• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Feature Voting for Object Localization via Density Ratio Estimation

Vol. 13, No. 12, December 31, 2019
10.3837/tiis.2019.12.012, Download Paper (Free):

Abstract

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes’ theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
L. Wang, D. Deng and C. Chen, "Feature Voting for Object Localization via Density Ratio Estimation," KSII Transactions on Internet and Information Systems, vol. 13, no. 12, pp. 6009-6027, 2019. DOI: 10.3837/tiis.2019.12.012.

[ACM Style]
Liantao Wang, Dong Deng, and Chunlei Chen. 2019. Feature Voting for Object Localization via Density Ratio Estimation. KSII Transactions on Internet and Information Systems, 13, 12, (2019), 6009-6027. DOI: 10.3837/tiis.2019.12.012.