BieColl - Bielefeld eCollections
Not a member yet
1004 research outputs found
Sort by
Genome feature exploration using hyperbolic Self-Organising Maps
Get PDFThe advent of sequencing technologies allows to reassess the relationship between species in the hierarchically organized tree of life. Self-Organizing Maps (SOM) in Euclidean and hyperbolic space are applied to genomic signatures of 350 different organisms of the two superkingdoms Bacteria and Archaea to link the sequence signature space to pre-defined taxonomic levels, i.e. the tree of life. In the hyperbolic space the SOMs are trained by either the standard algorithm (HSOM) or in a hierarchical manner (H²SOM). For evaluating the SOM performances, distances between organisms in the feature space, on the SOM grid and in the taxonomy tree are compared pair-wise. We show that the structure recovered using the different SOMs reflects the gold standard of current taxonomy. The distances between species are better preserved when using the HSOM or H²SOM which makes the hyperbolic space better suited for embedding the high dimensional genomic signatures
Sleep Spindle Detection by Using Merge Neural Gas
Get PDFIn this paper the Merge Neural Gas (MNG) model is applied to detect sleep spindles in EEG. Features are extracted from windows of the EEG by using short time Fourier transform. The total power spectrum is computed in six frequency bands and used as input to the MNG network. The results show that MNG outperforms simple neural gas in correctly detecting sleep spindles. In addition the temporal quantization results as well as sleep trajectories are visualized on two-dimensional maps by using the OVING projection method
Vessel Extracting Gas - Using self organization in the extraction of vascular trees
Get PDFA network model is introduced that allows the extraction of the topological structure of a set of input vectors corresponding to image voxels from a 3D doppler or contrast enhanced ultrasound. This extraction is a precondition for many medical image registration algorithms. Results on artificial and real ultrasound image data sets are discussed
A flexible multi-server platform for distributed video information processing
Get PDFThe complexity of recent computer vision system calls for an infrastructure of distributed processing. This paper presents a platform acting as a framework for video information processing applications to plug in and contribute to the "intelligence" of the system. The platform is composed by a set of servers which collaborate with each other to complete the tasks like video capture, transmission, buffering and synchronization. A user side lib is also provided for the simplicity of application-platform interface. We show the usefulness of the platform by a motion detect application in our On-The-Spot Archiving system. As the platform is flexible, its usage is not limited in one or two systems
A Real-time Algorithm for Finger Detection in a Camera Based Finger-Friendly Interactive Board System
Get PDFThis paper proposes an approach to finger detection for a type of camera based interactive board. In this approach, finger finding is confined within a stripe that is the projection of the edge of the board on the image plane with respect to a camera instead of using global search. The region where a finger intersects with the stripe is first detected and segmented from the background. A region growing algorithm is then applied to the region to segment the whole finger. This approach can detect multi-targets and be implemented efficiently, processing 30 or more 640×120 images per second even in a cheap DSP
A vision based motion interface for mobile phones
Get PDFIn this paper we present an interface system for the control of mobile devices based on motion and using existing camera technology. In this system the user can control the phone's functions by performing a series of motions with the camera and each command is defined by a unique series of these motions. A sequence of motion features is produced using the phone's camera and these characterise the translation motion of the phone. These sequences of motion features are classified using _Hidden Markov Models_ (HMMs). In order to improve the robustness of the system the results of this classification are then filtered using a likelihood ratio and the entropy of the sequence to reject possibly incorrect sequences. When tested on 570 previously unseen motion sequences the system incorrectly classified only 5 sequences
Stochastic Attentional Selection and Shift on the Visual Attention Pyramid
Get PDFThis paper proposes a computational model of visual attention which performs stochastic attentional selection and shift on the visual attention pyramid that is computed for each image frame of a video sequence. In this model, the visual attention pyramid is generated according to the rareness criteria by using intensity contrast, saturation contrast, hue contrast, orientation and motion energy on a Gaussian resolution pyramid. On this attention pyramid, stochastic attentional selection and shift is performed on mechanisms of the dynamic maintenance of IOR(Inhibition Of Return), the bottom-up spatial attention and the adaptive competitive filtering of attention. Experimental results show that this model achieves stochastic visual pop-out to artificial pop-out targets and stochastic attentional selection and shift, especially the whole-part attention shift and the motion-follow attention, in daily scenes
Subunit Boundary Detection for Sign Language Recognition Using Spatio-temporal Modelling
Get PDFThe use of subunits offers a feasible way to recognize sign language with large vocabulary. The initial step is to partition signs into elementary units. In this paper, we firstly define a subunit as one continuous hand action in time and space, which comprises a series of interrelated consecutive frames. Then, we propose a solution to detect the subunit boundary according to spatio-temporal features using a three-stage hierarchy: in the first stage, we apply hand segmentation and tracking algorithm to capture motion speeds and trajectories; in the second stage, the obtained speed and trajectory information are combined to locate subunit boundaries; finally, temporal clustering by dynamic time warping (DTW) is adopted to merge similar segments and refine the results. The presented work does not need prior knowledge of the types of signs and is robust to signer behaviour variation. Moreover, it can provide a base for high-level sign language understanding. Experiments on many real-world signing videos show the effectiveness of the proposed work
A comparison between dissimilarity SOM and kernel SOM for clustering the vertices of a graph
Get PDFFlexible and efficient variants of the Self Organizing Map algorithm have been proposed for non vector data, including, for example, the dissimilarity SOM (also called the Median SOM) and several kernelized versions of SOM. Although the first one is a generalization of the batch version of the SOM algorithm to data described by a dissimilarity measure, the various versions of the second ones are stochastic SOM. We propose here to introduce a batch version of the kernel SOM and to show how this one is related to the dissimilarity SOM. Finally, an application to the classification of the vertices of a graph is proposed and the algorithms are tested and compared on a simulated data set
An Energy Function-Based Optimization of Matching Parameters and Reference Vectors in SOR Network
Get PDFIn this paper we propose an energy function-based optimization method in order to improve the approximation ability of the self-organizing relationship (SOR) network. In the execution mode, the SOR network can be used as a fuzzy inference engine. The output of the SOR network is calculated by using the reference vectors and matching parameters. The matching parameters, which correspond to the standard deviation of the Gaussian membership function used in fuzzy inference, are only defined in the execution mode. However, the issue of the optimization of the matching parameters has not yet been treated in previous works. To optimize the matching parameters, we introduce an energy function to the SOR network. The energy function can be used to tune not only the matching parameters but also the reference vectors with a gradient descent method. The proposed method is applied to a function approximation problem and the improvement of the approximation ability is confirmed