Use of similarity metrics in template-based detection of objects in images

被引：0

作者：

Rubel O. ^{[1
]}

Abramov S. ^{[1
]}

Abramova V. ^{[1
]}

Lukin V. ^{[1
]}

机构：

[1] National Aerospace University, Kharkiv Aviation Institute, 17 Chkalov St., Kharkiv

来源：

Telecommunications and Radio Engineering (English translation of Elektrosvyaz and Radiotekhnika) | 2019年 / 78卷 / 14期

关键词：

Noise; Similarity metrics; Template-based detection;

D O I：

10.1615/TelecomRadEng.v78.i14.30

中图分类号：

学科分类号：

摘要：

A task of template-based detection of similar objects or blocks in images is considered. As a measure of similarity, different similarity metrics (distances) are studied under assumption that noise is present in images or video frames. It is shown that there are metrics that are able to perform sufficiently better than standard Euclidean norm in both spatial or transform domain, especially if noise is intensive and/or has certain degree of spatial correlation. Analysis is carried out for five test images and a wide set of noise variance values. Traditional and unconventional criteria of detection are applied. ©2019 by Begell House, Inc.

引用

页码：1249 / 1261

页数：12

共 24 条

[11]

Brunelli R., Template Matching Techniques in Computer Vision: Theory and Practice, (2009)

[12]

Sullivan G.J., Ohm J.R., Han W.J., Wiegand T., Overview of the high efficiency video coding (HEVC) standard, IEEE Transactions on Circuits and Systems for Video Technology, (2012)

[13]

Rubel A.S., Lukin V.V., Egiazarian K., Metric performance in similar blocks search and their use in collaborative 3D filtering of grayscale images, Proceedings of SPIE, 9019, (2014)

[14]

Kumar S., Biswas M., Nguyen T.Q., Global motion estimation in frequency and spatial domain, IEEE International Conference on Speech, Acoustics, and Signal Processing, pp. 14-23, (2004)

[15]

Rubel A.S., Lukin V.V., Similar patch search in Rs images using different metrics, Proceedings of MSMW, (2013)

[16]

Cieslak D.A., Hoens T.R., Chawla N.V., Kegelmeyer W.P., Hellinger distance decision trees are robust and skew-insensitive, Data Mining and Knowledge Discovery, 24, 1, pp. 136-158, (2012)

[17]

Fraser A.M., Incorporating invariants in Mahalanobis distance based classifiers: Application to face recognition, Neural Networks, Proceedings of the International Joint Conference, 4, pp. 3118-3123, (2003)

[18]

Emran S.M., Robustness of Canberra metric in computer intrusion detection, Proceedings of the IEEE Workshop on Information Assurance and Security, (2001)

[19]

Kadir A., Nugroho L.E., Susanto A., Santosa P.I., Experiments of distance measurements in a foliage plant retrieval system, International Journal of Signal Processing, Image Processing and Pattern Recognition, 5, 2, (2012)

[20]

van Dongen S., Enright A.J., Metric distances derived from cosine similarity and Pearson and Spearman correlations, Proceedings of CoRR, (2012)

← 1 2 3 →