Asymmetry as a Measure of Visual Saliency

Alsam, Ali; Sharma, Puneet; Wrålsen, Anette

doi:10.1007/978-3-642-38886-6_55

Cited by 3 publications

(11 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For our comparison, eleven state-of-the-art saliency models, namely, AIM by Bruce and Tsotsos [40], AWS by Garcia-Diaz et al [27], Erdem by Erdem and Erdem [22], Hou by Hou and Zhang [41], Spec by Schauerte and Stiefelhagen [42], GBA by Alsam et al [24,25], fast GBA proposed in this paper (S f = 0.5, N r = 3, b = 22; for details, please see Section 4.6), GBVS by Harel et al [43], Itti by Itti et al [26], Judd by Judd et al [16] and LG by Borji and Itti [44] are used. In line with the study by Borji et al [45], two models are selected to provide a baseline for the evaluation.…”

Section: Saliency Modelsmentioning

confidence: 99%

“…To observe if de-correlation of color image channels (mentioned in Section 3.3) influences the performance of group-based saliency models, we performed an analysis on two versions of the GBA by Alsam et al [24,25] and the proposed fast GBA models. In the first versions of both algorithms, we used the color space from the original GBA algorithm (luminance channel, red-green and blue-yellow color opponency channels).…”

Section: Impact Of De-correlation On the Performance Of The Proposed mentioning

confidence: 99%

“…Alsam et al [24,25] proposed a saliency model that uses asymmetry as a measure of saliency. In order to calculate saliency, the input image is decomposed into non-overlapping square blocks (as shown at the top-left in Figure 3), and for each block, the absolute difference between the block itself and the result of the D 4 group elements acting on the block is calculated.…”

Section: Introductionmentioning

confidence: 99%

“…Instead of calculating asymmetry values associated with each group element and followed by their sum, we propose that the algorithm can run faster if the calculations in Equation (1) [24,25], the figure shows an example image (from [16]) along with the associated saliency map. The figure on the top-right shows the eight group transformations pertaining to a square block of an image.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Sharma

2016

Symmetry

Self Cite

View full text Add to dashboard Cite

Abstract:In this paper, first, we briefly describe the dihedral group D 4 that serves as the basis for calculating saliency in our proposed model. Second, our saliency model makes two major changes in a latest state-of-the-art model known as group-based asymmetry. First, based on the properties of the dihedral group D 4 , we simplify the asymmetry calculations associated with the measurement of saliency. This results is an algorithm that reduces the number of calculations by at least half that makes it the fastest among the six best algorithms used in this research article. Second, in order to maximize the information across different chromatic and multi-resolution features, the color image space is de-correlated. We evaluate our algorithm against 10 state-of-the-art saliency models. Our results show that by using optimal parameters for a given dataset, our proposed model can outperform the best saliency algorithm in the literature. However, as the differences among the (few) best saliency models are small, we would like to suggest that our proposed model is among the best and the fastest among the best. Finally, as a part of future work, we suggest that our proposed approach on saliency can be extended to include three-dimensional image data.

show abstract

Section: Saliency Modelsmentioning

confidence: 99%

Section: Impact Of De-correlation On the Performance Of The Proposed mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Sharma

2016

Symmetry

Self Cite

View full text Add to dashboard Cite

show abstract

“…Itti et al, 44 Walther, 50 Walther et al, 51 Frintrop, 52 Meur et al, 54 Rajashekar et al, 55 Cerf et al, 36 Murray et al, 78 Erdem and Erdem, 24 Alsam et al 56,57 and Borji and Itti 53 …”

Section: Cognitive Modelsmentioning

confidence: 99%

Evaluating Visual Saliency Algorithms: Past, Present and Future

Sharma¹

2015

jist

Self Cite

View full text Add to dashboard Cite

Abstract.A salient image region is defined as an image part that is clearly different from its surround. This difference is measured in terms of a number of attributes, namely, contrast, brightness and orientation. By measuring these attributes, visual saliency algorithms aim to predict the regions in an image that would attract our attention under free viewing conditions. As the number of saliency models has increased significantly in the past two decades, one is faced with the challenge of finding a metric that can be used to objectively quantify the performance of different saliency algorithms. To address this issue in this article, first, the state of the art of saliency models is revisited. Second, the major challenges associated with the evaluation of saliency models are discussed. Third, ten frequently used evaluation metrics are examined and their results are discussed for ten latest state-of-the-art saliency models. INTRODUCTIONOur visual system is selective, i.e., we concentrate on certain aspects of a scene while neglecting other things. This is evident from studies on change blindness, 1-3 which show that large changes can be made in a visual scene that can remain unnoticed. The reason why our visual system is selective is because our brains do not process all the visual information in a scene. In fact, while the optic nerve receives information at the rate of approximately 3 × 10 6 bits/s, the brain processes less than 10 4 bits/s of this information. 4 In other words, the brain uses a tiny fraction (<1%) of the collected information to build a representation of the scene, a representation that is good enough to perform a number of complex activities in the environment such as walking, aiming at objects and detecting objects. Based on this, we can ask what mechanisms are responsible for building this representation of the scene.In the literature, two main attention mechanisms are discussed: top-down and bottom-up. 5-11 Top-down is voluntary, goal-driven and slow, i.e., typically in the range between 100 ms and several seconds. 9 It is assumed that the top-down attention is closely linked with cognitive aspects such as memory, thought and reasoning. For example, by employing top-down mechanisms, we can attend to a

show abstract

Group Based Asymmetry–A Fast Saliency Algorithm

Sharma

Eiksund

2015

Advances in Visual Computing

Self Cite

View full text Add to dashboard Cite

Abstract. In this paper, we propose a saliency model that makes two major changes in a latest state-of-the-art model known as group based asymmetry. First, based on the properties of the dihedral group D4 we simplify the asymmetry calculations associated with the measurement of saliency. This results is an algorithm which reduces the number of calculations by at-least half that makes it the fastest among the six best algorithms used in this paper. Second, in order to maximize the information across different chromatic and multi-resolution features the color image space is de-correlated. We evaluate our algorithm against 10 state-of-the-art saliency models. Our results show that by using optimal parameters for a given data-set our proposed model can outperform the best saliency algorithm in the literature. However, as the differences among the (few) best saliency models are small we would like to suggest that our proposed model is among the best and the fastest among the best.

show abstract

Asymmetry as a Measure of Visual Saliency

Cited by 3 publications

References 23 publications

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Evaluating Visual Saliency Algorithms: Past, Present and Future

Group Based Asymmetry–A Fast Saliency Algorithm

Contact Info

Product

Resources

About

Asymmetry as a Measure of Visual Saliency

Cited by 3 publications

References 23 publications

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Modeling Bottom-Up Visual Attention Using Dihedral Group D4

Evaluating Visual Saliency Algorithms: Past, Present and&#xA0;Future

Group Based Asymmetry–A Fast Saliency Algorithm

Contact Info

Product

Resources

About

Evaluating Visual Saliency Algorithms: Past, Present and Future