There is a rich literature of approaches to image feature extraction in computer vision. Many sophisticated approaches exist for lowand high-level feature extraction but can be complex to implement with parameter choice guided by experimentation, but impeded by speed of computation. We have developed new ways to extract features based on notional use of physical paradigms, with parameterisation...

We present a method for automatic feature extraction and cross-modal mapping using deep learning. Our system uses stacked autoencoders to learn a layered feature representation of the data. Feature vectors from two (or more) different domains are mapped to each other, effectively creating a cross-modal mapping. Our system can either run fully unsupervised, or it can use high-level labeling to f...

This paper proposes enhancements to the deformable models. Focusing on the problem of vessel segmentation, two general methods for improving the performance of the snakes are explained. The snake framework has a critical step when using the energy minimising scheme applied to the segmentation problem in computer vision: the potential map is based on the output of a low level feature detection o...

Physical analogies are an exciting paradigm for creating techniques for image feature extraction. A transform using an analogy to light rays has been developed for the detection of circular and tubular features. It uses a 2D ray tracing algorithm to follow rays through an image, interacting at a low level, to emphasise higher level features. It has been empirically tested as a pre-processor to ...

In this paper, we summarize our results for the shot boundary and high level feature detection task at TRECVID 2007. Our shot boundary detection approach of previous TRECVID evaluations served as a basis for our experiments this year and was modified in several ways. First, we have incorporated a new metric selection for cut detection based on the evaluation of a clustering result. Second, we h...

In this paper we promote the idea of using pixel-based models not only for low level vision, but also to extract high level symbolic representations. We use a deep architecture which has the distinctive property of relying on computational units that incorporate classic computer vision invariances and, especially, the scale invariance. The learning algorithm that is proposed, which is based on ...

Visual action recognition is an important problem in computer vision. In this paper, we propose a new method to probabilistically model and recognize actions of articulated objects, such as hand or body gestures, in image sequences. Our method consists of three levels of representation. At the low level, we first extract a feature vector invariant to scale and in-plane rotation by using the Fou...

This paper describes experiments carried out by the UC3M team for TRECVID 2008 high-level feature extraction task. Being our first participation in TRECVID, our goal this year has been to develop a modular system to facilitate future developments and incorporation of new functionality (feature extraction and classification modules). We have basically carried out experiments with two different k...

This paper discusses our expert system called Integrated System for Facial Expression Recognition (ISFER), which performs recognition and emotional classification of human facial expression from a still full-face image. The system consists of two major parts. The first one is the ISFER Workbench, which forms a framework for hybrid facial feature detection. Multiple feature detection techniques ...

introduction: oral mucositis is considered a severe complication in cancer patients receiving radiotherapy or chemotherapy for head and neck cancer. the aim of this review study was to assess the effect of low level laser therapy for prevention and management of oral mucositis in cancer patients. methods: the electronic databases searched included pubmed, isi web of knowledge and google scholar...