum of bright regions.  ... 
doi:10.7471/ikeee.2014.18.4.536 fatcat:m5yefybimzhblkxlj3zhaafjwy

Combination of Textural Features for the Improvement of Terrain Classification and Change Detection

Hoang Lam Le, Dong-Min Woo
2015 International Journal of Software Engineering and Its Applications  
To verify the efficiency of the proposed classification method, change detection using temporal images is also tested via experiment.  ...  We implement BPNN (Back Propagation neural network) and Adaboost algorithms for the classification of an urban area in terms of a combination of several textural features.  ...  Using this combination, Adaboost and BPNN achieve mean accuracy of region classification values of 94.5% and 89.8%, respectively in region classification.  ... 
doi:10.14257/ijseia.2015.9.5.14 fatcat:clavvgddv5fntjz6kmpdxhhiyi

Gabor Wavelet based Face Recognition System using EWCVT and Bagging Adaboost Algorithm

Srinivasan A
2011 International Journal of Computer Applications  
To reduce the data, edge weighted centroidal voronoi tessellation (EWCVT) is used and to increase the efficiency a classifier called Bagging AdaBoost is used.  ...  This method lacks in efficiency and computational complexity because it involves huge volume of data.  ...  So, in order to obtain a better recognition system and make the training process efficient a classification method is used.  ... 
doi:10.5120/2039-2667 fatcat:4nkgm44byvghheweo4jksuues4

Hemolysis detection based on SVM of Adaboost classification algorithm

xiaonan Shi, Zitong Wang, Zhenmin Zhao, J. Heled, A. Yuan
2018 MATEC Web of Conferences  
The Adaboost learning classification test based on SVM is compared with the macroscopic and red blood cell counting methods.  ...  The experimental results show that the learning-based classification testing method achieves higher detection accuracy without subjective factors and has the highest detection efficiency.  ...  In this paper, a new Adaboost classification method based on SVM is proposed.  ... 
doi:10.1051/matecconf/201817303006 fatcat:qjtshxmx3jbeziqa7vhs7bgisu


2014 Journal of Computer Science  
The contourlet features with Support vector machine classifier produced classification accuracy of 85.6% compared to 81.3% accuracy in Adaboost classifier.  ...  Images were normalized and plaque regions have been manually segmented by experts and these Region Of Interests (ROI) have been used for further processing. 4 level Contourlet transform has been applied  ...  The curvelet transform and wavelet packet have also been applied to all the selected Region of interests and classification was done using SVM and adaboost classifiers from the selected features.  ... 
doi:10.3844/jcssp.2014.1642.1649 fatcat:xjtdhln44facthkdgp6eigq6dm

Automatic human face detection for content-based image annotation

Richard M. Jiang, Abdul H. Sadka, Huiyu Zhou
2008 2008 International Workshop on Content-Based Multimedia Indexing  
The initial experimental benchmark shows the proposed scheme can be efficiently applied for image annotation with higher fidelity.  ...  In the face detection, the probable face region is detected by adaptive boosting algorithm, and then combined with a colour filtering classifier to enhance the accuracy in face detection.  ...  AdaBoost uses a cascaded scheme, as shown in Fig.3 , to overcome this problem and achieve the best of both worlds: high detection rates and extremely fast classification [14] .  ... 
doi:10.1109/cbmi.2008.4564929 dblp:conf/cbmi/JiangSZ08 fatcat:uanp7ftasfalrct7lafg22zofi

Learning local binary patterns for gender classification on real-world face images

Caifeng Shan
2012 Pattern Recognition Letters  
Local Binary Patterns (LBP) is employed to describe faces, and Adaboost is used to select the discriminative LBP features.  ...  However, real-world applications require gender classification on real-life faces, which is much more challenging due to significant appearance variations in unconstrained scenarios.  ...  To improve computation efficiency, we adopted a coarse to fine feature selection scheme: We first run Adaboost to select LBPH bins from each single scale LBP (8, R, u2) , then applied Adaboost to the  ... 
doi:10.1016/j.patrec.2011.05.016 fatcat:irojnour7rggzdiptpwv6sv6nq

Shape Classification Using Local and Global Features

Kart-Leong Lim, Hamed Kiani Galoogahi
2010 2010 Fourth Pacific-Rim Symposium on Image and Video Technology  
Moreover, by using a learning algorithm based on Adaboost we improve the global feature extraction by selecting a small number of more discriminative visual features through a large raw visual features  ...  set to increase the classification accuracy.  ...  As an efficient image descriptor, the histogram of gradient orientation is used efficiently by SIFT [1] for object classification [5] and human detection [2] .  ... 
doi:10.1109/psivt.2010.26 fatcat:ct4w3rojdve7dee7kxs25jeagu

Crop region extraction of remote sensing images based on fuzzy ARTMAP and adaptive boost

Da-Wei Li, Feng-Bao Yang, Xiao-Xia Wang, Ildar Batyrshin, Dragan S. Pamučar, Paolo Crippa, Feng Liu
2015 Journal of Intelligent & Fuzzy Systems  
With more samples, the algorithm efficiency is greatly affected. This paper proposes an improved fuzzy ARTMAP (FAM) with an adaptive boost strategy, namely Adaboost FAM.  ...  Weak classifiers are trained to construct strong classifiers so as to improve operation efficiency. Meanwhile, classification accuracy will not be greatly improved.  ...  Automatic classification accuracy and efficiency have been subjects of constant improvement.  ... 
doi:10.3233/ifs-151983 fatcat:3gvn5tpj35clteneulyaz46yaq

Improving object detection with boosted histograms

Ivan Laptev
2009 Image and Vision Computing  
AdaBoost learning AdaBoost [8] is a popular machine learning method combining properties of an efficient classifier and feature selection.  ...  Although efficient, such an approach can be suboptimal if a chosen set of functions g j is not well suited for a given classification problem.  ... 
doi:10.1016/j.imavis.2008.08.010 fatcat:em5ebtio4zhndi554jgimwqnmm

Learning-based Human Fall Detection using RGB-D cameras

Szu-Hao Huang, Ying-Cheng Pan
2013 IAPR International Workshop on Machine Vision Applications  
A background subtraction method based on iterative normalized-cut segmentation algorithm is proposed to identify the pixel-wise human regions rapidly.  ...  The experimental results based on a leave-one-out cross-validation testing show that our proposed system can detect the fall events effectively and efficiently.  ...  Classification Algorithms The accuracy of different classification algorithms is compared in this section, which include four discriminant analysis methods and AdaBoost classification.  ... 
dblp:conf/mva/HuangP13 fatcat:3kh2ourdlbe6dilvuvytqntihu

Multi-Stage Approach to Fast Face Detection

D. D. Le, S. Satoh
2005 Procedings of the British Machine Vision Conference 2005  
(ii) Second, we propose using SVM classifiers instead of AdaBoost classifiers in the last stage and study how to efficiently reuse Haar wavelet features selected by AdaBoost in the previous stage for SVM  ...  However, it is distinguished from the previous work by two facts: (i) First, a new stage is added to more quickly estimate face candidate regions by using a larger window size and a larger moving step  ...  Efficiency of SVM Classifiers Efficiency of a single SVM classifier over cascaded AdaBoost classifiers on hard classified patterns is shown in Figure 5 .  ... 
doi:10.5244/c.19.61 dblp:conf/bmvc/LeS05 fatcat:a5txm7knkvcjzds3du46yjiika
« Previous Showing results 1 — 15 out of 11,092 results