Home > Published Issues > 2017 > Volume 6, No. 2, April 2017 >


J Naga Surekha1*, Y Sri Chakrapani2, and N.Venkatewsara Rao3
1.Embedded Systems, Gudlavalleru Engineering College, Gudlavalleru, India.
2.Department of ECE, Gudlavalleru Engineering College, Gudlavalleru, India.
3.Department of ECE, Bapatla Engineering College, Bapatla , India.

Abstract—In this paper, the synopsis of local invariant interest point detectors, their working, advantages, disadvantages and recent trends are presented. The features detector extracts the features from the image, e.g., a corner, blob or edge detector. A features detector is said to be invariant if under a certain family of transformations if its value does not change when a transformation from this family is applied to its argument. The characteristics of this detector are robustness, repeatability, accuracy, generality, efficiency, quantity etc. Some of the feature detectors are SIFT SURF, FAST, BRISK, ORB and HCD. These descriptors are compared according to their average processing time per frame.

Index Terms—Feature, SURF, FAST, ORB, HCD

Cite: J Naga Surekha, Y Sri Chakrapani and N.Venkatewsara Rao, "A SURVEY OF TRENDS IN LOCAL INVARIANT FEATURE DETECTORS," International Journal of Electrical and Electronic Engineering & Telecommunications, Vol. 6, No. 2, pp. 9-17, April 2017.