Complementary Cohort Strategy for Multimodal Face Pair Matching
Complementary Cohort Strategy for Multimodal Face Pair Matching
复制标题
多模态人脸对匹配的补充队列策略
DOI：
10.1109/tifs.2015.2512561
复制
发表时间：
2016-05
影响因子：
6.8
通讯作者：
Tieniu Tan
中科院分区：
文献类型：
--
作者：
Yunlian Sun;Kamal Nasrollahi;Zhenan Sun;Tieniu Tan
人脸对匹配是确定两张人脸图像是否代表同一个人的任务。由于两幅人脸图像中所包含的表情信息有限，而人脸变化的来源又多种多样，这就成为一个相当困难的问题。对于很少有可用的图像来表示每个面孔的问题，我们建议通过一系列队列列表比较来利用额外的队列集（队列集中的身份与正在比较的身份不同）。然后从排序的群组身份和排序的群组图像中提取有用的群组系数以用于补充信息。为了增强其对复杂面部变化的鲁棒性，我们进一步采用多个面部模态，因为它们彼此互补的价值，用于面部对匹配任务。通过将提取的群组系数与所有可用面部模态的直接匹配分数融合来做出最终决定。为了研究每个个体模态在匹配人脸、队列行为以及使用我们的互补队列策略所实现的性能上的能力，我们在两个最近收集的多模态人脸数据库上进行了一组实验。结果表明，使用不同的模态导致不同的人脸对匹配性能。对于每种方式，采用我们的队列方案显着降低了等错误率。通过应用所提出的多模态互补队列策略，我们在人脸对匹配任务上实现了最佳性能。
Face pair matching is the task of determining whether two face images represent the same person. Due to the limited expressive information embedded in the two face images as well as various sources of facial variations, it becomes a quite difficult problem. Toward the issue of few available images provided to represent each face, we propose to exploit an extra cohort set (identities in the cohort set are different from those being compared) by a series of cohort list comparisons. Useful cohort coefficients are then extracted from both sorted cohort identities and sorted cohort images for complementary information. To augment its robustness to complicated facial variations, we further employ multiple face modalities owing to their complementary value to each other for the face pair matching task. The final decision is made by fusing the extracted cohort coefficients with the direct matching score for all the available face modalities. To investigate the capacity of each individual modality on matching faces, the cohort behavior, and the performance achieved using our complementary cohort strategy, we conduct a set of experiments on two recently collected multimodal face databases. It is shown that using different modalities leads to different face pair matching performance. For each modality, employing our cohort scheme significantly reduces the equal error rate. By applying the proposed multimodal complementary cohort strategy, we achieve the best performance on our face pair matching task.
登录
查看更多内容
影响因子：
2.1
作者：
Park, Mee Young;Hastie, Trevor
通讯作者：
Hastie, Trevor
DOI：
10.5281/zenodo.41648
发表时间：
2009-08
期刊：
2009 17th European Signal Processing Conference
影响因子：
--
作者：
N. Poh;A. Merati;J. Kittler
通讯作者：
N. Poh;A. Merati;J. Kittler
DOI：
10.1007/978-0-387-71041-9
发表时间：
2007-10
期刊：
--
影响因子：
--
作者：
Anil K. Jain;P. Flynn;A. Ross
通讯作者：
Anil K. Jain;P. Flynn;A. Ross
DOI：
10.1109/btas.2013.6712738
发表时间：
2013-09
期刊：
2013 IEEE Sixth International Conference on Biometrics: Theory, Applications and Systems (BTAS)
影响因子：
--
作者：
Yunlian Sun;M. Tistarelli;N. Poh
通讯作者：
Yunlian Sun;M. Tistarelli;N. Poh
DOI：
10.1109/icassp.1996.540295
发表时间：
1996-05
期刊：
1996 IEEE International Conference on Acoustics, Speech, and Signal Processing Conference Proceedings
影响因子：
--
作者：
A. Rosenberg;S. Parthasarathy
通讯作者：
A. Rosenberg;S. Parthasarathy