Filters








440 Hits in 5.7 sec

A New Approach of Dynamic Clustering Based on Particle Swarm Optimization and Application in Image Segmentation

Dang Cong Tran, Zhijian Wu
2017 Computing and informatics  
The improved PSO is then combined with the well-known data clustering k-means algorithm for dynamic clustering problem where the number of clusters has not yet been known.  ...  This paper presents a new approach of dynamic clustering based on improved Particle Swarm Optimization (PSO) and which is applied to image segmentation (called DCPSONS).  ...  There are many methods for image segmentation in the literature [28, 29] , of which one of the popular method is to use a clustering algorithm (such as k-means).  ... 
doi:10.4149/cai_2017_3_637 fatcat:5e7hov3lrfeqjfecyjeelbului

IDENTIFICATION OF PATCHOULI PLANTS USING LANDSAT-8 SATELLITE IMAGERY AND IMPROVED K-MEANS METHOD

Candra Dewi
2016 Journal of Enviromental Engineering and Sustainable Technology  
The test results also show that the use of the Improved K-Means on the Landsat-8 image has not been able to recognize the difference patchouli plants with other crops due to the limited resolution of imagery  ...  This study performed the identification of patchouli plant through Landsat-8 satellite imagery and Improved K-Means method.  ...  This study combine the KK-means clustering segmentation algorithm and mathematical morphology. The results show that the algorithm can separate between the fish image and the complex backgrounds.  ... 
doi:10.21776/ub.jeest.2016.003.02.1 fatcat:3eogqdguvrb5hpk35z74zopp7y

A Feature Learning and Object Recognition Framework for Underwater Fish Images [article]

Meng-Che Chuang, Jenq-Neng Hwang, Kresimir Williams
2016 arXiv   pre-print
For the classifier, an unsupervised clustering approach generates a binary class hierarchy, where each node is a classifier.  ...  Toward this end, we propose an underwater fish recognition framework that consists of a fully unsupervised feature learning technique and an error-resilient classifier.  ...  Object segmentation mask for each fish image is provided along with the dataset.  ... 
arXiv:1603.01696v1 fatcat:6tzaud6bjbbqldsxkgeq234mm4

Improved Artificial Bee Colony Using Sine-Cosine Algorithm for Multi-level Thresholding Image Segmentation

Ahmed A. Ewees, Mohamed Abd Elaziz, Mohammed A. A. Al-qaness, Hassan A. Khalil, Sunghwan Kim
2020 IEEE Access  
Multilevel-thresholding is an efficient method used in image segmentation.  ...  This paper presents a hybrid meta-heuristic approach for multi-level thresholding image segmentation by integrating both the artificial bee colony (ABC) algorithm and the sine-cosine algorithm (SCA).  ...  The FA was proposed in [35] for MTS to improve the performance of the K-means algorithm. The results showed high performance and good segmentation result for the proposed method.  ... 
doi:10.1109/access.2020.2971249 fatcat:psy7dvisdrebxmzwjwo536adqe

Integration of evolutionary computation algorithms and new AUTO-TLBO technique in the speaker clustering stage for speaker diarization of broadcast news

Karim Dabbabi, Salah Hajji, Adnen Cherif
2017 EURASIP Journal on Audio, Speech, and Music Processing  
grouping of speakers' segments.  ...  Clustering validity indexes, such as Within-Class Distance (WCD) index, Davies and Bouldin (DB) index, and Contemporary Document (CD) index, is also used in order to make a correction for each possible  ...  Indeed, obtaining GMM for a segment is done by mean adapting the UBM for the feature vectors of the concerned segment.  ... 
doi:10.1186/s13636-017-0117-1 fatcat:htbtt6oqnrdi5g5xliioqkl66i

Super-resolution Imaging Reveals 3D Structure and Organizing Mechanism of Accessible Chromatin [article]

Liangqi Xie, Peng Dong, Yifeng Qi, Margherita De Marzio, Xingqi Chen, Sambashiva Banala, Wesley R Legant, Brian P English, Anders Hansen, Anton Schulmann, Luke D Lavis, Eric Betzig (+5 others)
2019 bioRxiv   pre-print
Access to cis-regulatory elements packaged in chromatin is essential for directing gene expression and cell viability.  ...  We found that active chromosomal segments are organized into spatially-segregated accessible chromatin domains (ACDs).  ...  We also thank Deepika Walpita and Kathy Schaefer with assistance for FACS experiments, Damien Alcor for Airyscan Imaging and Melanie Radcliff for assistance.  ... 
doi:10.1101/678649 fatcat:isascfdol5cbbmq46bnyvm7hii

Figure-ground organization based on three-dimensional symmetry

Aaron Michaux, Vijai Jayadevan, Edward Delp, Zygmunt Pizlo
2016 Journal of Electronic Imaging (JEI)  
We tested our approach on a corpus of 180 images collected indoors with a stereo camera system. K -means clustering was used as a baseline for comparison.  ...  No general purpose approach is known for solving 3-D symmetry correspondence in two-dimensional (2-D) camera images, because few invariants exist.  ...  We would like to thank the reviewers for their helpful feedback, and Vikrant Satheesh for annotating the testing corpus.  ... 
doi:10.1117/1.jei.25.6.061606 fatcat:zsgk2t6fjjcbdlyo6giy6xcmim

Joint-Space Kinematic Control of a Bionic Continuum Manipulator in Real-time by using Hybrid Approach

Mrunal Kanti Mishra, Arun Kumar Samantaray, Goutam Chakraborty
2022 IEEE Access  
This research is partly funded by Indo French Centre for the Promotion of Advanced Research (IFCPAR), under DST (India) and CNRS (France) Collaboration for the project "Modelling and control of mobile  ...  The work in [33] is extended in [34] to formulate an adaptive NN model for improved trajectory tracking.  ...  P and 𝐊𝐊 I are tuned by minimising the total mean square error (MSE) of the system.  ... 
doi:10.1109/access.2022.3171236 fatcat:2osulv3edfhczl6osdmhvcoooe

Learning invariant structure for object identification by using graph methods

Bai Xiao, Song Yi-Zhe, Peter Hall
2011 Computer Vision and Image Understanding  
Practically, we depend on spectral graph analysis of a hierarchical description of an image to construct a feature vector of fixed dimension.  ...  Acknowledgements This work was supported by EPSRC Grant EP/D05429X/1, Fundamental Research Funds for the Cental Universities and Open Projects of National Laboratory of Pattern Recognition.  ...  The difference this conditioning matrix makes can be witnessed in Fig. 2 , where improved segmentations clearly result.  ... 
doi:10.1016/j.cviu.2010.12.016 fatcat:qhdoq4xrkrhllon3hd6ep2ttju

Light microscopy applications in systems biology: opportunities and challenges

Paul Michel Aloyse Antony, Christophe Trefois, Aleksandar Stojanovic, Aidos Sagatovich Baumuratov, Karol Kozak
2013 Cell Communication and Signaling  
Ilastik is an open-source tool based on user defined examples that train a machine-learning algorithm for identifying pixels of an image that belong to a class of interest [93, 136] .  ...  However, in contrast to classical tracking and cell lineage identification algorithms, improved algorithms that consider the entire image sequence, and prior knowledge (e.g., about mitosis and apoptosis  ...  CT prepared the tables of the manuscript, AS focused on the machine learning part, AB on microscopes, and KK helped to improve the review of workflow systems and databases.  ... 
doi:10.1186/1478-811x-11-24 pmid:23578051 pmcid:PMC3627909 fatcat:xfq3tvkb2reg7heojzoj2omb4e

A skeletal measure of 2D shape similarity

Andrea Torsello, Edwin R. Hancock
2004 Computer Vision and Image Understanding  
We illustrate how the new shapemeasure can be used for the purposes of clustering shock-trees of the same shape class.  ...  Details of the clustering algorithm are outside the scope of this paper. However, the method uses an iterative log-likelihood algorithm to identify the pairwise clusters via matrix factorization.  ...  This means that very short boundary segments generate very long skeleton branches.  ... 
doi:10.1016/j.cviu.2004.03.006 fatcat:pakmyur5jfcanpxlssz3hg6rgm

A skeletal measure of 2D shape similarity

A TORSELLO
2004 Computer Vision and Image Understanding  
We illustrate how the new shapemeasure can be used for the purposes of clustering shock-trees of the same shape class.  ...  Details of the clustering algorithm are outside the scope of this paper. However, the method uses an iterative log-likelihood algorithm to identify the pairwise clusters via matrix factorization.  ...  This means that very short boundary segments generate very long skeleton branches.  ... 
doi:10.1016/s1077-3142(04)00037-2 fatcat:oci2xhnqdncedopzctc7aqggnm

Analysis and synthesis of 3D shape families via deep-learned generative models of surfaces

Haibin Huang, Evangelos Kalogerakis, Benjamin Marlin
2015 Computer graphics forum (Print)  
We provide qualitative and quantitative evaluations of our method for shape correspondence, segmentation, fine-grained classification and synthesis.  ...  Finally, it can be also coupled with the probabilistic deformation model to further improve shape correspondence.  ...  We thank Qi-xing Huang and Vladimir Kim for sharing data from their methods. We thank Siddhartha Chaudhuri and anonymous reviewers for valuable comments.  ... 
doi:10.1111/cgf.12694 fatcat:6hmtn4da6zc4rf2mnemye3v4ie

A Skeletal Measure of 2D Shape Similarity [chapter]

Andrea Torsello, Edwin R. Hancock
2001 Lecture Notes in Computer Science  
We illustrate how the new shapemeasure can be used for the purposes of clustering shock-trees of the same shape class.  ...  Details of the clustering algorithm are outside the scope of this paper. However, the method uses an iterative log-likelihood algorithm to identify the pairwise clusters via matrix factorization.  ...  This means that very short boundary segments generate very long skeleton branches.  ... 
doi:10.1007/3-540-45129-3_23 fatcat:txclelvglbakzprklezdb3nlbu

D3.6: 2nd Design Guidelines for Open Sensor fabrication

Ilias Stavrakas, George Hloupis, Demosthenes Triantis, Konstantinos Moutzouris, Hai-Ying Liu, Arne Fellermann
2018 Zenodo  
The current report is the second version of the design guidelines for the hackAIR open sensor fabrication that describes the implementation details of three open hardware solutions along with an initial  ...  version of user guidelines for the construction of each one.  ...  [30] 5.5.6 Clustering (The Otsu Method) In image processing, segmentation is often the first step to pre-process images to extract objects of interest for further analysis.  ... 
doi:10.5281/zenodo.2252161 fatcat:ypobqwoa3jf7jd4z7rn4hrba7m
« Previous Showing results 1 — 15 out of 440 results