Avoiding staff removal stage in optical music recognition: application to scores written in white mensural notation

Staff detection and removal is one of the most important issues in optical music recognition (OMR) tasks since common approaches for symbol detection and classification are based on this process. Due to its complexity, staff detection and removal is often inaccurate, leading to a great number of errors in posterior stages. For this reason, a new approach that avoids this stage is proposed in this paper, which is expected to overcome these drawbacks. Our approach is put into practice in a case of study focused on scores written in white mensural notation. Symbol detection is performed by using the vertical projection of the staves. The cross-correlation operator for template matching is used at the classification stage. The goodness of our proposal is shown in an experiment in which our proposal attains an extraction rate of 96 % and a classification rate of 92 %, on average. The results found have reinforced the idea of pursuing a new research line in OMR systems without the need of the removal of staff lines.

Human-computer interaction for optical music recognition tasks

The need to digitise music scores has led to the development of Optical Music Recognition (OMR) tools. Unfortunately, the performance of these systems is still far from providing acceptable results. This situation forces the user to be involved in the process due to the need of correcting the mistakes made during recognition. However, this correction is performed over the output of the system, so these interventions are not exploited to improve the performance of the recognition. This work sets the scenario in which human and machine interact to accurately complete the OMR task with the least possible effort for the user.

Chebanov law and Vakar formula in mathematical models of complex systems

Ecological models written in a mathematical language L(M) or model language, with a given style or methodology can be considered as a text. It is possible to apply statistical linguistic laws and the experimental results demonstrate that the behaviour of a mathematical model is the same of any literary text of any natural language. A text has the following characteristics: (a) the variables, its transformed functions and parameters are the lexic units or LUN of ecological models; (b) the syllables are constituted by a LUN, or a chain of them, separated by operating or ordering LUNs; (c) the flow equations are words; and (d) the distribution of words (LUM and CLUN) according to their lengths is based on a Poisson distribution, the Chebanov's law. It is founded on Vakar's formula, that is calculated likewise the linguistic entropy for L(M). We will apply these ideas over practical examples using MARIOLA model. In this paper it will be studied the problem of the lengths of the simple lexic units composed lexic units and words of text models, expressing these lengths in number of the primitive symbols, and syllables. The use of these linguistic laws renders it possible to indicate the degree of information given by an ecological model.

Bayesian models for finding and grouping junctions

In this paper, we propose two Bayesian methods for detecting and grouping junctions. Our junction detection method evolves from the Kona approach, and it is based on a competitive greedy procedure inspired in the region competition method. Then, junction grouping is accomplished by finding connecting paths between pairs of junctions. Path searching is performed by applying a Bayesian A* algorithm that has been recently proposed. Both methods are efficient and robust, and they are tested with synthetic and real images.

Realistic limits for subpixel movement detection

Object tracking with subpixel accuracy is of fundamental importance in many fields since it provides optimal performance at relatively low cost. Although there are many theoretical proposals that lead to resolution increments of several orders of magnitude, in practice this resolution is limited by the imaging systems. In this paper we propose and demonstrate through simple numerical models a realistic limit for subpixel accuracy. The final result is that maximum achievable resolution enhancement is connected with the dynamic range of the image, i.e., the detection limit is 1/2∧(nr.bits). The results here presented may aid in proper design of superresolution experiments in microscopy, surveillance, defense, and other fields.

Deformable templates for tracking and analysis of intravascular ultrasound sequences

Deformable Template models are first applied to track the inner wall of coronary arteries in intravascular ultrasound sequences, mainly in the assistance to angioplasty surgery. A circular template is used for initializing an elliptical deformable model to track wall deformation when inflating a balloon placed at the tip of the catheter. We define a new energy function for driving the behavior of the template and we test its robustness both in real and synthetic images. Finally we introduce a framework for learning and recognizing spatio-temporal geometric constraints based on Principal Component Analysis (eigenconstraints).

Image processing for safety assessment in Civil Engineering

Behaviour analysis of construction safety systems is of fundamental importance to avoid accidental injuries. Traditionally, measurements of dynamic actions in Civil Engineering have been done through accelerometers, but high-speed cameras and image processing techniques can play an important role in this area. Here, we propose using morphological image filtering and Hough transform on high-speed video sequence as tools for dynamic measurements on that field. The presented method is applied to obtain the trajectory and acceleration of a cylindrical ballast falling from a building and trapped by a thread net. Results show that safety recommendations given in construction codes can be potentially dangerous for workers.

Recognition of online handwritten music symbols

Paper submitted to MML 2013, 6th International Workshop on Machine Learning and Music, Prague, September 23, 2013.

Integration of different models in the design of chemical processes: Application to the design of a power plant

With advances in the synthesis and design of chemical processes there is an increasing need for more complex mathematical models with which to screen the alternatives that constitute accurate and reliable process models. Despite the wide availability of sophisticated tools for simulation, optimization and synthesis of chemical processes, the user is frequently interested in using the ‘best available model’. However, in practice, these models are usually little more than a black box with a rigid input–output structure. In this paper we propose to tackle all these models using generalized disjunctive programming to capture the numerical characteristics of each model (in equation form, modular, noisy, etc.) and to deal with each of them according to their individual characteristics. The result is a hybrid modular–equation based approach that allows synthesizing complex processes using different models in a robust and reliable way. The capabilities of the proposed approach are discussed with a case study: the design of a utility system power plant that has been decomposed into its constitutive elements, each treated differently numerically. And finally, numerical results and conclusions are presented.

Saint Mathew Law and Bonini Paradox in Textual Theory of Complex Models

The mathematical models of the complex reality are texts belonging to a certain literature that is written in a semi-formal language, denominated L(MT) by the authors whose laws linguistic mathematics have been previously defined. This text possesses linguistic entropy that is the reflection of the physical entropy of the processes of real world that said text describes. Through the temperature of information defined by Mandelbrot, the authors begin a text-reality thermodynamic theory that drives to the existence of information attractors, or highly structured point, settling down a heterogeneity of the space text, the same one that of ontologic space, completing the well-known law of Saint Mathew, of the General Theory of Systems and formulated by Margalef saying: “To the one that has more he will be given, and to the one that doesn't have he will even be removed it little that it possesses.

Method for targetless tracking subpixel in-plane movements

We present a targetless motion tracking method for detecting planar movements with subpixel accuracy. This method is based on the computation and tracking of the intersection of two nonparallel straight-line segments in the image of a moving object in a scene. The method is simple and easy to implement because no complex structures have to be detected. It has been tested and validated using a lab experiment consisting of a vibrating object that was recorded with a high-speed camera working at 1000 fps. We managed to track displacements with an accuracy of hundredths of pixel or even of thousandths of pixel in the case of tracking harmonic vibrations. The method is widely applicable because it can be used for distance measuring amplitude and frequency of vibrations with a vision system.

A Novel Prediction Method for Early Recognition of Global Human Behaviour in Image Sequences

Human behaviour recognition has been, and still remains, a challenging problem that involves different areas of computational intelligence. The automated understanding of people activities from video sequences is an open research topic in which the computer vision and pattern recognition areas have made big efforts. In this paper, the problem is studied from a prediction point of view. We propose a novel method able to early detect behaviour using a small portion of the input, in addition to the capabilities of it to predict behaviour from new inputs. Specifically, we propose a predictive method based on a simple representation of trajectories of a person in the scene which allows a high level understanding of the global human behaviour. The representation of the trajectory is used as a descriptor of the activity of the individual. The descriptors are used as a cue of a classification stage for pattern recognition purposes. Classifiers are trained using the trajectory representation of the complete sequence. However, partial sequences are processed to evaluate the early prediction capabilities having a specific observation time of the scene. The experiments have been carried out using the three different dataset of the CAVIAR database taken into account the behaviour of an individual. Additionally, different classic classifiers have been used for experimentation in order to evaluate the robustness of the proposal. Results confirm the high accuracy of the proposal on the early recognition of people behaviours.

A connectionist computational method for face recognition

In this work, a modified version of the elastic bunch graph matching (EBGM) algorithm for face recognition is introduced. First, faces are detected by using a fuzzy skin detector based on the RGB color space. Then, the fiducial points for the facial graph are extracted automatically by adjusting a grid of points to the result of an edge detector. After that, the position of the nodes, their relation with their neighbors and their Gabor jets are calculated in order to obtain the feature vector defining each face. A self-organizing map (SOM) framework is shown afterwards. Thus, the calculation of the winning neuron and the recognition process are performed by using a similarity function that takes into account both the geometric and texture information of the facial graph. The set of experiments carried out for our SOM-EBGM method shows the accuracy of our proposal when compared with other state-of the-art methods.

A three-dimensional representation method for noisy point clouds based on growing self-organizing maps accelerated on GPUs

The research described in this thesis was motivated by the need of a robust model capable of representing 3D data obtained with 3D sensors, which are inherently noisy. In addition, time constraints have to be considered as these sensors are capable of providing a 3D data stream in real time. This thesis proposed the use of Self-Organizing Maps (SOMs) as a 3D representation model. In particular, we proposed the use of the Growing Neural Gas (GNG) network, which has been successfully used for clustering, pattern recognition and topology representation of multi-dimensional data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models, without considering time constraints. It is proposed a hardware implementation leveraging the computing power of modern GPUs, which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). The proposed methods were applied to different problem and applications in the area of computer vision such as the recognition and localization of objects, visual surveillance or 3D reconstruction.

Contributions to 3D Data Registration and Representation

Nowadays, new computers generation provides a high performance that enables to build computationally expensive computer vision applications applied to mobile robotics. Building a map of the environment is a common task of a robot and is an essential part to allow the robots to move through these environments. Traditionally, mobile robots used a combination of several sensors from different technologies. Lasers, sonars and contact sensors have been typically used in any mobile robotic architecture, however color cameras are an important sensor due to we want the robots to use the same information that humans to sense and move through the different environments. Color cameras are cheap and flexible but a lot of work need to be done to give robots enough visual understanding of the scenes. Computer vision algorithms are computational complex problems but nowadays robots have access to different and powerful architectures that can be used for mobile robotics purposes. The advent of low-cost RGB-D sensors like Microsoft Kinect which provide 3D colored point clouds at high frame rates made the computer vision even more relevant in the mobile robotics field. The combination of visual and 3D data allows the systems to use both computer vision and 3D processing and therefore to be aware of more details of the surrounding environment. The research described in this thesis was motivated by the need of scene mapping. Being aware of the surrounding environment is a key feature in many mobile robotics applications from simple robotic navigation to complex surveillance applications. In addition, the acquisition of a 3D model of the scenes is useful in many areas as video games scene modeling where well-known places are reconstructed and added to game systems or advertising where once you get the 3D model of one room the system can add furniture pieces using augmented reality techniques. In this thesis we perform an experimental study of the state-of-the-art registration methods to find which one fits better to our scene mapping purposes. Different methods are tested and analyzed on different scene distributions of visual and geometry appearance. In addition, this thesis proposes two methods for 3d data compression and representation of 3D maps. Our 3D representation proposal is based on the use of Growing Neural Gas (GNG) method. This Self-Organizing Maps (SOMs) has been successfully used for clustering, pattern recognition and topology representation of various kind of data. Until now, Self-Organizing Maps have been primarily computed offline and their application in 3D data has mainly focused on free noise models without considering time constraints. Self-organising neural models have the ability to provide a good representation of the input space. In particular, the Growing Neural Gas (GNG) is a suitable model because of its flexibility, rapid adaptation and excellent quality of representation. However, this type of learning is time consuming, specially for high-dimensional input data. Since real applications often work under time constraints, it is necessary to adapt the learning process in order to complete it in a predefined time. This thesis proposes a hardware implementation leveraging the computing power of modern GPUs which takes advantage of a new paradigm coined as General-Purpose Computing on Graphics Processing Units (GPGPU). Our proposed geometrical 3D compression method seeks to reduce the 3D information using plane detection as basic structure to compress the data. This is due to our target environments are man-made and therefore there are a lot of points that belong to a plane surface. Our proposed method is able to get good compression results in those man-made scenarios. The detected and compressed planes can be also used in other applications as surface reconstruction or plane-based registration algorithms. Finally, we have also demonstrated the goodness of the GPU technologies getting a high performance implementation of a CAD/CAM common technique called Virtual Digitizing.