Filters








77,376 Hits in 4.4 sec

Interactive Image Segmentation Using Constrained Dominant Sets [article]

Eyasu Zemene, Marcello Pelillo
2016 arXiv   pre-print
We propose a new approach to interactive image segmentation based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster  ...  clusters which are constrained to contain user-selected elements.  ...  Conclusions In this paper, we have developed an interactive image segmentation algorithm based on the idea of finding a collection of dominant-set clusters constrained to contain the elements of a user  ... 
arXiv:1608.00641v2 fatcat:qtdoaozpwbba3meto7hr5soiaq

Interactive Image Segmentation Using Constrained Dominant Sets [chapter]

Eyasu Zemene, Marcello Pelillo
2016 Lecture Notes in Computer Science  
We propose a new approach to interactive image segmentation based on some properties of a family of quadratic optimization problems related to dominant sets, a well-known graph-theoretic notion of a cluster  ...  clusters which are constrained to contain user-selected elements.  ...  Conclusions In this paper, we have developed an interactive image segmentation algorithm based on the idea of finding a collection of dominant-set clusters constrained to contain the elements of a user  ... 
doi:10.1007/978-3-319-46484-8_17 fatcat:pye3hglzqzd43bbjgbgljxmxay

Constrained Dominant sets and Its applications in computer vision [article]

Alemu Leulseged Tesfaye
2020 arXiv   pre-print
In this thesis, we present new schemes which leverage a constrained clustering method to solve several computer vision tasks ranging from image retrieval, image segmentation and co-segmentation, to person  ...  Sets.  ...  Multi-features Fusion Using Constrained Dominant Sets for Image Retrieval .1. Multi-features Fusion Using Constrained Dominant Sets for Image Retrieval  ... 
arXiv:2002.06028v1 fatcat:rxf5idn2fjcvzj24iu4kggbaoq

Weakly Supervised Semantic Segmentation Using Constrained Dominant Sets [chapter]

Sinem Aslan, Marcello Pelillo
2019 Lecture Notes in Computer Science  
In this work, we explore the potential of Constrained Dominant Sets (CDS) for generating multi-labeled full mask predictions to train a fully convolutional network (FCN) for semantic segmentation.  ...  The availability of large-scale data sets is an essential pre-requisite for deep learning based semantic segmentation schemes.  ...  Constrained Dominant Sets Dominant Set Framework.  ... 
doi:10.1007/978-3-030-30645-8_39 fatcat:zbdzkwa6yfavjhxefpomhexs3a

Dominant Sets for "Constrained" Image Segmentation

Eyasu Zemene Mequanint, Leulseged Tesfaye Alemu, Marcello Pelillo
2018 IEEE Transactions on Pattern Analysis and Machine Intelligence  
., some form of user assistance (interactive segmentation) or ask for the simultaneous segmentation of two or more images (co-segmentation).  ...  In particular, we shall focus on interactive segmentation and co-segmentation (in both the unsupervised and the interactive versions).  ...  Given the affinity matrix, we used replicator dynamics (12) to exctract constrained dominant sets.  ... 
doi:10.1109/tpami.2018.2858243 pmid:30040623 fatcat:wlo5jf7mzfh3jlww7mbzpblgpq

AN INTERACTIVE IMAGE SEGMENTATION USING MULTIPLE USER INPUTªS

Swathika P .
2013 International Journal of Research in Engineering and Technology  
Interactive image segmentation involves a proposed algorithm, Constrained Random walks algorithm. The Constrained Random Walks algorithm facilitates the use of three types of user inputs. 1.  ...  In this paper, we consider the Interactive image segmentation with multiple user inputs. The proposed system is the use of multiple intuitive user inputs to better reflect the user's intention.  ...  The extension is known as constrained random walks algorithm to facilitate the use of various user inputs in interactive image segmentation.  ... 
doi:10.15623/ijret.2013.0203016 fatcat:ivzut2damvcarpfpph5u5v35fq

Robust interactive image segmentation via iterative refinement

Yao Peng, Juyong Zhang, Yancheng Yuan, Shuyuan Zhu, Lu Fang
2014 2014 IEEE International Conference on Image Processing (ICIP)  
However, existing interactive image segmentation methods still might fail if the image contains messy textures, or the user inputs are sparse or at inappropriate locations.  ...  Extensive experiments using real world images, and segmentation benchmark dataset show that our proposed method has superior performance compared with representative state-of-the-art methods.  ...  [11] extended it to interactive image segmentation, which is named constrained active contour model.  ... 
doi:10.1109/icip.2014.7025889 dblp:conf/icip/PengZYZF14 fatcat:swqyxu5awvfv5iurbaaadtcs24

Automatic corpus callosum segmentation using a deformable active Fourier contour model

Clement Vachet, Benjamin Yvernault, Kshamta Bhatt, Rachel G. Smith, Guido Gerig, Heather Cody Hazlett, Martin Styner
2012 Medical Imaging 2012: Biomedical Applications in Molecular, Structural, and Functional Imaging  
A multi-step optimization strategy, with two constrained steps and a final unconstrained step, is then applied. If needed, interactive segmentation can be performed via contour repulsion points.  ...  Using MNI space aligned T1w MRI data, the CC segmentation is initialized on the mid-sagittal plane using the tissue segmentation.  ...  Interactive use of repulsion points The automatic segmentation may not be fully accurate in certain areas of the corpus callosum, due to variations in shape but also other issues related to MRI brain images  ... 
doi:10.1117/12.911504 pmid:24353382 pmcid:PMC3864934 fatcat:nn7j4urolrfwzmu63h34otd44i

Building and Assessing a Constrained Clustering Hierarchical Algorithm [chapter]

Eduardo R. Concepción Morales, Yosu Yurramendi Mendizabal
2008 Lecture Notes in Computer Science  
., spatial interactions. A constrained hierarchical agglomerative algorithm with an aggregation index is introduced which uses neighbouring relations present in the data.  ...  Unsupervised classification or clustering has been used in many disciplines and contexts.  ...  This information could be obtained, e.g., applying an edge detector to the image.  ... 
doi:10.1007/978-3-540-85920-8_26 fatcat:eydu25ct25aybphwg7xwdhj34y

Robust Interactive Image Segmentation Using Convex Active Contours

Thi Nhat Anh Nguyen, Jianfei Cai, Juyong Zhang, Jianmin Zheng
2012 IEEE Transactions on Image Processing  
Experimental results on a benchmark data set show that the proposed tool is highly effective and outperforms the state-of-the-art interactive image segmentation algorithms.  ...  Index Terms-Interactive image segmentation, convex active contour, digital image editing.  ...  The above observations motivate us to design a new method for interactive image segmentation.  ... 
doi:10.1109/tip.2012.2191566 pmid:22453637 fatcat:6mw2n7hukrd3hcpmkt46a3uz24

3D Kidney Segmentation from CT Images Using a Level Set Approach Guided by a Novel Stochastic Speed Function [chapter]

Fahmi Khalifa, Ahmed Elnakib, Garth M. Beache, Georgy Gimel'farb, Mohamed Abo El-Ghar, Rosemary Ouseph, Guela Sokhadze, Samantha Manning, Patrick McClure, Ayman El-Baz
2011 Lecture Notes in Computer Science  
The segmentation approach was evaluated on 21 CT data sets with available manual expert segmentation.  ...  This paper describes a new 3-D segmentation approach for the kidney from computed tomography (CT) images.  ...  Approximate the empirical gray level distribution by using the LCDG with two dominant Gaussian modes. 3. Form an initial region map m using the estimated LCDG models. 4.  ... 
doi:10.1007/978-3-642-23626-6_72 fatcat:pmlapskxy5cazehrjegobpnaam

IRIS—Intelligent Rapid Interactive Segmentation for Measuring Liver Cyst Volumes in Autosomal Dominant Polycystic Kidney Disease

Collin Li, Dominick Romano, Sophie J. Wang, Hang Zhang, Martin R. Prince, Yi Wang
2022 Tomography  
Methods: SmartClick and antiSmartClick were developed using iterative region growth guided by spatial and intensity connections and were integrated with automated level set (LS) segmentation and graphical  ...  Purpose: To develop and integrate interactive features with automatic methods for accurate liver cyst segmentation in patients with autosomal dominant polycystic kidney and liver disease (ADPKD).  ...  Conclusions In summary, intelligent rapid interactive segmentation (IRIS) is feasible for fast and accurate liver cyst segmentation in autosomal dominant polycystic kidney disease (ADPKD), using SmartClick  ... 
doi:10.3390/tomography8010037 pmid:35202202 pmcid:PMC8877996 fatcat:5bwm6q4dajahjn3q6p5m7nphwu

Moment Constraints in Convex Optimization for Segmentation and Tracking [chapter]

Maria Klodt, Frank Steinbrücker, Daniel Cremers
2013 Advanced Topics in Computer Vision  
GPU-based computation times of around 1 second allow for interactive segmentation.  ...  Quantitative segmentation studies on a variety of images demonstrate that the user can impose such constraints with a few mouse clicks, leading to substantial improvements of the resulting segmentation  ...  Efficient GPU-accelerated PDE solvers allow for computation times of about one second for images of size 300 × 400, making this a practical tool for interactive image segmentation. 1 . 1 Set u := u 0 ,  ... 
doi:10.1007/978-1-4471-5520-1_8 dblp:series/acvpr/KlodtSC13 fatcat:hoeng5wc65h6fpn6tfbqbwxrmq

Automatic video segmentation using spatiotemporal T-junctions

N. Apostoloff, A. W. Fitzgibbon
2006 Procedings of the British Machine Vision Conference 2006  
Classical video segmentation algorithms approach the problem from one of two perspectives. At one extreme, global approaches constrain the camera motion to simplify the image structure.  ...  Graph cut is then used to segment each frame of the video showing that sparse occlusion edge information can automatically initialize the video segmentation problem.  ...  Interactive video cutout by Wang and Cohen extends a frame-wise 2D colour over-segmentation over time using graph cut and user interaction through a novel volumetric painting interface [34] .  ... 
doi:10.5244/c.20.111 dblp:conf/bmvc/ApostoloffF06 fatcat:fayefoebejaf7fle2ziooeb7h4

Deep Constrained Dominant Sets for Person Re-identification [article]

Leulseged Tesfaye Alemu, Marcello Pelillo, Mubarak Shah
2019 arXiv   pre-print
To overcome this, we propose an intriguing scheme which treats person-image retrieval problem as a constrained clustering optimization problem, called deep constrained dominant sets (DCDS).  ...  By optimizing the constrained clustering in an end-to-end manner, we naturally leverage the contextual knowledge of a set of images corresponding to the given person-images.  ...  [40] presented CDS with its applications to interactive Image segmentation. Following, [39] uses CDS to tackle both image segmentation and co-segmentation in interactive and unsupervised setup.  ... 
arXiv:1904.11397v2 fatcat:ztvu33hvezgqzo2o63lnjrkjfq
« Previous Showing results 1 — 15 out of 77,376 results