Vol. 23 (2014):
Abstracts and Contents of Papers
Reviewers of this volume
Machine GRAPHICS & VISION, Vol. 23 (2014), No. 1/2:
MGV vol. 23, no. 1/2, 2014, pp. 1-2.
Hast A., Marchetti A.:
Improved Illumination Correction that Preserves Medium Sized Objects
MGV vol. 23, no. 1/2, 2014, pp. 3-20.
Illumination correction is a method used for removing the influence of light coming from the
environment and of other distorting factors in the image capturing process. An algorithm based on the
luminance mapping is proposed that can be used to remove low frequency variations in the intensity,
and to increase the contrast in low contrast areas when necessary. Moreover, the algorithm can be
employed to preserve the intensity of medium-sized objects with different intensity or colour than their
surroundings, which otherwise would tend to be washed out. Furthermore, examples are given showing
how the method can be used for both greyscale images and colour photos.
illumination correction, luminance mapping, image stitching, image mosaicing, vignetting.
A Method of Constructing Phyllotaxically Arranged Modular Models by Partitioning the Interior of a Cylinder or a Cone
MGV vol. 23, no. 1/2, 2014, pp. 21-36.
The paper describes a method of partitioning a cylinder space into three-dimensional subspaces,
congruent to each other, as well as partitioning a cone space into subspaces similar to each
other. The way of partitioning is of such a nature that the intersection of any two subspaces is the
empty set. Subspaces are arranged with regard to phyllotaxis. Phyllotaxis lets us distinguish privileged
directions and observe parastichies trending these directions. The subspaces are created by sweeping
a changing cross-section along a given path, which enables us to obtain not only simple shapes but
also complicated ones. Having created these subspaces, we can put modules inside them, which do not
need to be obligatorily congruent or similar. The method ensures that any module does not intersect
another one. An example of plant model is given, consisting of modules phyllotaxically arranged inside
a cylinder or a cone.
computer graphics; modeling; modular model; phyllotaxis; cylinder partitioning; cone partitioning; genetic helix; parastichy.
Baataoui A., El Akkad N., Saaidi A., Satori K., Masrar Med.:
Robust Method for Camera Self-Calibration by an Unknown Planar Scene
MGV vol. 23, no. 1/2, 2014, pp. 37-57.
In this paper we present a self-calibration method for a CCD camera with varying intrinsic
parameters based on an unknown planar scene. The advantage of our method is reducing the number of
images (two images) needed to estimate the parameters of the camera used. Moreover, self-calibration
equations are related to the number of points matched (very numerous and easy to detect) rather than
to the number of images, since the use of a large number of images requires high computation time. On
the other hand, we base on the points matched, which are numerous, when estimating the projection
matrices and homographies between the images. The latter are used with the images of the absolute
conic to formulate a system of non-linear equations (self-calibration equations depend on the number
of matched pairs). Finally, the intrinsic parameters of the camera can be obtained by minimizing a
non-linear cost function in a two-step procedure: initialization and optimization. Experiment results
show the robustness of our algorithms in terms of stability and convergence.
matching, self-calibration, equilateral triangle, absolute conic, homography, varying intrinsic parameters.
Torkhani F., Wang K., Chassery J.-M.:
A Curvature-Tensor-Based Perceptual
Quality Metric for 3D Triangular Meshes
MGV vol. 23, no. 1/2, 2014, pp. 59-82.
Perceptual quality assessment of 3D triangular meshes is crucial for a variety of applications.
In this paper, we present a new objective metric for assessing the visual difference between a
reference triangular mesh and its distorted version produced by lossy operations, such as noise addition,
simplification, compression and watermarking. The proposed metric is based on the measurement of
the distance between curvature tensors of the two meshes under comparison. Our algorithm uses not
only tensor eigenvalues (i.e., curvature amplitudes) but also tensor eigenvectors (i.e., principal curvature
directions) to derive a perceptually-oriented tensor distance. The proposed metric also accounts
for the visual masking effect of the human visual system, through a roughness-based weighting of the
local tensor distance. A final score that reflects the visual difference between two meshes is obtained
via a Minkowski pooling of the weighted local tensor distances over the mesh surface. We validate the
performance of our algorithm on four subjectively-rated visual mesh quality databases, and compare the
proposed method with state-of-the-art objective metrics. Experimental results show that our approach
achieves high correlation between objective scores and subjective assessments.
3D triangular mesh, perceptual quality, human visual system, objective metric, curvature tensor, visual masking.
Paradowski M., Durak M., Broda B.:
Bag of Words - Quality Issues of Near-Duplicate Image Retrieval
MGV vol. 23, no. 1/2, 2014, pp. 83-96.
This paper addresses the problem of large scale near-duplicate image retrieval. Issues related
to visual words dictionary generation are discussed. A new spatial verification routine is proposed. It
incorporates neighborhood consistency, term weighting and it is integrated into the Bhattacharyya
coefficient. The proposed approach reaches almost 10% higher retrieval quality, comparing to other
recently reported state-of-the-art methods.
spatial verification, vector space model, visual words, clustering.
Lalithamani N., Sabrigiriraj M.:
Technique to Generate a Face and Palm Vein-Based Fuzzy Vault for a Multi-Biometric Cryptosystem
MGV vol. 23, no. 1/2, 2014, pp. 97-114.
Template security of biometric systems is a vital issue and needs critical focus. The importance
lies in the fact that unlike passwords, stolen biometric templates cannot be revoked. Hence, the
biometric templates cannot be stored in plain format and needs strong protection against any forgery. In
this paper, we present a technique to generate face and palm vein-based fuzzy vault for multi-biometric
cryptosystem. Here, initially the input images are pre-processed using various processes to make images
fit for further processing. In our proposed method, the features are extracted from the processed face
and palm vein images by finding out unique common points. The chaff points are added to the already
extracted points to obtain the combined feature vector. The secret key points which are generated
based on the user key input (by using proposed method) are added to the combined feature vector
to have the fuzzy vault. For decoding, the multi-modal biometric template from palm vein and face
image is constructed and is combined with the stored fuzzy vault to generate the final key. Finally,
the experimentation is conducted using the palm vein and face database available in the CASIA and
JAFFE database. The evaluation metrics employed are FMR (False Match Ratio) and GMR (Genuine
Match Ratio). From the metric values obtained for the proposed system, we can infer that the system
has performed well.
multimodal biometric cryptosystems, biometric template security, palm vein feature extraction, face feature extraction, fuzzy vault, secret key.
Wei Z., Wang Z., Kim H., Kim Y., Kim J.:
Novel Approach Based on Topological Simplification Algorithm Optimized with Particle Swarm Optimization
MGV vol. 23, no. 1/2, 2014, pp. 115-132.
The movement of people can be considered as the flow of liquid, so we can use the methods
employed for the flow of liquid to understand the motion of a crowd. Based on this, we present a novel
framework for abnormal behavior detection in crowded scenes. We extract a topological structure from
the crowd with the topology simplification algorithm. However, a conventional topology simplification
algorithm can not work well if we apply it to the crowd directly because there is too much noises
produced by the random motion of the people in the original image. To overcome this, we make a
step forward by optimizing this model using Particle Swarm Optimization (PSO) to perform the
advection of particle population spread randomly over the image frames. Then we propose two new
methods for analyzing the boundary point structure and extraction of a critical point from the particle
motion field; both methods can be used to describe the global topological structure of the crowd motion.
The advantage of our approach is that each kind of abnormal event can be described as a specific change
in the topological structure, so we do not need construct a complex classifier, but can classify the crowd
anomalies dynamically and directly. Moreover, the approach monitors the crowd motion macroscopically,
making it insensitive to the motion of an individual, disregarding the global movement. The result of
an experiment conducted on a common data set shows that our method is both precise and stable.
topological structure, particle swarm optimization, abnormal behavior, crowd behavior modeling.
MGV vol. 23, no. 1/2, 2014, pp. 133-134.
Machine GRAPHICS & VISION, Vol. 23 (2014), No. 3/4:
MGV vol. 23, no. 3/4, 2014, pp. 1-2.
Visualization and Interaction in the Atlas of the Human Brain, Head and Neck
MGV vol. 23, no. 3/4, 2014, pp. 3-10.
Our ultimate objective is to create a holistic and reference atlas of the whole adult human brain along with the head and neck. Several techniques have been employed to create atlases. Here we discuss the atlas design and use from a point of view of two key techniques, visualization and interaction. For visualization, surface rendering of a geometrical model of the brain, head and neck is employed. Geometrical model ensures anatomic parcellability, high (sub-pixel) resolution, editibility, extendibility, structure separability, structure-to-structure conflict detection, and integration a knowledge-based content with the atlas. Interaction allows the user to create and explore any region of interest along with its surroundings just with a few clicks, taking into account that the atlas provides a rich set of functions and the number of atlas components is about 3,000. There are seven types of interaction enabling to: select and deselect tissue classes/groups/individual structures, do real-time manipulation, do virtual dissections, select and scroll the original scans, query a structure to get its label or location, get stereotactic coordinates and measure distances, and support other functionality. This design of visualization and interaction provides a fast and easy to use solution, and allows the atlas to run on desktop and mobile iPad and Android-based platforms.
atlas, brain, head, neck, visualization, interaction, geometrical model, integration, knowledge base, desktop platform, mobile platform.
Pach J.L., Bilski P.:
Robust Method for the Text Line Detection and Splitting of Overlapping Text in the Latin Manuscripts
MGV vol. 23, no. 3/4, 2014, pp. 11-22.
The paper presents the modified method of the text lines separation in the handwritten manuscripts. Such an approach is required for the medieval text analysis, where multiple text lines overlap and are written at different angles. The proposed approach consists in dividing the bounding boxes into smaller components based on the points of the character curves intersection. The method considers the askew text lines, producing non-rectangular zones between the neighboring lines.
document analysis, unconstrained handwriting, Hough transform, text line detection, connected component analysis, histogram analysis.
EBMBDT: Effective Block Matching Based Denoising Technique using Dual Tree Complex Wavelet Transform
MGV vol. 23, no. 3/4, 2014, pp. 23-41.
In processing and investigation of digital image denoising of images is hence very important. In this paper, we propose a Hybrid de-noising technique by using Dual Tree Complex Wavelet Transform (DTCWT) and Block Matching Algorithm (BMA). DTCWT and BMA is a method to identify the noisy pixel information and remove the noise in the image. The noisy image is given as input at first. Then, bring together the comparable image blocks into the load. Afterwards Complex Wavelet Transform (CWT) is applied to each block in the group. The analytic filters are made use of by CWT, i.e. their real and imaginary parts from the Hilbert Transform (HT) pair, defending magnitude-phase representation, shift invariance, and no aliasing. After that, adaptive thresholding is applied to enhance the image in which the denoising result is visually far superior. The proposed method has been compared with our previous de-noising technique with Gaussian and salt-pepper noise. From the results, we can conclude that the proposed de-noising technique have shown better values in the performance analysis.
image denoising, Complex Wavelet Transform (CWT), dual tree CWT, block matching, soft thresholding.
Syntactic Pattern Recognition of ECG for Diagnostic Justification
MGV vol. 23, no. 3/4, 2014, pp. 43-55.
A novel hybrid structural-parametric model for ECG diagnostic justification is
presented in the paper. In order to distinguish between specific
subclasses of heart dysfunction phenomena both grammars and automata
are enhanced with a formalism of dynamic programming. It allows one
to construct a system, which is feasible for aiding a process of
teaching and evaluating medical students' diagnostic reasoning in
the area of electrocardiography.
syntactic pattern recognition, ECG analysis, diagnostic justification.
Siudak M., Rokita P.:
A Survey of Passive 3D Reconstruction Methods on the Basis of More than One Image
MGV vol. 23, no. 3/4, 2014, pp. 57-117.
The research on the 3D scene reconstruction on the basis of its images and video recordings has been in progress for many years. As a result there is a number of methods concerning how to manage the reconstruction problem. This article's goal is to present the most important methods of reconstruction including stereo vision, shape from motion, shape from defocus, shape form silhouettes. shape from photo-consistency. All the algorithms explained in this article can be used on images taken with casual cameras in an ordinary illuminated scene (passive methods).
3D reconstruction, stereo vision, shape from motion, shape from defocus, shape from silhouettes, shape from photo-consistency, shape from X.
Brož P., Zemek M., Kolingerová I., Szkandera J.:
Dynamic Path Planning with Regular Triangulations
MGV vol. 23, no. 3/4, 2014, pp. 119-142.
Path planning is a well known problem that has been extensively studied in many scientific disciplines. In general, it defines a task of finding a path between two given spots in an abstract environment so that the path satisfies certain criterion of optimality. Although there are many methods solving this objective, they usually assume the examined space does not change in runtime. Modern applications, however, do not have to meet these requirements, especially in case of virtual reality or computer games. Therefore, we propose a general model for real-time path planning in dynamic environment where the obstacles can nondeterministically appear, disappear, change the position, orientation or even shape. The model uses a triangulation for dynamic space subdivision among bounding spheres of the obstacles and a heuristic algorithm to repair an already found path after any change of the scene. The presented solution is the first one using regular triangulation. At the price of the suboptimal result, it provides an efficient and fast way to plan a path with the maximal clearance among the moving and changing obstacles. In comparison to raster based techniques and methods using the Delaunay triangulation (Voronoi diagram), it requires less time to preprocess and generates paths with a larger clearance.
path planning, path finding, motion planning, virtual reality, robotics, proteins, suboptimality, gaps filling.
MGV vol. 23, no. 3/4, 2014, pp. 143-144.