IMT Institutional Repository: No conditions. Results ordered -Date Deposited. 2024-03-29T04:42:34ZEPrintshttp://eprints.imtlucca.it/images/logowhite.pnghttp://eprints.imtlucca.it/2016-02-26T13:11:06Z2016-02-26T13:11:06Zhttp://eprints.imtlucca.it/id/eprint/3126This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/31262016-02-26T13:11:06ZA SOM-based Chan–Vese model for unsupervised image segmentationActive Contour Models (ACMs) constitute an efficient energy-based image segmentation framework. They usually deal with the segmentation problem as an optimization problem, formulated in terms of a suitable functional, constructed in such a way that its minimum is achieved in correspondence with a contour that is a close approximation of the actual object boundary. However, for existing ACMs, handling images that contain objects characterized by many different intensities still represents a challenge. In this paper, we propose a novel ACM that combines—in a global and unsupervised way—the advantages of the Self-Organizing Map (SOM) within the level set framework of a state-of-the-art unsupervised global ACM, the Chan–Vese (C–V) model. We term our proposed model SOM-based Chan–Vese (SOMCV) active contour model. It works by explicitly integrating the global information coming from the weights (prototypes) of the neurons in a trained SOM to help choosing whether to shrink or expand the current contour during the optimization process, which is performed in an iterative way. The proposed model can handle images that contain objects characterized by complex intensity distributions, and is at the same time robust to the additive noise. Experimental results show the high accuracy of the segmentation results obtained by the SOMCV model on several synthetic and real images, when compared to the Chan–Vese model and other image segmentation models.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.itMohamed Medhat Gaber2016-02-26T12:55:26Z2016-02-26T12:55:26Zhttp://eprints.imtlucca.it/id/eprint/3125This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/31252016-02-26T12:55:26ZOn the Relationship between Variational Level Set-Based and SOM-Based Active ContoursMost Active Contour Models (ACMs) deal with the image segmentation problem as a functional optimization problem, as they work on dividing an image into several regions by optimizing a suitable functional. Among ACMs, variational level set methods have been used to build an active contour with the aim of modeling arbitrarily complex shapes. Moreover, they can handle also topological changes of the contours. Self-Organizing Maps (SOMs) have attracted the attention of many computer vision scientists, particularly in modeling an active contour based on the idea of utilizing the prototypes (weights) of a SOM to control the evolution of the contour. SOM-based models have been proposed in general with the aim of exploiting the specific ability of SOMs to learn the edge-map information via their topology preservation property and overcoming some drawbacks of other ACMs, such as trapping into local minima of the image energy functional to be minimized in such models. In this survey, we illustrate the main concepts of variational level set-based ACMs, SOM-based ACMs, and their relationship and review in a comprehensive fashion the development of their state-of-the-art models from a machine learning perspective, with a focus on their strengths and weaknesses.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.itMohamed Medhat GaberEyad Elyan2015-12-15T11:27:37Z2016-03-18T10:39:28Zhttp://eprints.imtlucca.it/id/eprint/2972This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/29722015-12-15T11:27:37ZA Concurrent SOM-Based Chan-Vese Model for Image SegmentationConcurrent Self Organizing Maps (CSOMs) deal with the pattern classification problem in a parallel processing way, aiming to minimize a suitable objective function. Similarly, Active Contour Models (ACMs) (e.g., the Chan-Vese (CV) model) deal with the image segmentation problem as an optimization problem by minimizing a suitable energy functional. The effectiveness of ACMs is a real challenge in many computer vision applications. In this paper, we propose a novel regional ACM, which relies on a CSOM to approximate the foreground and background image intensity distributions in a supervised way, and to drive the active-contour evolution accordingly. We term our model Concurrent Self Organizing Map-based Chan-Vese (CSOM-CV) model. Its main idea is to concurrently integrate the global information extracted by a CSOM from a few supervised pixels into the level-set framework of the CV model to build an effective ACM. Experimental results show the effectiveness of CSOM-CV in segmenting synthetic and real images, when compared with the stand-alone CV and CSOM models.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.itMohamed Medhat Gaber2015-02-23T11:11:28Z2015-02-23T11:11:28Zhttp://eprints.imtlucca.it/id/eprint/2621This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/26212015-02-23T11:11:28ZRobust local–global SOM-based ACMA novel active contour model (ACM) for image segmentation, driven by both local and global image-intensity information encoded by a self-organising map (SOM), is proposed. Experimental results demonstrate the robustness of the proposed model to the contour initialisation and to the additive noise, when compared with the state-of-the-art local and global ACMs. They also demonstrate its robustness to scene changes.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.it2015-02-23T11:04:02Z2015-02-23T11:04:02Zhttp://eprints.imtlucca.it/id/eprint/2620This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/26202015-02-23T11:04:02ZAn efficient Self-Organizing Active Contour model for image segmentation Active Contour Models (ACMs) constitute a powerful energy-based minimization framework for image segmentation, based on the evolution of an active contour. Among ACMs, supervised {ACMs} are able to exploit the information extracted from supervised examples to guide the contour evolution. However, their applicability is limited by the accuracy of the probability models they use. As a consequence, effectiveness and efficiency of supervised {ACMs} are among their main real challenges, especially when handling images containing regions characterized by intensity inhomogeneity. In this paper, to deal with such kinds of images, we propose a new supervised ACM, named Self-Organizing Active Contour (SOAC) model, which combines a variational level set method (a specific kind of ACM) with the weights of the neurons of two Self-Organizing Maps (SOMs). Its main contribution is the development of a new {ACM} energy functional optimized in such a way that the topological structure of the underlying image intensity distribution is preserved – using the two {SOMs} – in a parallel-processing and local way. The model has a supervised component since training pixels associated with different regions are assigned to different SOMs. Experimental results show the superior efficiency and effectiveness of {SOAC} versus several existing ACMs. Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.itMohamed Medhat Gaber2015-02-18T14:33:29Z2015-02-18T14:33:29Zhttp://eprints.imtlucca.it/id/eprint/2610This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/26102015-02-18T14:33:29ZA Survey of SOM-Based Active Contour Models for Image SegmentationSelf Organizing Maps (SOMs) have attracted the attention of many computer vision scientists, particularly when dealing with image segmentation as a contour extraction problem. The idea of utilizing the prototypes (weights) of a SOM to model an evolving contour has produced a new class of Active Contour Models (ACMs), known as SOM-based ACMs. Such models have been proposed in general with the aim of exploiting the specific ability of SOMs to learn the edge-map information via their topology preservation property, and overcoming some drawbacks of other ACMs, such as trapping into local minima of the image energy functional to be minimized in such models. In this survey paper, the main principles of SOMs and their application in modelling active contours are first highlighted. Then, we review existing SOM-based ACMs with a focus on their advantages and disadvantages in modelling the evolving contour via different kinds of SOMs. Finally, some current research directions are identified.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itGiorgio Gneccogiorgio.gnecco@imtlucca.itMohamed Medhat Gaber2013-11-20T10:52:50Z2013-11-20T10:52:50Zhttp://eprints.imtlucca.it/id/eprint/1915This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/19152013-11-20T10:52:50ZActive contour model driven by Globally Signed Region Pressure ForceOne of the most popular and widely used global active contour models (ACM) is the region-based ACM, which relies on the assumption of homogeneous intensity in the regions of interest. As a result, most often than not, when images violate this assumption the performance of this method is limited. Thus, handling images that contain foreground objects characterized by multiple intensity classes present a challenge. In this paper, we propose a novel active contour model based on a new Signed Pressure Force (SPF) function which we term Globally Signed Region Pressure Force (GSRPF). It is designed to incorporate, in a global fashion, the skewness of the intensity distribution of the region of interest (ROI). It can accurately modulate the signs of the pressure force inside and outside the contour, it can handle images with multiple intensity classes in the foreground, it is robust to additive noise, and offers high efficiency and rapid convergence. The proposed GSRPF is robust to contour initialization and has the ability to stop the curve evolution close to even ill-defined (weak) edges. Our model provides a parameter-free environment to allow minimum user intervention, and offers both local and global segmentation properties. Experimental results on several synthetic and real images demonstrate the high accuracy of the segmentation results in comparison to other methods adopted from the literature.Mohammed Abdelsameamohammed.abdelsamea@imtlucca.itSotirios A. Tsaftarissotirios.tsaftaris@imtlucca.it2013-03-06T08:41:56Z2013-03-12T09:32:21Zhttp://eprints.imtlucca.it/id/eprint/1511This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/15112013-03-06T08:41:56ZActive Contour Model driven by Globally Signed Region Pressure ForceMohammed Abdelsameamohammed.abdelsamea@imtlucca.itSotirios A. Tsaftarissotirios.tsaftaris@imtlucca.it2013-03-05T13:49:40Z2014-08-08T10:37:54Zhttp://eprints.imtlucca.it/id/eprint/1505This item is in the repository with the URL: http://eprints.imtlucca.it/id/eprint/15052013-03-05T13:49:40ZImage based plant phenotyping with incremental learning and active contoursPlant phenotyping investigates how a plant's genome, interacting with the environment, affects the observable traits of a plant (phenome). It is becoming increasingly important in our quest towards efficient and sustainable agriculture. While sequencing the genome is becoming increasingly efficient, acquiring phenotype information has remained largely of low throughput. Current solutions for automated image-based plant phenotyping, rely either on semi-automated or manual analysis of the imaging data, or on expensive and proprietary software which accompanies costly hardware infrastructure. While some attempts have been made to create software applications that enable the analysis of such images in an automated fashion, most solutions are tailored to particular acquisition scenarios and restrictions on experimental design. In this paper we propose and test, a method for the segmentation and the automated analysis of time-lapse plant images from phenotyping experiments in a general laboratory setting, that can adapt to scene variability. The method involves minimal user interaction, necessary to establish the statistical experiments that may follow. At every time instance (i.e., a digital photograph), it segments the plants in images that contain many specimens of the same species. For accurate plant segmentation we propose a vector valued level set formulation that incorporates features of color intensity, local texture, and prior knowledge. Prior knowledge is incorporated using a plant appearance model implemented with Gaussian mixture models, which utilizes incrementally information from previously segmented instances. The proposed approach is tested on Arabidopsis plant images acquired with a static camera capturing many subjects at the same time. Our validation with ground truth segmentations and comparisons with state-of-the-art methods in the literature shows that the proposed method is able to handle images with complicated and changing background in an automated fashion. An accuracy of 96.7% (dice similarity coefficient) was observed, which was higher than other methods used for comparison. While here it was tested on a single plant species, the fact that we do not employ shape driven models and we do not rely on fully supervised classification (trained on a large dataset) increases the ease of deployment of the proposed solution for the study of different plant species in a variety of laboratory settings. Our solution will be accompanied by an easy to use graphical user interface and, to facilitate adoption, we will make the software available to the scientific community.Massimo Minervinimassimo.minervini@imtlucca.itMohammed Abdelsameamohammed.abdelsamea@imtlucca.itSotirios A. Tsaftarissotirios.tsaftaris@imtlucca.it