Saliency Detection using Boundary Aware Regional Contrast Based Seam-map

Islam, A. Z. M. Touhidul; Ahsan, Sk. Md. Masudul; Tan, Joo Kooi

doi:10.1109/ciet.2018.8660825

Cited by 2 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In doing so, β = 0.25 is considered in eq. 20 like [8] and [3] to draw F-beta measures in Figure 14. The bars in this figure demonstrate that the presented method clearly surpasses other state of the art techniques.…”

Section: Resultsmentioning

confidence: 99%

“…Many methods including [8]- [12] have combined multiple saliency maps to produce better optimized versions successfully. Some of them became complex and their implementation and performance in real world situations are still to be tested.…”

Section: Related Workmentioning

confidence: 99%

“…The superpixelized input image taken as the input to the seam map generation process following [5]. It produces better results as compared to [8] which uses the raw input image in the seam map generation procedure. The reason for this enhancement is the smoothness and stronger edges of the superpixelized image.…”

Section: Seam Importance Mapmentioning

confidence: 99%

“…CA [23], FT [24], HC [15], LC [25], MSS [16], GS [1], SF [10], SWD [26], BARC [3], BARCS [8], BACS[5] MSRA 10k GS [1], SF [10], BARC [3], BARCS [8], BACS [5] CSSD GS [1], SF [10], BARC [3], BARCS [8], BACS [5] ECSSD GR [27], IT [17], SR [28], MSS [16], GS [1], SF [10], BARC [3], BARCS [8], BACS [5]…”

Section: Msra 1kmentioning

confidence: 99%

“…There are usually two types of evaluation strategies for every computer vision technique -qualitative analysis and quantitative analysis. Results found in this study are compared with several state of the art methods which are labelled as HC [15], MSS [16], GB [18], SWD [26], RC [29], AC [30], IT [17], GR [27], LC [25], FT [24], CA [23], AIM [31], GS [1], SF [10], SR [28], BARC [3], BARCS [8] and BACS [5]. Most of these labels are used in previous researches like [21], [15] and [32].…”

Section: Evaluation Metricsmentioning

confidence: 99%

See 4 more Smart Citations

Visual Saliency Detection using Seam and Color Cues

Ahsan¹,

Islam²

2021

Adv. sci. technol. eng. syst. j.

Self Cite

View full text Add to dashboard Cite

Human have the god gifted ability to focus on the essential part of a visual scenery irrespective of its background. This important area is called the salient region of an image. Computationally achieving this natural human quality is an attractive goal of today's scientific world. Saliency detection is the technique of finding the salient region of a digital image. The color contrast between the foreground and background present in an image is usually used to extract this region. Seam Map is computed from the cumulative sum of energy values of an image. The proposed method uses seam importance map along with the weighted average of various color channels of Lab color space namely boundary aware color map to extract the saliency map. These two maps are combined and further optimized to get the final saliency output using the optimization technique proposed in a previous study. Some intermediate combinations which are closer to the proposed optimized version but differ in the optimization technique are also presented in this paper. Several standard benchmark datasets including the famous MSRA 10k dataset are used to evaluate performance of the suggested procedure. Precision-recall curve and F-beta values found from the experiments on those datasets and comparison with other state of the art techniques prove the superiority of the proposed method.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%