AW k S: adaptive, weighted k -means-based superpixels for improved saliency detection
- PDF / 2,334,434 Bytes
- 15 Pages / 595.276 x 790.866 pts Page_size
- 18 Downloads / 176 Views
THEORETICAL ADVANCES
AWkS: adaptive, weighted k‑means‑based superpixels for improved saliency detection Ashish Kumar Gupta1 · Ayan Seal1,2 · Pritee Khanna1 · Ondrej Krejcar2,3 · Anis Yazidi4 Received: 29 June 2020 / Accepted: 26 October 2020 © Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Clustering inspired superpixel algorithms perform a restricted partitioning of an image, where each visually coherent region containing perceptually similar pixels serves as a primitive in subsequent processing stages. Simple linear iterative clustering (SLIC) has emerged as a standard superpixel generation tool due to its exceptional performance in terms of segmentation accuracy and speed. However, SLIC applies a manually adjusted distance measure for dis-similarity computation which directly affects the quality of superpixels. In this work, self-adjustable distance measures are adapted from the weighted k-means clustering (W-k-means) for generating superpixel segmentation. In the proposed distance measures, an adaptive weight associated with each variable reflects its relevance in the clustering process. Intuitively, the variable weights correspond to the normalization terms in SLIC that affect the trade-off between superpixels boundary adherence and compactness. Weights that influence consistency in superpixel generation are automatically updated. The variable weights update is accomplished during optimization with a closed-form solution based on the current image partition. The proposed adaptive, W-k-means-based superpixels (AWkS) experimented on three benchmarks under different distance measure outperform the conventional SLIC algorithm with respect to various boundary adherence metrics. Finally, the effectiveness of the AWkS over SLIC is demonstrated for saliency detection. Keywords Superpixels · Segmentation · W-k-means · Distance measure
* Ayan Seal [email protected] Ashish Kumar Gupta [email protected] Pritee Khanna [email protected] Ondrej Krejcar [email protected] Anis Yazidi [email protected] 1
Department of Computer Science and Engineering, PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur 482005, India
2
Center for Basic and Applied Research, Faculty of Informatics and Management, University of Hradec Kralove, Hradecka 1249, 50003 Hradec Kralove, Czech Republic
3
Malaysia Japan International Institute of Technology, Universiti Teknologi Malaysia, Jalan Sultan Yahya Petra, 54100 Kuala Lumpur, Malaysia
4
Artificial Intelligence Lab, Oslo Metropolitan University, 460167 Oslo, Norway
1 Introduction In recent years, superpixel segmentation has became an integral preprocessing tool in various image processing and computer vision applications such as object detection [1, 2], recognition [3], semantic segmentation [4], image classification [5], object proposal detection [6, 7], visual tracking [8, 9], indoor seen understanding [10], and salient object detection [11–16]. Superpixel segmentation of an image partitions it
Data Loading...
