Local Feature Detectors Performance Analysis on Digital Image

The article puts an experiment on application of widely used ORB, SIFT and SURF feature point detectors represented by the corresponding functions in the OpenCV library, to the images of the most common object classes such as human faces, fine details and artificial images. The considered detectors display as a result a huge number of points that are not classified or structured. Building an appropriate classifier would greatly increase the efficiency of subsequent image processing operations: localization, recognition, search, and tracking of objects. The article analyzes the effectiveness of the experimental results at a quantitative and qualitative level taking into account the conditions and limitations (primarily temporal) on solving practical problems in the era of Big Data, as well as taking into account the fact that some detectors are proprietary. According to the analysis results of the usage effectiveness of the features points detectors considered in the work the practical recommendations for specific use cases are given at the end of the work.

[1]  Milan Sonka,et al.  Image Processing, Analysis and Machine Vision , 1993, Springer US.

[2]  Milan Sonka,et al.  Image processing analysis and machine vision [2nd ed.] , 1999 .

[3]  A. N. Kopylev,et al.  Modelling of multiservice streams at the decision of tasks of parametric synthesis , 2013, 2013 23rd International Crimean Conference "Microwave & Telecommunication Technology".

[4]  Vitalii Tkachov,et al.  Method for transfer of data with intermediate storage , 2014, 2014 First International Scientific-Practical Conference Problems of Infocommunications Science and Technology.

[5]  Jun Su,et al.  The Method of Variant Synthesis of Information and Communication Network Structures on the Basis of the Graph and Set-Theoretical Models , 2017 .

[6]  Oleksandr Lemeshko,et al.  Enhanced method of fast re-routing with load balancing in software-defined networks , 2017 .

[7]  Igor Ruban,et al.  Network Technology for Transmission of Visual Information , 2019 .

[8]  Kirill Smelyakov,et al.  Investigation of network infrastructure control parameters for effective intellectual analysis , 2018, 2018 14th International Conference on Advanced Trends in Radioelecrtronics, Telecommunications and Computer Engineering (TCSET).

[9]  Valentin Filatov,et al.  Methods for Synthesis of Relational Data Model in Information Systems Reengineering Problems , 2018, 2018 International Scientific-Practical Conference Problems of Infocommunications. Science and Technology (PIC S&T).

[10]  Igor Ruban,et al.  Method of neural network recognition of ground-based air objects , 2018, 2018 IEEE 9th International Conference on Dependable Systems, Services and Technologies (DESSERT).

[11]  Igor Ruban,et al.  Evolution of Convolutional Neural Network Architecture in Image Classification Problems , 2019 .