Megafauna play an important role in benthic ecosystem function and are sensitive indicators of environmental change. Non-invasive monitoring of benthic communities can be accomplished by seafloor imaging. However, manual quantification of megafauna in images is labor-intensive and therefore, this organism size class is often neglected in ecosystem studies. Automated image analysis has been proposed as a possible approach to such analysis, but the heterogeneity of megafaunal communities poses a non-trivial challenge for such automated techniques. Here, the potential of a generalized object detection architecture, referred to as iSIS (intelligent Screening of underwater Image Sequences), for the quantification of a heterogenous group of megafauna taxa is investigated. The iSIS system is tuned for a particular image sequence (i.e. a transect) using a small subset of the images, in which megafauna taxa positions were previously marked by an expert. To investigate the potential of iSIS and compare its results with those obtained from human experts, a group of eight different taxa from one camera transect of seafloor images taken at the Arctic deep-sea observatory HAUSGARTEN is used. The results show that inter- and intra-observer agreements of human experts exhibit considerable variation between the species, with a similar degree of variation apparent in the automatically derived results obtained by iSIS. Whilst some taxa (e. g. Bathycrinus stalks, Kolga hyalina, small white sea anemone) were well detected by iSIS (i. e. overall Sensitivity: 87%, overall Positive Predictive Value: 67%), some taxa such as the small sea cucumber Elpidia heckeri remain challenging, for both human observers and iSIS.

/pdf/semi-automated-image-analysis-for-the-assessment-of-4zxucr8k7r.pdf

Semi-automated image analysis for the assessment of megafaunal densities at the Arctic deep-sea observatory HAUSGARTEN.

http://xrm.phys.northwestern.edu/research/pdf_papers/2007/zheng_eaai_2007.pdf

Initialization enhancer for non-negative matrix factorization

This paper proposes a new document retrieval (DR) and plagiarism detection (PD) system using multilayer self-organizing map (MLSOM). A document is modeled by a rich tree-structured representation, and a SOM-based system is used as a computationally effective solution. Instead of relying on keywords/lines, the proposed scheme compares a full document as a query for performing retrieval and PD. The tree-structured representation hierarchically includes document features as document, pages, and paragraphs. Thus, it can reflect underlying context that is difficult to acquire from the currently used word-frequency information. We show that the tree-structured data is effective for DR and PD. To handle tree-structured representation in an efficient way, we use an MLSOM algorithm, which was previously developed by the authors for the application of image retrieval. In this study, it serves as an effective clustering algorithm. Using the MLSOM, local matching techniques are developed for comparing text documents. Two novel MLSOM-based PD methods are proposed. Detailed simulations are conducted and the experimental results corroborate that the proposed approach is computationally efficient and accurate for DR and PD.

Multilayer SOM With Tree-Structured Data for Efficient Document Retrieval and Plagiarism Detection

In this paper, we propose a novel method SOMKE, for kernel density estimation (KDE) over data streams based on sequences of self-organizing map (SOM). In many stream data mining applications, the traditional KDE methods are infeasible because of the high computational cost, processing time, and memory requirement. To reduce the time and space complexity, we propose a SOM structure in this paper to obtain well-defined data clusters to estimate the underlying probability distributions of incoming data streams. The main idea of this paper is to build a series of SOMs over the data streams via two operations, that is, creating and merging the SOM sequences. The creation phase produces the SOM sequence entries for windows of the data, which obtains clustering information of the incoming data streams. The size of the SOM sequences can be further reduced by combining the consecutive entries in the sequence based on the measure of Kullback-Leibler divergence. Finally, the probability density functions over arbitrary time periods along the data streams can be estimated using such SOM sequences. We compare SOMKE with two other KDE methods for data streams, the M-kernel approach and the cluster kernel approach, in terms of accuracy and processing time for various stationary data streams. Furthermore, we also investigate the use of SOMKE over nonstationary (evolving) data streams, including a synthetic nonstationary data stream, a real-world financial data stream and a group of network traffic data streams. The simulation results illustrate the effectiveness and efficiency of the proposed approach.

SOMKE: Kernel Density Estimation Over Data Streams by Sequences of Self-Organizing Maps

WeVoS-ViSOM: An ensemble summarization algorithm for enhanced data visualization

In this paper a variant of the well-known self-organizing map algorithm is exploited for document organization and retrieval. An ensemble of self-organizing maps are employed in an effort to boost the performance of the standard algorithm. In doing so, the feature space is uniformly sampled and the bootstrapped sets that are created are supplied to each of the constituent members of the ensemble. The proposed variant along with the standard selforganizing map algorithm are used to partition the document repository into clusters of semantically related documents. The quality of clustering offered by the proposed variant is accessed quantitatively via information retrieval experiments using a set of test documents to query the text clusters created by the proposed algorithm. The same experiment is repeated for the standard self-organizing algorithm. An improved performance with respect to the average recall-precision curves is achieved by the proposed variant compared to the standard algorithm.

An ensemble of SOM networks for document organization and retrieval

http://poseidon.csd.auth.gr/papers/PUBLISHED/JOURNAL/pdf/Georgakis_NN2004.pdf

Marginal median SOM for document organization and retrieval

Underwater images analysis is a difficult task due to their specific attributes: weak and variable lighting, low contrast, blurring. Therefore powerful image analysis algorithms, application specific, must be employed to obtain good results. In this paper we propose such a novel architecture based on a support vector machine (SVM) classifier, dedicated to large underwater scenes analysis for the specific task of localizing circular shaped objects of known dimension ? the pressure equalization openings on the underwater face of a hydro-dam. Despite the very good recognition performance of SVM classifiers, their success on such poor quality images is relatively modest. The new proposed architecture achieves the maximization of the correct classification rate in two steps. In the first step, a non-linear SVM classifier is trained on raw color pixel features extracted from regions of interest of approximately the object's size. In the classification phase, the underwater image to be analyzed is decomposed on such partially overlapping elementary regions of interest. The regions of interest are classified by the SVM, using as threshold for the decision function a real value selected to minimize the false rejection rate. Then, in the second step, a shape descriptor (the circularity) of the patterns classified by the SVM as objects of interest is computed. This shape descriptor of the positive patterns is used for their classification as objects of interest or not, through a simple threshold comparison. As a result of this classification, the false acceptance rate is minimized as well, thus refining the classification results.

A New SVM-Based Architecture for Object Recognition in Color Underwater Images with Classification Refinement by Shape Descriptors

The problem of lip contour detection is critical in the lipreading systems based on contour processing. The typical contour detection strategy based on image segmentation in homogeneous regions fails in the case when the mouth images available for lipreading are lowcontrast gray level images. Most of the solutions adopted require manual marking of some contour points. Here we propose a new solution from the image segmentation class suitable to lip contour extraction, using a modified version of the fuzzy c-means image segmentation algorithm. The novelty of the solution proposed consists in the types of features used for segmentation, which include not only luminance information (as in the standard use of fuzzy cmeans), but also spatial information about the pixels in the image. After a simple filtering of the outliers, the contours of the resulting segmented objects are extracted. The experimental results obtained are superior to the ones obtained by standard or other versions of geometrically constrained fuzzy c-means, or by gradient-based edge detection strategies, without the need of manual marking of any contour points. Thus we consider the strategy proposed promising for automatic lip contour extraction applications.

/pdf/a-new-fuzzy-c-means-based-segmentation-strategy-applications-4n5vqy6mjh.pdf

A new fuzzy c-means based segmentation strategy. applications to lip region identification

A novel fuzzy edge detection and classification scheme to aid hydro-dams surface examination

Apostolos Georgakis

Papers

An ensemble of SOM networks for document organization and retrieval

Marginal median SOM for document organization and retrieval

A New SVM-Based Architecture for Object Recognition in Color Underwater Images with Classification Refinement by Shape Descriptors

A new fuzzy c-means based segmentation strategy. applications to lip region identification

A novel fuzzy edge detection and classification scheme to aid hydro-dams surface examination