Exploiting variable-width features in large vocabulary speech recognition

The use of variable-width features (prosodics, broad structural information etc.) in large vocabulary speech recognition systems is discussed. Although the value of this sort of information has been recognized in the past, previous approaches have not been widely used in speech systems because either they have not been robust enough for realistic, large vocabulary tasks or they have been limited to certain recognizer architectures. A framework for the use of variable-width features is presented which employs the N-Best algorithm with the features being applied in a post-processing phase. The framework is flexible and widely applicable, giving greater scope for exploitation of the features than previous approaches. Large vocabulary speech recognition experiments using TIMIT show that the application of variable-width features has potential benefits.

Observation of large-scale features on graphite by scanning tunnelling microscopy

Superlattice structures and rippling fringes were imaged on two separate pieces of graphite (HOPG) by scanning tunnelling microscopy (STM). We observed the corrugation conservation phenomenon on one of the superlattice structures where an overlayer does not attenuate the corrugation amplitude of the superlattice. Such a phenomenon may illustrate an implication that nanoscale defects a few layers underneath the surface may propagate through many layers without decay and form the superlattice structure on the topmost surface. Some rippling fringes with periodicities of 20 nm and 30 nm and corrugations of 0.1 nm and 0.15nm were observed in the superlattice area and in nearby regions. Such fringes are believed to be due to physical buckling of the surface. The stress required to generate such structures is estimated, and a possible cause is discussed. An equation relating the attenuation factor to the number of overlayers is proposed. © 2005 The Japan Society of Applied Physics.

Multiscale object features from clustered complex wavelet coefficients

This paper introduces a method by which intuitive feature entities can be created from ILP (InterLevel Product) coefficients. The ILP transform is a pyramid of decimated complex-valued coefficients at multiple scales, derived from dual-tree complex wavelets, whose phases indicate the presence of different feature types (edges and ridges). We use an Expectation-Maximization algorithm to cluster large ILP coefficients that are spatially adjacent and similar in phase. We then demonstrate the relationship that these clusters possess with respect to observable image content, and conclude with a look at potential applications of these clusters, such as rotation- and scale-invariant object recognition. © 2005 IEEE.

Biologically-inspired object recognition system with features from complex wavelets

In this paper, a novel cortex-inspired feed-forward hierarchical object recognition system based on complex wavelets is proposed and tested. Complex wavelets contain three key properties for object representation: shift invariance, which enables the extraction of stable local features; good directional selectivity, which simplifies the determination of image orientations; and limited redundancy, which allows for efficient signal analysis using the multi-resolution decomposition offered by complex wavelets. In this paper, we propose a complete cortex-inspired object recognition system based on complex wavelets. We find that the implementation of the HMAX model for object recognition in [1, 2] is rather over-complete and includes too much redundant information and processing. We have optimized the structure of the model to make it more efficient. Specifically, we have used the Caltech 5 standard dataset to compare with Serre's model in [2] (which employs Gabor filter bands). Results demonstrate that the complex wavelet model achieves a speed improvement of about 4 times over the Serre model and gives comparable recognition performance. © 2011 IEEE.

Upheaval Buckling Assessment Based on Pipeline Features

Upheaval buckling (UHB) is a common design issue for high temperature buried pipelines. This paper highlights some of thekey issues affecting out-of-straightness (OOS) assessment of pipelines. The following factors are discussed; uplift resistancesoil models, uplift resistance in cohesive soils, uplift mobilisation, ratcheting, uplift resistance at low H/D ratios and thecorrect methodology for load factor selection. A framework for determining ratcheting mobilisation is proposed. Furtherresearch is required to verify and validate this proposed framework. UHB assessment of three different diameter pipelineswere carried out using finite element SAGE PROFILE package incorporating pipeline mobilisation and the results arecompared with semi-analytical formulation proposed by Palmer et al. 1990. The paper also presents a summary of as-laidpipeline features based on projects over the past 10 years.

Branching toughens fibrous networks.

Fibrous collagenous networks are not only stiff but also tough, due to their complex microstructures. This stiff yet tough behavior is desirable for both medical and military applications but it is difficult to reproduce in engineering materials. While the nonlinear hyperelastic behavior of fibrous networks has been extensively studied, the understanding of toughness is still incomplete. Here, we identify a microstructure mimicking the branched bundles of a natural type I collagen network, in which partially cross-linked long fibers give rise to novel combinations of stiffness and toughness. Finite element analysis shows that the stiffness of fully cross-linked fibrous networks is amplified by increasing the fibril length and cross-link density. However, a trade-off of such stiff networks is reduced toughness. By having partially cross-linked networks with long fibrils, the networks have comparable stiffness and improved toughness as compared to the fully cross-linked networks. Further, the partially cross-linked networks avoid the formation of kinks, which cause fibril rupture during deformation. As a result, the branching allows the networks to have stiff yet tough behavior.

MCBoost: Multiple classifier boosting for perceptual co-clustering of images and visual features

We present a new co-clustering problem of images and visual features. The problem involves a set of non-object images in addition to a set of object images and features to be co-clustered. Co-clustering is performed in a way that maximises discrimination of object images from non-object images, thus emphasizing discriminative features. This provides a way of obtaining perceptual joint-clusters of object images and features. We tackle the problem by simultaneously boosting multiple strong classifiers which compete for images by their expertise. Each boosting classifier is an aggregation of weak-learners, i.e. simple visual features. The obtained classifiers are useful for object detection tasks which exhibit multimodalities, e.g. multi-category and multi-view object detection tasks. Experiments on a set of pedestrian images and a face data set demonstrate that the method yields intuitive image clusters with associated features and is much superior to conventional boosting classifiers in object detection tasks.

Automated sparse 3D point cloud generation of infrastructure using its distinctive visual features

The commercial far-range (>10 m) spatial data collection methods for acquiring infrastructure’s geometric data are not completely automated because of the necessary manual pre- and/or post-processing work. The required amount of human intervention and, in some cases, the high equipment costs associated with these methods impede their adoption by the majority of infrastructure mapping activities. This paper presents an automated stereo vision-based method, as an alternative and inexpensive solution, to producing a sparse Euclidean 3D point cloud of an infrastructure scene utilizing two video streams captured by a set of two calibrated cameras. In this process SURF features are automatically detected and matched between each pair of stereo video frames. 3D coordinates of the matched feature points are then calculated via triangulation. The detected SURF features in two successive video frames are automatically matched and the RANSAC algorithm is used to discard mismatches. The quaternion motion estimation method is then used along with bundle adjustment optimization to register successive point clouds. The method was tested on a database of infrastructure stereo video streams. The validity and statistical significance of the results were evaluated by comparing the spatial distance of randomly selected feature points with their corresponding tape measurements.

Recovering 3D Structure of Poorly Textured Infrastructure Scenes Using Point and Line Features

Most of the existing automated machine vision-based techniques for as-built documentation of civil infrastructure utilize only point features to recover the 3D structure of a scene. However it is often the case in man-made structures that not enough point features can be reliably detected (e.g. buildings and roofs); this can potentially lead to the failure of these techniques. To address the problem, this paper utilizes the prominence of straight lines in infrastructure scenes. It presents a hybrid approach that benefits from both point and line features. A calibrated stereo set of video cameras is used to collect data. Point and line features are then detected and matched across video frames. Finally, the 3D structure of the scene is recovered by finding 3D coordinates of the matched features. The proposed approach has been tested on realistic outdoor environments and preliminary results indicate its capability to deal with a variety of scenes.

ChESS - Quick and Robust Detection of Chess-board Features

Localization of chess-board vertices is a common task in computer vision, underpinning many applications, but relatively little work focusses on designing a specific feature detector that is fast, accurate and robust. In this paper the `Chess-board Extraction by Subtraction and Summation' (ChESS) feature detector, designed to exclusively respond to chess-board vertices, is presented. The method proposed is robust against noise, poor lighting and poor contrast, requires no prior knowledge of the extent of the chess-board pattern, is computationally very efficient, and provides a strength measure of detected features. Such a detector has significant application both in the key field of camera calibration, as well as in Structured Light 3D reconstruction. Evidence is presented showing its robustness, accuracy, and efficiency in comparison to other commonly used detectors both under simulation and in experimental 3D reconstruction of flat plate and cylindrical objects