Search results for "GEP"
showing 10 items of 1017 documents
Browser independent content based image resizing for liquid web layouts
2010
A typical problem for webdesigners is to realize pages that can be potentially accessed from a number of display devices with different screen sizes and resolutions. Liquid layouts can help for this purpose. However, they can not typically be applied to images, which need to be rescaled or deformed. In both cases usability could be deteriorated. Content-aware image resizing techniques can help for this goal by rescaling the images to the desired width while preserving important image structures. This paper presents a content-aware resizing technique which can be seamlessly integrated into web pages without any effort from the user. The results from the system application prove its effective…
Composition of SIFT features for robust image representation
2010
In this paper we propose a novel feature based on SIFT (Scale Invariant Feature Transform) algorithm1 for the robust representation of local visual contents. SIFT features have raised much interest for their power of description of visual content characterizing punctual information against variation of luminance and change of viewpoint and they are very useful to capture local information. For a single image hundreds of keypoints are found and they are particularly suitable for tasks dealing with image registration or image matching. In this work we stretched the spatial coverage of descriptors creating a novel feature as composition of keypoints present in an image region while maintaining…
Using Temporal Texture for Content-Based Video Retrieval
2000
Textures evolving over time are called temporal textures and are very common in everyday life. Examples are the smoke flowing or the wavy water of a river. The idea explored in this paper is that image features based on temporal texture could allow a better performance of current content-based video retrieval systems that are mainly based on static characteristics of representative frames, like color and texture. To this aim we analyze the spatio-temporal nature of texture and its application in content-based access to video databases. In particular, we represent temporal texture using the spatio-temporal autoregressive (STAR) model and a variation of self-organizing maps (SOM) where each n…
Multidirectional Scratch Detection and Restoration in Digitized Old Images
2010
Line scratches are common defects in old archived videos, but similar imperfections may occur in printed images, in most cases by reason of improper handling or inaccurate preservation of the support. Once an image is digitized, its defects become part of that image. Many state-of-the-art papers deal with long, thin, vertical lines in old movie frames, by exploiting both spatial and temporal information. In this paper we aim to face with a more challenging and general problem: the analysis of line scratches in still images, regardless of their orientation, color, and shape. We present a detection/restoration method to process this defect.
Unsupervised Clustering in Personal Photo Collections
2008
In this paper we propose a probabilistic approach for the automatic organization of collected pictures aiming at more effective representation in personal photo albums. Images are analyzed and described in two representation spaces, namely, faces and background. Faces are automatically detected, rectified and represented projecting the face itself in a common low dimensional eigenspace. Backgrounds are represented with low-level visual features based on RGB histogram and Gabor filter energy. Face and background information of each image in the collection is automatically organized by mean-shift clustering technique. Given the particular domain of personal photo libraries, where most of the …
Exploiting Visual Saliency Algorithms for Object-Based Attention: A New Color and Scale-Based Approach
2017
Visual Saliency aims to detect the most important regions of an image from a perceptual point of view. More in detail, the goal of Visual Saliency is to build a Saliency Map revealing the salient subset of a given image by analyzing bottom-up and top-down factors of Visual Attention. In this paper we proposed a new method for Saliency detection based on colour and scale analysis, extending our previous work based on SIFT spatial density inspection. We conducted several experiments to study the relationships between saliency methods and the object attention processes and we collected experimental data by tracking the eye movements of thirty viewers in the first three seconds of observation o…
Texture classification for content-based image retrieval
2002
An original approach to texture-based classification of regions, for image indexing and retrieval, is presented. The system addresses automatic macro-textured ROI detection, and classification: we focus our attention on those objects that can be characterized by a texture as a whole, like trees, flowers, walls, clouds, and so on. The proposed architecture is based on the computation of the /spl lambda/ vector from each selected region, and classification of this feature by means of a pool of suitably trained support vector machines (SVM). This approach is an extension of the one previously developed by some of the authors to classify image regions on the basis of the geometrical shape of th…
A tool to support the creation of datasets of tampered videos
2015
Digital Video Forensics is getting a growing interest from the Multimedia research community, as the need for methods to validate the authenticity of a video content is increasing with the number of videos freely available to the digital users. Unlike Digital Image Forensics, to our knowledge, there are not standard datasets to test video forgery detection techniques. In this paper we present a new tool to support the users in creating datasets of tampered videos. We furthermore present our own dataset and we discuss some remarks about how to create forgeries difficult to be detected by an observer, to the naked eye.
State of the art in passive digital image forgery detection: copy-move image forgery
2017
Authenticating digital images is increasingly becoming important because digital images carry important information and due to their use in different areas such as courts of law as essential pieces of evidence. Nowadays, authenticating digital images is difficult because manipulating them has become easy as a result of powerful image processing software and human knowledge. The importance and relevance of digital image forensics has attracted various researchers to establish different techniques for detection in image forensics. The core category of image forensics is passive image forgery detection. One of the most important passive forgeries that affect the originality of the image is cop…
Fast adaptive frame preprocessing for 3D reconstruction
2015
Abstract: This paper presents a new online preprocessing strategy to detect and discard ongoing bad frames in video sequences. These include frames where an accurate localization between corresponding points is difficult, such as for blurred frames, or which do not provide relevant information with respect to the previous frames in terms of texture, image contrast and non-flat areas. Unlike keyframe selectors and deblurring methods, the proposed approach is a fast preprocessing working on a simple gradient statistic, that does not require to compute complex time-consuming image processing, such as the computation of image feature keypoints, previous poses and 3D structure, or to know a prio…