Salient Object Detection Based on Multiscale Segmentation and Fuzzy Broad Learning

Abstract

Saliency detection has been a hot topic in the field of computer vision. In this paper, we propose a novel approach that is based on multiscale segmentation and fuzzy broad learning. The core idea of our method is to segment the image into different scales, and then the extracted features are fed to the fuzzy broad learning system (FBLS) for training. More specifically, it first segments the image into superpixel blocks at different scales based on the simple linear iterative clustering algorithm. Then, it uses the local binary pattern algorithm to extract texture features and computes the average color information for each superpixel of these segmentation images. These extracted features are then fed to the FBLS to obtain multiscale saliency maps. After that, it fuses these saliency maps into an initial saliency map and uses the label propagation algorithm to further optimize it, obtaining the final saliency map. We have conducted experiments based on several benchmark datasets. The results show that our solution can outperform several existing algorithms. Particularly, our method is significantly faster than most of deep learning-based saliency detection algorithms, in terms of training and inferring time.

A Salient Object Detection Method Based on Boundary Enhancement

“…Certain techniques, such as multi-level feature aggregation and multi-scale information extraction [ 11 , 12 , 13 ], have been explored in prior research on SOD. While the proposed method shares common modules with these earlier publications, the main contributions of our method lie in the innovative combination and adaptation of these techniques to address specific challenges in SOD.…”

“…The structure of EdgeInfo is shown in the lower right corner of Figure 5, which includes four convolutional layers and has the function of further fusing features and changing the number of channels. The calculation process of multi-level boundary feature fusion is shown in Equation (12). EF = EdgeIn f o(Concat(U p(eh 1 ), U p(eh 2 ), U p(eh 3 ), U p(eh 4 ))) (12) where EdgeIn f o(•) represents the boundary feature aggregation module and EF represents the salient boundary features that aggregate multi-level information and can be used to fuse with the salient object features in the next step.…”

“…The calculation process of multi-level boundary feature fusion is shown in Equation (12). EF = EdgeIn f o(Concat(U p(eh 1 ), U p(eh 2 ), U p(eh 3 ), U p(eh 4 ))) (12) where EdgeIn f o(•) represents the boundary feature aggregation module and EF represents the salient boundary features that aggregate multi-level information and can be used to fuse with the salient object features in the next step.…”

A Moiré Removal Method Based on Peak Filtering and Image Enhancement

“…The presence of moiré patterns severely degrades the visual quality of captured images and affects the effectiveness of subsequent image processing tasks, such as image super-resolution [4,5], image segmentation [6][7][8][9], and face recognition [10][11][12]. In addition, traditional image restoration algorithms, such as image denoising [13,14], mesh removal [15,16], and deblurring [17,18], cannot be effectively and directly applied to the moiré pattern removal task.…”