Results 131 to 140 of about 2,106 (179)
Some of the next articles are maybe not open access.
Content-Adaptive Superpixel Segmentation
IEEE Transactions on Image Processing, 2018Superpixel segmentation targets at grouping pixels in an image into atomic regions whose boundaries align well with the natural object boundaries. This paper first proposes a new feature representation for superpixel segmentation that holistically embraces color, contour, texture, and spatial features.
Xiaolin Xiao +2 more
exaly +3 more sources
Lazy Random Walks for Superpixel Segmentation
IEEE Transactions on Image Processing, 2014We present a novel image superpixel segmentation approach using the proposed lazy random walk (LRW) algorithm in this paper. Our method begins with initializing the seed positions and runs the LRW algorithm on the input image to obtain the probabilities of each pixel.
Xuelong Li +2 more
exaly +3 more sources
Vine Spread for Superpixel Segmentation
IEEE Transactions on Image Processing, 2023Superpixel is the over-segmentation region of an image, whose basic units "pixels" have similar properties. Although many popular seeds-based algorithms have been proposed to improve the segmentation quality of superpixels, they still suffer from the seeds initialization problem and the pixel assignment problem.
Pei Zhou, Xuejing Kang, Anlong Ming
openaire +2 more sources
Variational Fuzzy Superpixel Segmentation
IEEE Transactions on Fuzzy Systems, 2022This paper presents a novel variational model based on fuzzy clustering and total variation regularization for superpixel segmentation. Compared with the classical hard-labeled methodologies, our approach gives soft results via the fuzzy membership function, and moreover, the use of total variation provides additional information that can enhance the ...
Tsz-Ching Ng, Siu-Kai Choy
openaire +1 more source
Superpixel Convolution for Segmentation
2018 25th IEEE International Conference on Image Processing (ICIP), 2018In this paper, we propose a novel segmentation algorithm based on convolutional neural networks (CNNs) on superpix-else CNNs are powerful methods for several computer vision tasks, but spatial information disappears through the pooling process.
Teppei Suzuki +3 more
openaire +1 more source
Spherical superpixel segmentation
2016 IEEE International Conference on Multimedia and Expo (ICME), 2016In this paper, we present a superpixel generation method for spherical images, which cover 360° field-of-view. Unlike previous works that directly use existing superpixel algorithms on unrolled spherical images, our approach explicitly considers the geometry for spherical images and uses sphere as the underlying representation.
Qiang Zhao 0005, Liang Wan, Jiawan Zhang
openaire +1 more source
Weighted superpixel segmentation
The Visual Computer, 2019Image boundaries and regularity are two important factors in superpixel segmentation. Balancing the influence of image boundaries and regularity is key to producing superpixels. In this paper, we present a novel superpixel segmentation algorithm, called weighted superpixel segmentation (WSS), which is capable of generating superpixels with high ...
Xin Qian +2 more
openaire +1 more source
Superpixel segmentation: A benchmark
Signal Processing: Image Communication, 2017Abstract Various superpixel approaches have been published recently. These algorithms are assessed using different evaluation metrics and datasets resulting in discrepancy in algorithm comparison. This calls for a benchmark to compare the state-of-the-arts methods and evaluate their pros and cons.
Murong Wang +4 more
openaire +1 more source
Spherical Superpixel Segmentation
IEEE Transactions on Multimedia, 2018These days, superpixel algorithms are widely used in computer vision and multimedia applications. However, existing algorithms are designed for planar images, which are less suited to deal with wide angle images. In this paper, we present a superpixel segmentation method for $\text{360}^\circ$ spherical images.
Qiang Zhao 0005 +5 more
openaire +1 more source