Saliency Filtering of SIFT Detectors: Application to CBIR

Awad, Dounia; Courboulay, Vincent; Revel, Arnaud

doi:10.1007/978-3-642-33140-4_26

Cited by 13 publications

(10 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To name a couple of simple examples, applications like saliency manipulation (Margolin, Zelnik-Manor, & Tal, 2013), image retrieval (Awad, Courboulay, & Revel, 2012), decolorization (Ancuti, Ancuti, & Bekaert, 2011) could use the proposed model to improve their effectiveness.…”

Section: Resultsmentioning

confidence: 99%

Saccadic model of eye movements for free-viewing condition

2015

View full text Add to dashboard Cite

In this paper, we propose a new framework to predict visual scanpaths of observers while they freely watch a visual scene. The visual fixations are inferred from bottom-up saliency and several oculomotor biases. Bottom-up saliency is represented by a saliency map whereas the oculomotor biases (saccade amplitudes and saccade orientations) are modeled using public eye tracking datasets. Our experiments show that the simulated scanpaths exhibit similar trends of human eye movements in a free-viewing condition. The generated scanpaths are more similar to human scanpaths than those generated by two existing methods. In addition, we show that computing saliency maps from simulated visual scanpaths allows to outperform existing saliency models.

show abstract

Section: Resultsmentioning

confidence: 99%

Saccadic model of eye movements for free-viewing condition

2015

View full text Add to dashboard Cite

show abstract

“…The saliency threshold value for this binary classifier varies from 0.2 to 0.3. In [29], [30], the saliencybased feature filtering was used on SIFT features. More specifically, instead of defining a global threshold for all images as in [28], the threshold is made depend on each image and set to 3 times the average salience of the image in [29].…”

Section: Saliency-based Methodsmentioning

confidence: 99%

Performance Evaluation of State-of-the-Art Filtering Criteria Applied to SIFT Features

Silvère

Pothin

Honeiné

et al. 2019

2019 IEEE International Symposium on Signal Processing and Information Technology (ISSPIT)

View full text Add to dashboard Cite

Feature matching is an important and crucial task in computer vision. Unfortunately, the features extracted from images are usually redundant or irrelevant, leading to many ambiguities and false positives during matching. This work provides an exhaustive study of state-of-the-art feature filtering strategies investigating different criteria, such as the contrast level, inner primary ratio, entropy, saliency and median value, in the purpose of discarding irrelevant features. The evaluation on the well-known Oxford-5k dataset demonstrates the relevance of these criteria to reduce the amount of data involved in the matching step and the number of false positives, thus leading to faster and more accurate matching with almost no loss in performance. Our results are also compared to convolutional neural networks (CNNs), providing extensive experiments that corroborate recently published work.

show abstract

“…In this area the main approach is to (1) extract features (SIFT, SURF, or any others) from the object, (2) filter the features based on a saliency map, and (3) perform the recognition based on a classifier (such as a SVM or others). Papers like [117] or [118] apply this technique which let a computer drastically decrease the number of needed key points to perform the object recognition. Further details can be found in Chap.…”

Section: Object Recognitionmentioning

confidence: 98%

Applications of Saliency Models

Mancaş¹,

Meur²

2016

From Human Attention to Computational Attention

View full text Add to dashboard Cite

International audienceThis chapter proposes a taxonomy to classify the real-life applications which can benefit from the use of attention models. There are numerous applications and we try here to remain as exhaustive as possible to provide a picture of all the applications of saliency models, but also to detect where future developments might be of interest. The applications are grouped into three categories. The first one uses the detection of the most important regions in an image and contains applications such as video surveillance, audio surveillance, defect detection, pathology detection, expressive and social gestures, computer graphics and quality metrics. The second category uses saliency maps to detect the regions which are the less interesting in an image. Here one can found applications like texture metrics, compression, retargeting, summarization, watermarking and attention-based ad insertion. Finally, a third category uses the most interesting areas in an image with further processing like comparisons between those areas. In this category one can find image registration and landmarks, object recognition, action guidance in robotics or avatars, web sites optimization, images memorability, best viewpoint, symmetries and automatic focus on images

show abstract

Saliency Filtering of SIFT Detectors: Application to CBIR

Cited by 13 publications

References 10 publications

Saccadic model of eye movements for free-viewing condition

Saccadic model of eye movements for free-viewing condition

Performance Evaluation of State-of-the-Art Filtering Criteria Applied to SIFT Features

Applications of Saliency Models

Contact Info

Product

Resources

About