Maximum-likelihood approximate nearest neighbor method in real-time image recognition
详细信息 查看全文
- 作者：A.V. Savchenko avsavchenko@hse.ru" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：AESA ; Approximating and Eliminating Search Algorithm ; ANN ; approximate nearest neighbor ; DEM ; directed enumeration method ; DNN ; deep neural network ; HOG ; histograms of oriented gradients ; HT-PNN ; homogeneity testing probabilistic neural network ; ML-ANN ; maximal-likelihood approximate nearest neighbor ; NN ; nearest neighbor ; P-ML-ANN ; pivot-based maximal-likelihood approximate nearest neighbor ; SVM ; support vector machine
- 刊名：Pattern Recognition
- 出版年：2017
- 出版时间：January 2017
- 年：2017
- 卷：61
- 期：Complete
- 页码：459-469
- 全文大小：1518 K
文摘
- •
Maximal-likelihood search improves the performance of the nearest neighbor method.
- •
Proposed method is 2-10 faster than brute force, randomized kd-tree and perm-sort.
- •
Unlike the baseline DEM, proposed method does not require quadratic memory space.
- •
The method is applied with similarity measures which do not met metric properties.