A comparative experimental study of image feature detectors and descriptors

Mukherjee, Dibyendu; Wu, Q. M. Jonathan; Wang, Guanghui

doi:10.1007/s00138-015-0679-9

Cited by 99 publications

(84 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For object recognition, BRIEF and SYBA outperformed both SIFT and SURF for high performances value. However, BRIEF and SYBA did not perform well when there is a large viewpoint change, invariance to rotation, and illumination changes [26,27]. In other words, as the descriptor is mostly responsible for improving the feature detector by extracting rotation and illumination invariant descriptors, descriptors such as BRIEF and SYBA that are truly disassociated with any detector would be unable to enhance the capabilities of the detectors, thereby SURF outperformed both BRIEF and SYBA algorithms for high recall values used with orientation and illumination changes.…”

Section: Related Workmentioning

confidence: 91%

“…The BRIEF and SYBA descriptors are binary descriptors that consist of a binary string including the results of intensity comparison at random pre-determined pixel locations. These two descriptor methods employ faster feature detectors and provide lowering descriptor size than SIFT and SURF [26,27]. For object recognition, BRIEF and SYBA outperformed both SIFT and SURF for high performances value.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

SEPIM: Secure and Efficient Private Image Matching

et al. 2016

View full text Add to dashboard Cite

Matching a particular image within extensive datasets has become increasingly pressing in many practical fields. Hence, a number of matching methods have been developed when confidential images are used in image matching between a pair of security agencies, but they are limited by either search cost or search precision. In this paper, we propose a privacy-preserving private image matching scheme between two parties where images are confidential, namely secure and efficient private image matching (SEPIM). The descriptor set of the queried party needs to be generated and encrypted properly with the use of a secret key at the queried party side before being transferred to the other party. We present the development and validation of a secure scheme to measure the cosine similarity between two descriptor sets. To hasten the search process, we construct a tree-based index structure by utilizing the k-means clustering algorithm. The method can work without using any image encryption, sharing, and trusted third party. SEPIM is relatively efficient when set against other methods of searching images over plaintexts, and shows a higher search cost of just 14% and reduction in search precision of just 2%. We conducted several empirical analyses on real image collections to demonstrate the performance of our work.

show abstract

Section: Related Workmentioning

confidence: 91%

Section: Related Workmentioning

confidence: 99%

SEPIM: Secure and Efficient Private Image Matching

et al. 2016

View full text Add to dashboard Cite

show abstract

“…However, there is still a place for faster and more robust techniques, able to successfully describe and match images despite various transformations, distortions, or illumination conditions [6,12,24,25].…”

Section: Proposed Methodsmentioning

confidence: 99%

An approach to vision-based localisation with binary features for partially sighted people

Oszust

Padjasek

Kasprzyk

2017

SIViP

View full text Add to dashboard Cite

In this paper, an approach to the development of a localisation system for supporting visually impaired people is proposed. Instead of using unique visual markers or radio tags, this approach relies on image recognition with local feature descriptors. In order to provide fast and robust keypoint description, a new binary descriptor is introduced. The descriptor computation pipeline selects four image patches with scale-dependent sizes around the keypoint and then places five square pixel blocks within each patch. The binary string is obtained in pairwise tests between directional gradients obtained for blocks. In contrary to other binary descriptors, tests take into account gradient values obtained for blocks from all patches. The proposed approach is extensively tested using six demanding image datasets. Some of them contain labelled indoor and outdoor images under different real-world transformations, as well as challenging illumination conditions. Two datasets were prepared for the needs of this research. Experimental evaluation reveals that the introduced binary descriptor is more robust and achieves shorter computation time than state-of-the-art floating-point and binary descriptors. Furthermore, the approach outperforms other techniques in image recognition tasks, making it more suitable for the vision-based localisation.

show abstract

“…Regarding the quality of feature extractors, a key paper of Mikolajczyk and Schmid [2] introduced a methodology for evaluation of feature invariance to image scale, rotation, exposure and camera viewpoint changes. Mukherjee et al [3] evaluated a wide range of image feature detectors and descriptors, confirming the superior performance of the SIFT algorithm [4]. Other comparisons were aimed at the quality of features for visual odometry [5] or visual Simultaneous Localization and Mapping (SLAM) [6].…”

Section: Introductionmentioning

confidence: 99%

Image features for visual teach-and-repeat navigation in changing environments

Krajník

Cristóforis

Kusumam

et al. 2017

Robotics and Autonomous Systems

View full text Add to dashboard Cite

We present an evaluation of standard image features in the context of long-term visual teach-and-repeat navigation of mobile robots, where the environment exhibits significant changes in appearance caused by seasonal weather variations and daily illumination changes. We argue that for long-term autonomous navigation, the viewpoint-, scaleand rotation-invariance of the standard feature extractors is less important than their robustness to the mid-and longterm environment appearance changes. Therefore, we focus our evaluation on the robustness of image registration to variable lighting and naturally-occurring seasonal changes. We combine detection and description components of different image extractors and evaluate their performance on five datasets collected by mobile vehicles in three different outdoor environments over the course of one year. Moreover, we propose a trainable feature descriptor based on a combination of evolutionary algorithms and Binary Robust Independent Elementary Features, which we call GRIEF (Generated BRIEF). In terms of robustness to seasonal changes, the most promising results were achieved by the SpG/CNN and the STAR/GRIEF feature, which was slightly less robust, but faster to calculate.

show abstract

A comparative experimental study of image feature detectors and descriptors

Cited by 99 publications

References 38 publications

SEPIM: Secure and Efficient Private Image Matching

SEPIM: Secure and Efficient Private Image Matching

An approach to vision-based localisation with binary features for partially sighted people

Image features for visual teach-and-repeat navigation in changing environments

Contact Info

Product

Resources

About