Analysis of Application of Cluster Descriptions in Space of Characteristic Image Features

Data

Olena Peredrii¹  Oleksii Gorokhovatskyi¹  Volodymyr Gorokhovatskyi² 

[1] Department of Informatics and Computer Technologies, Simon Kuznets Kharkiv National University of Economics, Nauky ave. 9-A, 61166 Kharkiv, Ukraine;Department of Informatics, Kharkiv National University of Radio Electronics, Nauky ave. 14, 61166 Kharkiv, Ukraine;

关键词: computer vision;    structural recognition methods;    set of characteristic features;    descriptor;    quantization;    clustering;    competitive learning;    recognition performance;    recognition accuracy;   

DOI  :  10.3390/data3040052

来源: DOAJ

【 摘 要 】

In this paper, we propose an investigation of the properties of structural image recognition methods in the cluster space of characteristic features. Recognition, which is based on key point descriptors like SIFT (Scale-invariant Feature Transform), SURF (Speeded Up Robust Features), ORB (Oriented FAST and Rotated BRIEF), etc., often relating to the search for corresponding descriptor values between an input image and all etalon images, which require many operations and time. Recognition of the previously quantized (clustered) sets of descriptor features is described. Clustering is performed across the complete set of etalon image descriptors and followed by screening, which allows for representation of each etalon image in vector form as a distribution of clusters. Due to such representations, the number of computation and comparison procedures, which are the core of the recognition process, might be reduced tens of times. Respectively, the preprocessing stage takes additional time for clustering. The implementation of the proposed approach was tested on the Leeds Butterfly dataset. The dependence of cluster amount on recognition performance and processing time was investigated. It was proven that recognition may be performed up to nine times faster with only a moderate decrease in quality recognition compared to searching for correspondences between all existing descriptors in etalon images and input one without quantization.

【 授权许可】

Unknown