Search results for "Seam carving"

showing 6 items of 6 documents

Seam-Based Edge Blending for Multi-Projection Systems

2016

Perceptual seamlessness of large-scale tiled displays is still a challenge. One way to avoid Bezel effects from contiguous displays is to blend superimposed parts of the image over the edges. This work proposes a new approach for edge blending. It is based on intensity edge blending adapted on the seam description of the image content. The main advantage of this method is to reduce visual artifacts thanks to context adaptation and smooth transitions. We evaluate the quality of the method with a perceptual experiment where it is compared with state-of-the-art methods. The new method shows most improvement in low frequency areas compared to the other techniques. This method can be inserted in…

Computer sciencebusiness.industryComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONImage content020207 software engineering02 engineering and technologyEdge (geometry)01 natural scienceslaw.inventionImage (mathematics)010309 opticsProjectorContext adaptationSeam carvinglaw0103 physical sciencesSignal Processing0202 electrical engineering electronic engineering information engineeringComputer visionArtificial intelligenceVisual artifactProjection (set theory)businessComputingMethodologies_COMPUTERGRAPHICSInternational Journal of Signal Processing, Image Processing and Pattern Recognition
researchProduct

Streams as Seams: Carving trajectories out of the time-frequency matrix

2020

A time-frequency representation of sound is commonly obtained through the Short-Time Fourier Transform. Identifying and extracting the prominent frequency components of the spectrogram is important for sinusoidal modeling and sound processing. Borrowing a known image processing technique, known as seam carving, we propose an algorithm to track and extract the sinusoidal components from the sound spectrogram. Experiments show how this technique is well suited for sound whose prominent frequency components vary both in amplitude and in frequency. Moreover, seam carving naturally produces some auditory continuity effects. We compare this algorithm with two other sine extraction techniques, bas…

Settore INF/01 - InformaticaTime-frequency analysis. Sinusoidal components. Seam carving.Settore ING-INF/03 - TelecomunicazioniComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
researchProduct

Springs-based Simulation for Image Retargeting

2011

In this paper an efficient method for image retargeting is pro- posed. It relies onto a mechanical model based on springs network. Each pixel displacement (compression or expan- sion) is given by the network response, according to the springs stiffness. The properties of the springs are deter- mined as function of the visual relevance of the pixels. Such model does not require any optimization, since its so- lution is obtained simply from a linear system of equations, allowing real-time application even for large images. The approach is fully automatic, though can be improved by interactively providing cues such as geometric constraints and/or manual relevant object labeling. The results pr…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniImage resizing Image retargeting simu- lation linear algebra visual saliencyPixelComputer sciencebusiness.industryStiffnessImage processingSystem of linear equationsDisplacement (vector)VisualizationSeam carvingmedicineComputer visionArtificial intelligencemedicine.symptombusiness
researchProduct

Real-time content-aware image resizing using reduced linear model

2010

In this paper an effective and efficient method for contentaware image resizing is proposed. It is based on the solution of a linear system where each pixel displacement (compression or expansion) is determined in dependence of the visual relevance of the pixel itself. The linear nature of the model allows real-time application of the method even for large images. This fully automatic approach can be also improved by interactively providing cues such as geometric constraints and/or manual relevant object labeling. The results have proven that the presented method achieves results comparable or superior to existent strategies, while improving efficiency.

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniPixelImage resizing Image retargeting linear optimization visual saliencyPhysics::Instrumentation and Detectorsbusiness.industryComputer scienceComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONLinear modelIterative reconstructionDisplacement (vector)Computer Science::GraphicsSeam carvingComputer Science::Computer Vision and Pattern RecognitionComputer Science::MultimediaComputer visionArtificial intelligencebusinessImage resolutionComputingMethodologies_COMPUTERGRAPHICS2010 IEEE International Conference on Image Processing
researchProduct

Retargeting Framework Based on Monte-carlo Sampling

2015

Advance in image technology and proliferation of acquisition devices like smartphones, digital cameras, etc., made the display of digital images ubiquitous. Many displays exist in the market, spanning within a large variety of resolutions and shapes. Thus, displaying content optimizing the available number of pixels has become a very important issue in the multimedia community, and the image retargeting problem is being widely faced. In this work, we propose an image retargeting framework based on monte-carlo sampling. We operate the non-homogeneous resizing as the composition of several simple atomic resizing functions. The shape of such atomic operator can be chosen within a set of tested…

Settore ING-INF/05 - Sistemi Di Elaborazione Delle InformazioniRetargetingSaliencyPixelComputer sciencebusiness.industryComputer Science (all)ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONVisualizationSet (abstract data type)Image resizingDigital imageSeam carvingMonte-carloRetargetingKey (cryptography)Computer visionArtificial intelligencebusiness
researchProduct

Physical simulation for real-time image/video retargeting

2012

Retargeting methods present content on arbitrary aspect ratio me- dia displays limiting distortions in relevant objects. This is done by means of applying non-homogeneous resizing operators across the whole media, constraining it to fit into the required size. Several succesful systems have been proposed to achieve image retargeting, while video retargeting is still challenging due to time consistency and computational complexity requirements. Two important con- tributes were proposed: non-homogeneous retargeting [Wolf et al. 2007] and improved seam-carving [Rubinstein et al. 2008]. The first one claims to achieve real-time performance but considers spa- tial coordinates separately. The lat…

Structure (mathematical logic)Settore ING-INF/05 - Sistemi Di Elaborazione Delle Informazioniimage retargeting spring-based system real timeSeam carvingbusiness.industryComputer scienceRetargetingComputer visionArtificial intelligencebusinessAspect ratio (image)Image (mathematics)
researchProduct