A hybrid approach using color spatial variance and novel object position prior for salient object detection
- PDF / 4,376,632 Bytes
- 23 Pages / 439.642 x 666.49 pts Page_size
- 27 Downloads / 212 Views
A hybrid approach using color spatial variance and novel object position prior for salient object detection Vivek Kumar Singh1 · Nitin Kumar1 · Navjot Singh2 Received: 6 May 2019 / Revised: 5 February 2020 / Accepted: 28 July 2020 / © Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Salient object detection in a real-time environment demands high accuracy with less computation time. It is a changeling task to investigate a saliency model which improves saliency detection accuracy as well as reduces computation time. In this paper, we propose a hybrid model that improves detection accuracy with low computational time. The input image is simplified and clustered at multiple scales using SLIC and K-means clustering algorithms respectively. Gaussian Mixture Model (GMM) is developed on various color components of the digital image at multiple scales. The parameters of GMM are learnt using Expectation Maximization (EM) algorithm. The spatial variance of each color component is determined using GMM parameters and hence object position is estimated. Further, spatial variance of color components and object position is exploited to compute saliency map at a scale level. Afterwards, all the saliency maps generated across various scales are linearly combined to produce the final saliency map. The performance of the proposed model is compared in terms of Precision, Recall, F-Measure, Area under the Curve (AUC), Receiver Operating Characteristics (ROC) and Mean Absolute Error (MAE). Extensive experiments on six publicly available datasets viz. MSRA10K, DUT-OMRON, ECSSD, PASCAL-S, SED2, and THUR15K show that the proposed model outperforms or comparable against 11 state-ofthe-art methods of the last decade. The key features of the proposed method are object completeness and efficiency in terms of computational time. Keywords Superpixel · K-means · Gaussian mixture model (GMM) · Color spatial variance · Saliency map Vivek Kumar Singh
[email protected] Nitin Kumar [email protected] Navjot Singh [email protected] 1
National Institute of Technology Uttarakhand, Uttarakhand, India
2
Motilal Nehru National Institute of Technology Allahabad, Uttar Pradesh, India
Multimedia Tools and Applications
1 Introduction Salient object detection (SOD) aims to identify and annotate more distinctive objects or regions which capture human’s attention in natural images. SOD is an active and important research area in computer vision community in the last two decades. The visual saliency has two research directions namely eye fixation [25] and Salient object detection [7]. The eye fixation keeps tracking the human eye moment while SOD detects and segments objects in an image. The focus of research on SOD is gaining more popularity as compared to eye fixation. SOD is a fundamental problem of isolating the salient object(s) from the background by exploiting contrast in their various features. Generally, SOD is employed as a pre-processing step to the visual input for various vision tasks such as obje
Data Loading...
