Fourier active appearance models

Gaining invariance to camera and illumination variations has been a well investigated topic in Active Appearance Model (AAM) fitting literature. The major problem lies in the inability of the appearance parameters of the AAM to generalize to unseen conditions. An attractive approach for gaining invariance is to fit an AAM to a multiple filter response (e.g. Gabor) representation of the input image. Naively applying this concept with a traditional AAM is computationally prohibitive, especially as the number of filter responses increase. In this paper, we present a computationally efficient AAM fitting algorithm based on the Lucas-Kanade (LK) algorithm posed in the Fourier domain that affords invariance to both expression and illumination. We refer to this as a Fourier AAM (FAAM), and show that this method gives substantial improvement in person specific AAM fitting performance over traditional AAM fitting methods.

Symmetry adaptation of correlated states in the valence bond basis

Symmetry?adapted linear combinations of valence?bond (VB) diagrams are constructed for arbitrary point groups and total spin S using diagrammatic VB methods. VB diagrams are related uniquely to invariant subspaces whose size reflects the number of group elements; their nonorthogonality leads to sparser matrices and is fully incorporated into a binary integer representation. Symmetry?adapated linear combinations of VB diagrams are constructed for the 1764 singlets of a half?filled cube of eight sites, the 2.8 million ??electron singlets of anthracene, and for illustrative S?0 systems.

Fast computation of Legendre and Zernike moments

This paper presents recursive algorithms for fast computation of Legendre and Zernike moments of a grey-level image intensity distribution. For a binary image, a contour integration method is developed for the evaluation of Legendre moments using only the boundary information. A method for recursive calculation of Zernike polynomial coefficients is also given. A square-to-circular image transformation scheme is introduced to minimize the computation involved in Zernike moment functions. The recursive formulae can also be used in inverse moment transforms to reconstruct the original image from moments. The mathematical framework of the algorithms is given in detail, and illustrated with binary and grey-level images.

Lo visual como construcción. Desarrollo de un modelo pictórico de representación de la imagen

903 páginas, bibliografía en páginas 854-895, glosario en páginas 896-903

Logic-operated mathematical morphology and its optical implementation

A more powerful tool for binary image processing, i.e., logic-operated mathematical morphology (LOMM), is proposed. With LOMM the image and the structuring element (SE) are treated as binary logical variables, and the MULTIPLY between the image and the SE in correlation is replaced with 16 logical operations. A total of 12 LOMM operations are obtained. The optical implementation of LOMM is described. The application of LOMM and its experimental results are also presented. (C) 1999 Optical Society of America.

Automated Detection of Exposed Reinforcement in Post-Earthquake Safety and Structural Evaluations

Post-earthquake structural safety evaluations are currently performed manually by a team of certified inspectors and/or structural engineers. This process is time-consuming and costly, keeping owners and occupants from returning to their businesses and homes. Automating these evaluations would enable faster, and potentially more consistent, relief and response processes. In order to do this, the detection of exposed reinforcing steel is of utmost significance. This paper presents a novel method of detecting exposed reinforcement in concrete columns for the purpose of advancing practices of structural and safety evaluation of buildings after earthquakes. Under this method, the binary image of the reinforcing area is first isolated using a state-of-the-art adaptive thresholding technique. Next, the ribbed regions of the reinforcement are detected by way of binary template matching. Finally, vertical and horizontal profiling are applied to the processed image in order to filter out any superfluous pixels and take into consideration the size of reinforcement bars in relation to that of the structural element within which they reside. The final result is the combined binary image disclosing only the regions containing rebar overlaid on top of the original image. The method is tested on a set of images from the January 2010 earthquake in Haiti. Preliminary test results convey that most exposed reinforcement could be properly detected in images of moderately-to-severely damaged concrete columns.

Beyond dataset bias: Multi-task unaligned shared knowledge transfer

Many visual datasets are traditionally used to analyze the performance of different learning techniques. The evaluation is usually done within each dataset, therefore it is questionable if such results are a reliable indicator of true generalization ability. We propose here an algorithm to exploit the existing data resources when learning on a new multiclass problem. Our main idea is to identify an image representation that decomposes orthogonally into two subspaces: a part specific to each dataset, and a part generic to, and therefore shared between, all the considered source sets. This allows us to use the generic representation as un-biased reference knowledge for a novel classification task. By casting the method in the multi-view setting, we also make it possible to use different features for different databases. We call the algorithm MUST, Multitask Unaligned Shared knowledge Transfer. Through extensive experiments on five public datasets, we show that MUST consistently improves the cross-datasets generalization performance. © 2013 Springer-Verlag.

土石混合体细观结构力学及其边坡稳定性研究

Soil-rock mixture (S-RM) refers to one extremely uneven loose rock and soil materials system with certain stone content. Its formation has started since Quaternary and it is composed of block stone, fine grained soil and pore with certain project scale and high strength. S-RM has extensive distribution in nature, especially in southwest China where the geotectonic background is complicated, the fracture activity is developed and the geomorphological characteristics of high mountain and steep gorge area are protuberant. This kind of complicated geologic body has developed wider in these areas. S-RM has obvious difference with the general soil or rock (rock mass) in physical and mechanical properties because its two components-“soil” and “rock-block” has extreme differences in physical and mechanical properties. The proposition of S-RM and its deep research are needed in the modern engineering construction. It is also the necessity in the modern development of rock and soil mechanics. The dissertation starts from the meso-structural characteristics of soil-rock and takes a systematic research on its meso-structural mechanics, deformation and failure mechanism and the stability of S-RM slope. In summary, it achieves the following innovative results and conclusions. There are various views on the conception of S-RM and its classification system. Based on the large number of field tests, the dissertation makes the conception and classification of S-RM more systematic. It systematically proposed the conception of meso-structural mechanics of S-RM. Thus the dissertation has laid a foundation for its deep study. With the fast development of the computer technology and digital image processing theory, digital image processing technology has been successfully applied in many fields and provided reliable technology support for the quantitative description of the structural characteristics of S-RM. Based on the digital image processing technology, the dissertation systematically proposes and developed the quantitative analysis method and quantitative index for the meso-structure of S-RM. The results indicate that the meso-structure such as its internal soil-rock granularity composition, the soil-rock shape and the orientability has obvious self-organization in the macro statistical level. The dissertation makes a systematic research on the physical mechanical properties, deformation and failure mechanism of S-RM based on large field test. It proposes the field test for the underwater S-RM and deduces the 3D data analysis method of in-situ horizontal push-shear test. The result indicates that S-RM has significant phenomenon of shear dilatancy in the shearing process, and its dilatancy will be more obvious with the increased proportion of rock or the decreased confining pressure. The proportion of rock has great effect on the strength of S-RM and rock-block, especially the spatial position of particles with comparatively big size has great effect on the shape and spatial position of the sample shear zone. The dissertation makes some improvements in the single ring infiltration test equipment and its application on the permeability of S-RM. The results indicate that the increasing of rock-block would make it more difficult for the soil to fill in the vacuity between the rock-block and the proportion would increase which would result in the increased permeability coefficient. The dissertation builds the real meso-structural model of S-RM based on the digital image processing technology. By using geometric reconstruction technology, it transfers the structural mode represented by Binary image into CAD format, which makes it possible to introduce the present finite element analysis software to take research on numerical experimental investigation. It systematically realizes leaping research from the image，geometric mode, to meso-structural mechanics numerical experiment. By using this method, the dissertation takes large scale numerical direct-shear test on the section of S-RM. From the mesoscopic perspective, it reveals three extended modes about the shear failure plane of S-RM. Based on the real meso-structural model and by using the numerical simulation test, the character and mechanics of seepage failure of S-RM are studied. At the same time, it builds the real structural mode of the slope based on the analysis about the slope crosssection of S-RM. By using the strength reduction method, it takes the research on the stability of S-RM and gets great achievements. The three dimensional geometric reconstruction technology of rock block is proposed, which provides technical support for the reconstruction of the 3D meso-structural model of S-RM. For the first time, the dissertation builds the stochastic structure model of two-dimensional and three-dimensional polygons or polyhedron based on the stochastic simulation technique of monte carlo method. It breaks the traditional research which restricted to the random generation method of regular polygon and develops the relevant software system (R-SRM2D/3D) which has great effect on meso-structural mechanics of S-RM. Based on the R-SRM software system which randomly generates the meso-structural mode of S-RM according to the different meso-structural characteristics, the dissertation takes a series of research on numerical test of dual axis and real three-axis, systematically analyses the meso destroy system, the effects of meso-structural characteristics such as on the stone content, size composition and block directionality on the macro mechanical behavior and macro-permeability. Then it proposes the expression of the upper and lower limit for the macro-permeability coefficient of the inhomogeneous geomaterials, such as S-RM. By using the strength reduction FEM, the dissertation takes the research on the stability of the slope structural mode of the randomly formed S-RM. The results indicate that generally, the stability coefficient of S-RM slope increases with the increasing of stone content; on the condition of the same stone content, the stability coefficient of slope will be different with different size composition and the space position of large block at the internal slop has great effect on the stability. It suggests that meso-structural characteristics, especially the space position of large block should be considered when analyzing the stability of this kind of slope and strengthening design. Taking Xiazanri S-RM slope as an example, the dissertation proposes the fine modeling of complicated geologic body based on reverse engineering and the generation method of FLAC3D mode. It resolves the bottleneck problem about building the fine structural mode of three-dimensional geological body. By using FLAC3D, the dissertation takes research on the seepage field and the displacement field of Xiazanri S-RM slope in the process of reservoir water level rising and decreasing. By using strength reduction method, it analyses the three-dimension stability in the process of reservoir water level rising and decreasing. The results indicate that the slope stability firstly show downward trend in the process of reservoir water level rising and then rebound to increase; the sudden drawdown of reservoir water level has great effect on the slope stability and this effect will increase with the sudden drawdown amplitude rising. Based on the result of the rock block size analysis of S-RM, and using R-SRM2D the stochastic structure model of Xiazanri S-RM slope is built. By using strength reduction method, the stability of the stochastic structure model is analysis, the results shows that the stability factor increases significantly after considering the block.

幼儿绘画表征的发展－－发展过程及其影响因素

Two major questions in this study are the development of children's representative drawing and the influence of semantic representation and image representation on it. Children aged from 3 and a half to 7 participated the experiments. Two-dimension and three-dimension displays were used in four experiments. The results show that: The development of children's representational drawing can be divided into stages. They become maturer in selecting the strategies of the representational drawing, which are different in nature across different ages. There is a development from feature processing to integrative processing in children's drawing. At the feature processing stage, the typological features are represented easily. No matter global or partial. They tend to use unconnected parts to represent, which is called the strategy of distributed representation, those displays without prominent features. In integrative processing stage, the features of two-dimension display are integrated according to its gestalt. And the features of three-dimension display are integrated by its prototypical view across the main axis of the display. Cubic representations were found in some of the children's drawings, but none of them can do it from a perspective view before 7 years old. The semantic processing of the display, both global and partial meaning, can influence the development of the representational drawing. The structural features of the display influence the development of drawing representation. Semantic principles and structural features influence the representational drawings together. For three-dimension display, the semantic face and structural face coexist and work together. Children's ability to draw the display according to the right perspective rather than the prototypical view increase along with them growing up.

Vectorizing Face Images by Interpreting Shape and Texture Computations

The correspondence problem in computer vision is basically a matching task between two or more sets of features. In this paper, we introduce a vectorized image representation, which is a feature-based representation where correspondence has been established with respect to a reference image. This representation has two components: (1) shape, or (x, y) feature locations, and (2) texture, defined as the image grey levels mapped onto the standard reference image. This paper explores an automatic technique for "vectorizing" face images. Our face vectorizer alternates back and forth between computation steps for shape and texture, and a key idea is to structure the two computations so that each one uses the output of the other. A hierarchical coarse-to-fine implementation is discussed, and applications are presented to the problems of facial feature detection and registration of two arbitrary faces.

Context-Based Vision System for Place and Object Recognition

While navigating in an environment, a vision system has to be able to recognize where it is and what the main objects in the scene are. In this paper we present a context-based vision system for place and object recognition. The goal is to identify familiar locations (e.g., office 610, conference room 941, Main Street), to categorize new environments (office, corridor, street) and to use that information to provide contextual priors for object recognition (e.g., table, chair, car, computer). We present a low-dimensional global image representation that provides relevant information for place recognition and categorization, and how such contextual information introduces strong priors that simplify object recognition. We have trained the system to recognize over 60 locations (indoors and outdoors) and to suggest the presence and locations of more than 20 different object types. The algorithm has been integrated into a mobile system that provides real-time feedback to the user.

A high performance IIR digital filter chip

The design of a high-performance IIR (infinite impulse response) digital filter is described. The chip architecture operates on 11-b parallel, two's complement input data with a 12-b parallel two's complement coefficient to produce a 14-b two's complement output. The chip is implemented in 1.5-µm, double-layer-metal CMOS technology, consumes 0.5 W, and can operate up to 15 Msample/s. The main component of the system is a fine-grained systolic array that internally is based on a signed binary number representation (SBNR). Issues addressed include testing, clock distribution, and circuitry for conversion between two's complement and SBNR.

A vision fronted with a new disparity model

We are developing a frontend that is based on the image representation in the visual cortex and plausible processing schemes. This frontend consists of multiscale line/edge and keypoint (vertex) detection, using models of simple, complex and end-stopped cells. This frontend is being extended by a new disparity model. Assuming that there is no neural inverse tangent operator, we do not exploit Gabor phase information. Instead, we directly use simple cell (Gabor) responses at positions where lines and edges are detected.

Multi-scale lines and edges in V1 and beyond: brightness, object categorization and recognition, and consciousness

In this paper we present an improved model for line and edge detection in cortical area V1. This model is based on responses of simple and complex cells, and it is multi-scale with no free parameters. We illustrate the use of the multi-scale line/edge representation in different processes: visual reconstruction or brightness perception, automatic scale selection and object segregation. A two-level object categorization scenario is tested in which pre-categorization is based on coarse scales only and final categorization on coarse plus fine scales. We also present a multi-scale object and face recognition model. Processing schemes are discussed in the framework of a complete cortical architecture. The fact that brightness perception and object recognition may be based on the same symbolic image representation is an indication that the entire (visual) cortex is involved in consciousness.

Advanced side information creation techniques and framework for Wyner-Ziv video coding

Recently, several distributed video coding (DVC) solutions based on the distributed source coding (DSC) paradigm have appeared in the literature. Wyner-Ziv (WZ) video coding, a particular case of DVC where side information is made available at the decoder, enable to achieve a flexible distribution of the computational complexity between the encoder and decoder, promising to fulfill novel requirements from applications such as video surveillance, sensor networks and mobile camera phones. The quality of the side information at the decoder has a critical role in determining the WZ video coding rate-distortion (RD) performance, notably to raise it to a level as close as possible to the RD performance of standard predictive video coding schemes. Towards this target, efficient motion search algorithms for powerful frame interpolation are much needed at the decoder. In this paper, the RD performance of a Wyner-Ziv video codec is improved by using novel, advanced motion compensated frame interpolation techniques to generate the side information. The development of these type of side information estimators is a difficult problem in WZ video coding, especially because the decoder only has available some reference, decoded frames. Based on the regularization of the motion field, novel side information creation techniques are proposed in this paper along with a new frame interpolation framework able to generate higher quality side information at the decoder. To illustrate the RD performance improvements, this novel side information creation framework has been integrated in a transform domain turbo coding based Wyner-Ziv video codec. Experimental results show that the novel side information creation solution leads to better RD performance than available state-of-the-art side information estimators, with improvements up to 2 dB: moreover, it allows outperforming H.264/AVC Intra by up to 3 dB with a lower encoding complexity.