Image Classification With Densely Sampled Image Windows and Generalized Adaptive Multiple Kernel Learning

Yan, Shengye; Xu, Xinxing; Xu, Dong; Lin, Stephen; Li, Xuelong

doi:10.1109/tcyb.2014.2326596

Cited by 32 publications

(9 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The idea of combining the outputs of several individual classifiers to produce an ensemble has gained a lot of interest in many machine learning communities and pattern recognition applications [1,2,3,4]. In machine learning, classifier ensembles have been very popular recently because they often improve classification performance significantly.…”

Section: Introductionmentioning

confidence: 99%

Classifier ensembles for image identification using multi-objective Pareto features

2017

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Classifier ensembles for image identification using multi-objective Pareto features

2017

View full text Add to dashboard Cite

“…In this experiment, the regular spatial pooling in SPM method with two pyramid levels is used to partition the pyramid level. The two pyramid levels (L=2) that were used in this work are according to the experimental setup used in a previous study [19,34,35,36]. The previous settings used L=2 with vocabulary size of M=200 and were tested on a small resolution image of about 300 × 250 pixels [19].…”

Section: Methodsmentioning

confidence: 99%

Vision-Based Apple Classification for Smart Manufacturing

Ismail

Idris

Ayub

et al. 2018

Sensors

View full text Add to dashboard Cite

Smart manufacturing enables an efficient manufacturing process by optimizing production and product transaction. The optimization is performed through data analytics that requires reliable and informative data as input. Therefore, in this paper, an accurate data capture approach based on a vision sensor is proposed. Three image recognition methods are studied to determine the best vision-based classification technique, namely Bag of Words (BOW), Spatial Pyramid Matching (SPM) and Convolutional Neural Network (CNN). The vision-based classifiers categorize the apple as defective and non-defective that can be used for automatic inspection, sorting and further analytics. A total of 550 apple images are collected to test the classifiers. The images consist of 275 non-defective and 275 defective apples. The defective category includes various types of defect and severity. The vision-based classifiers are trained and evaluated according to the K-fold cross-validation. The performances of the classifiers from 2-fold, 3-fold, 4-fold, 5-fold and 10-fold are compared. From the evaluation, SPM with SVM classifier attained 98.15% classification accuracy for 10-fold and outperformed the others. In terms of computational time, CNN with SVM classifier is the fastest. However, minimal time difference is observed between the computational time of CNN and SPM, which were separated by only 0.05 s.

show abstract

“…Althloothi et al [44] used a MKL method to fuse two sets of features, namely shape representation and kinematic structure features, for human activity recognition using a sequence of RGB-D images. Later, Yan et al [45] introduced a generalized adaptive lp-norm multiple kernel learning (GA-MKL) to train a robust image classifier based on multiple base kernels.…”

Section: Mkl In Biometric Identificationmentioning

confidence: 99%

User Identification Using Real Environmental Human Computer Interaction Behavior

Wu¹,

Zheng²,

Wu³

et al. 2019

KSII TIIS

View full text Add to dashboard Cite

In this paper, a new user identification method is presented using real environmental human-computer-interaction (HCI) behavior data to improve method usability. User behavior data in this paper are collected continuously without setting experimental scenes such as text length, action number, etc. To illustrate the characteristics of real environmental HCI data, probability density distribution and performance of keyboard and mouse data are analyzed through the random sampling method and Support Vector Machine(SVM) algorithm. Based on the analysis of HCI behavior data in a real environment, the Multiple Kernel Learning (MKL) method is first used for user HCI behavior identification due to the heterogeneity of keyboard and mouse data. All possible kernel methods are compared to determine the MKL algorithm's parameters to ensure the robustness of the algorithm. Data analysis results show that keyboard data have a narrower range of probability density distribution than mouse data. Keyboard data have better performance with a 1-min time window, while that of mouse data is achieved with a 10-min time window. Finally, experiments using the MKL algorithm with three global polynomial kernels and ten local Gaussian kernels achieve a user identification accuracy of 83.03% in a real environmental HCI dataset, which demonstrates that the proposed method achieves an encouraging performance.

show abstract

Image Classification With Densely Sampled Image Windows and Generalized Adaptive Multiple Kernel Learning

Cited by 32 publications

References 31 publications

Classifier ensembles for image identification using multi-objective Pareto features

Classifier ensembles for image identification using multi-objective Pareto features

Vision-Based Apple Classification for Smart Manufacturing

User Identification Using Real Environmental Human Computer Interaction Behavior

Contact Info

Product

Resources

About