Renzo Perfetti

Retinal Blood Vessel Segmentation Using Line Operators and Support Vector Classification

In the framework of computer-aided diagnosis of eye diseases, retinal vessel segmentation based on line operators is proposed. A line detector, previously used in mammography, is applied to the green channel of the retinal image. It is based on the evaluation of the average grey level along lines of fixed length passing through the target pixel at different orientations. Two segmentation methods are considered. The first uses the basic line detector whose response is thresholded to obtain unsupervised pixel classification. As a further development, we employ two orthogonal line detectors along with the grey level of the target pixel to construct a feature vector for supervised classification using a support vector machine. The effectiveness of both methods is demonstrated through receiver operating characteristic analysis on two publicly available databases of color fundus images.

Cellular Neural Networks With Virtual Template Expansion for Retinal Vessel Segmentation

A retinal vessel segmentation method based on cellular neural networks (CNNs) is proposed. The CNN design is characterized by a virtual template expansion obtained through a multistep operation. It is based on linear space-invariant 3times3 templates and can be realized using existing chip prototypes like the ACE16K. The proposed design is capable of performing vessel segmentation within a short computation time. It was tested on a publicly available database of color images of the retina, using receiver operating characteristic curves. The simulation results show good performance comparable with that of the best existing methods

Rigorous Network and Full-Wave Electromagnetic Modeling of Wireless Power Transfer Links

The proposed approach makes use of full-wave electromagnetic modeling of wireless power transfer links in order to derive the network characterization, e.g., in terms of scattering or impedance matrix. Once the latter is obtained, we show that network theory provides the appropriate matching impedances for achieving either maximum efficiency, maximum power on the load, or conjugate matching. The proposed approach also permits to derive closed-form matching networks and expressions for power and efficiency. An example of full-wave numerical electromagnetic modeling of a wireless power transfer link is presented. The selected example, which is similar to the experiment published by Kurs et al., shows the importance of selecting the appropriate source/load impedance for obtaining significative results.

Neural associative memory storing gray-coded gray-scale images

We present a neural associative memory storing gray-scale images. The proposed approach is based on a suitable decomposition of the gray-scale image into gray-coded binary images, stored in brain-state-in-a-box-type binary neural networks. Both learning and recall can be implemented by parallel computation, with time saving. The learning algorithm, used to store the binary images, guarantees asymptotic stability of the stored patterns, low computational cost, and control of the weights precision. Some design examples and computer simulations are presented to show the effectiveness of the proposed method.

Event based transcription system for polyphonic piano music

Music transcription consists in transforming the musical content of audio data into a symbolic representation. The objective of this study is to investigate a transcription system for polyphonic piano, triggered by events corresponding to the played notes. The proposed method focuses on note events and their main characteristics: the attack instant, the pitch and the final instant. Onset detection exploits a binary time-frequency representation of the audio signal. Note classification and offset detection are based on constant Q transform (CQT) and support vector machines (SVMs). We present a collection of experiments using synthesized MIDI files and piano recordings, and compare the results with existing approaches.

Associative Memory Design Using Support Vector Machines

The relation existing between support vector machines (SVMs) and recurrent associative memories is investigated. The design of associative memories based on the generalized brain-state-in-a-box (GBSB) neural model is formulated as a set of independent classification tasks which can be efficiently solved by standard software packages for SVM learning. Some properties of the networks designed in this way are evidenced, like the fact that surprisingly they follow a generalized Hebbs law. The performance of the SVM approach is compared to existing methods with nonsymmetric connections, by some design examples

Recurrent Correlation Associative Memories: A Feature Space Perspective

In this paper, we analyze a model of recurrent kernel associative memory (RKAM) recently proposed by Garcia and Moreno. We show that this model consists in a kernelization of the recurrent correlation associative memory (RCAM) of Chiueh and Goodman. In particular, using an exponential kernel, we obtain a generalization of the well-known exponential correlation associative memory (ECAM), while using a polynomial kernel, we obtain a generalization of higher order Hopfield networks with Hebbian weights. We show that the RKAM can outperform the aforementioned associative memory models, becoming equivalent to them when a dominance condition is fulfilled by the kernel matrix. To ascertain the dominance condition, we propose a statistical measure which can be easily computed from the probability distribution of the interpattern Hamming distance or directly estimated from the memory vectors. The RKAM can be used below saturation to realize associative memories with reduced dynamic range with respect to the ECAM and with reduced number of synaptic coefficients with respect to higher order Hopfield networks.

Quasi-Lagrangian Neural Network for Convex Quadratic Optimization

A new neural network for convex quadratic optimization is presented in this brief. The proposed network can handle both equality and inequality constraints, as well as bound constraints on the optimization variables. It is based on the Lagrangian approach, but exploits a partial dual method in order to keep the number of variables at minimum. The dynamic evolution is globally convergent and the steady-state solutions satisfy the necessary and sufficient conditions of optimality. The circuit implementation is simpler with respect to existing solutions for the same class of problems. The validity of the proposed approach is verified through some simulation examples.

Frequency domain criteria for cellular neural networks

A dynamical system is called globally asymptotically stable if it has a unique equilibrium point which attracts every trajectory in state space. As a consequence its steady state response is insensitive to initial conditions and then depends only on the input. In this paper some criteria are presented for the global asymptotic stability of cellular neural networks (CNNs), concerning both discrete-time and continuous-time dynamics. The proposed criteria represent necessary and sufficient conditions that can easily be checked by computing the discrete Fourier transform of the template elements. For this reason they have been called frequency domain stability criteria. These criteria provide milder constraints on the template coefficients than required in existing results for general recurrent neural network models.

Associative memory design for 256 gray-level images using a multilayer neural network

A design procedure is presented for neural associative memories storing gray-scale images. It is an evolution of a previous work based on the decomposition of the image with 2/sup L/ gray levels into L binary patterns, stored in L uncoupled neural networks. In this letter, an L-layer neural network is proposed with both intralayer and interlayer connections. The connections between different layers introduce interactions among all the neurons, increasing the recall performance with respect to the uncoupled case. In particular, the proposed network can store images with the commonly used number of 256 gray levels instead of 16, as in the previous approach.