ÐWe study implementation issues for spatial convolution filters and their Fourier alternative, with the aim to optimize the accuracy of filter output. We focus on Gaussian scale-space filters and show that there exists a trade-off scale that subdivides the available scale range into two subintervals of equal length. Below this trade-off scale Fourier filtering yields more accurate results than ...

In this paper we describe our experiments in the automatic search task of TRECVid 2007. For this we have implemented a new video search technique based on SIFT features and manual annotation. We submitted two runs, one solely based on the SIFT features with keyframe matching and the other based on adapted SIFT features for video retrieval in addition to manually annotated data.

Facial perception research has benefited from the use of computer graphic methods, such as facial image prototyping and transformation. This paper describes new methods for improved prototyping and transformation of skin textures including wrinkles and stubble. We use a biologically inspired wavelet transform to capture the textural detail in different facial regions at multiple spatial scales ...

In this paper we describe an approach to recognizing poorly textured objects, that may contain holes and tubular parts, in cluttered scenes under arbitrary viewing conditions. To this end we develop a number of novel components. First, we introduce a new edge-based local feature detector that is invariant to similarity transformations. The features are localized on edges and a neighbourhood is ...

In our paper we explore the application of the SIFT method on terrestrial laser scan data. The energy of the backscattered laser light is represented in a reflectance image. This representation of the data can be directly used with standard SIFT implementations. We show that the extracted features are good candidates for registration. Furthermore, we show that feature matching based on the feat...

Content-aware image retargeting has attracted substantial research interests in the related research community. However, so far there is still no method can preserve important image contents and structure well without introducing deformation. To address this problem, we propose a Saliency & Structure Preserving Multi-operator (SSPM) method. SSPM classifies images into three categories utilizing...

In this paper, we present a method that uses web photos for measuring frame interestingness of a travel video. Web photo collections, such as those on Flickr, tend to contain interesting images because their images are more carefully taken, composed, and selected. Because these photos have already been chosen as subjectively interesting, they serve as evidence that similar images are also inter...

Classification of texture images, especially those with different orientation and scale changes, is a challenging and important problem in image analysis and classification. This paper proposes an effective scheme for rotation and scale invariant texture classification using log-polar wavelet signatures. The rotation and scale invariant feature extraction for a given image involves applying a l...

In this paper, an analytic solution is presented using differential transform method (DTM) for a class of wave equation. The emphasis is on the nonlinear two-dimensional wave equation. The procedures introduced in this paper are in recursive forms which can be used to obtain the closed form of the solutions, if they are required. The method is tested on various examples, and the results reveal ...

This paper proposes a high-precision, high-speed keypoint matching method using a two-stage Randomized Trees. The keypoint classification method uses the conventional Randomized Trees to enable highprecision, real-time keypoint matching. But the wide variety of view transformations for templates expressed by Randomized Trees make high-precision keypoint classification for all transformations di...