Results 91 to 100 of about 384,232 (160)

Rethinking Unsupervised Neural Superpixel Segmentation

, 2022
Recently, the concept of unsupervised learning for superpixel segmentation via CNNs has been studied. Essentially, such methods generate superpixels by convolutional neural network (CNN) employed on a single image, and such CNNs are trained without any ...
Zikri, Nir Ben, Treister, Eran, Eliasof, Moshe   +2 more
core  

Superpixel-based Hyperspectral Unmixing with Regional Segmentation [PDF]

, 2018
Unsupervised unmixing analysis aims to extract the basic materials, also known as, endmembers, and their fractions (or abundances) from a hyperspectral image. In this work, a new unsupervised unmixing approach based on Low Dimensional representation with
Alkhatib, Mohammed Qassim
core   +1 more source

Image Anonymization by Superpixel Segmentation

We propose a method for anonymizing a given image by removing personally identifiable information with a superpixel segmentation technique. Especially, we would like to focus on human faces in an image, because face images bear important personal ...
張, 碩延, 井上, 光平, イノウエ, コウヘイ, 原, 健二, Urahama, Kiichi, Zhang, Shuoyan, Hara, Kenji, ハラ, ケンジ, 浦濱, 喜一, Inoue, Kohei, ウラハマ, キイチ   +10 more
core  

USNet: underwater image superpixel segmentation via multi-scale water-net

Frontiers in Marine Science
Underwater images commonly suffer from a variety of quality degradations, such as color casts, low contrast, blurring details, and limited visibility.
Chuhong Wang, Chuhong Wang, Wenli Duan, Chengche Luan, Junyan Liang, Lengyu Shen, Hua Li   +6 more
doaj   +1 more source

Rapid Recognition of Field-Grown Wheat Spikes Based on a Superpixel Segmentation Algorithm Using Digital Images. [PDF]

Front Plant Sci, 2020
Tan C, Zhang P, Zhang Y, Zhou X, Wang Z, Du Y, Mao W, Li W, Wang D, Guo W.   +9 more
europepmc   +1 more source

Learning contextual superpixel similarity for consistent image segmentation

, 2019
International audienceThis paper addresses the problem of image segmentation by iterative region aggregations starting from an initial superpixel decomposition.
Chaibou Salaou, Mahaman Sani, Mahjoub, Mohamed Ali, Solaiman, Basel, Kalti, Karim, Conze, Pierre-Henri   +4 more
core   +1 more source

Superpixel Sizes using Topology Preserved Regular Superpixel Algorithm and their Impacts on Interactive Segmentation

, 2022
Interactive Image Segmentation is a type of semiautomated segmentation that uses user input to extract the object of interest. It is possible to speed up and improve the end result of segmentation by using pre-processing steps. The use of superpixels is
Muzaffar, Hamzah, Kok Luong, Goh, Giap Weng, Ng, Soo See, Chai   +3 more
core  

Research on Fine Water Body Extraction From SAR Images Based on Superpixel Segmentation

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
The water body extraction technology based on superpixel segmentation in SAR images faces challenges such as insufficient precision in extracting fine water boundaries under speckle noise and complex scattering conditions.
Fengcheng Guo, Xiaoxiao Ma, Ning Sun, Lianpeng Zhang, Wensong Liu   +4 more
doaj   +1 more source

SymmSLIC: Symmetry Aware Superpixel Segmentation

, 2017
Over-segmentation of an image into superpixels has become an useful tool for solving various problems in computer vision. Reflection symmetry is quite prevalent in both natural and man-made objects.
Shanmuganathan Raman, Nagar, Rajendra, Raman, Shanmuganathan, Rajendra Nagar   +3 more
core   +1 more source

Spherical Superpixel Segmentation with Context Identity and Contour Intensity

Superpixel segmentation is a popular preprocessing tool in the field of image processing. Nevertheless, conventional planar superpixel generation algorithms are inadequately suited for segmenting symmetrical spherical images due to the distinctive ...
Baolong Guo, Fangliang He, Nannan Liao, Cheng Li, Hui Liu, Wenxing Li   +5 more
core   +1 more source