Urinary Tract Infections (UTIs) are very common in women, babies and the elderly. The most frequent cause is a bacterium, called Escherichia coli, which usually lives in the digestive system and in the bowel. Infections can target the urethra, bladder or kidneys. Traditional analysis methods, based on human experts' evaluation, are typically used to diagnose UTIs, an error prone and lengthy process, whereas an early treatment of common pathologies is fundamental to prevent the infection spreading to kidneys. This paper presents an image based Automated Bacterial Load Estimator (ABLE) system for the urinoculture screening, that provides quick and traceable results for UTIs. Infections are accurately detected and the bacterial load is evaluated through image processing techniques. First, digital color images of the Petri dishes are automatically captured, and cleaned from noisily elements due to laboratory procedures, then specific spatial clustering algorithms are applied to isolate the colonies from the culture ground and, finally, an accurate evaluation of the infection severity is performed. A dataset of 499 urine samples has been used during the experiments and the obtained results are fully discussed. The ABLE system speeds up the analysis, grants repeatable results, contributes to the process standardization, and guarantees a significant cost reduction.

Accurate vessel detection in retinal images is an important and difficult task. Detection is made more challenging in pathological images with the presence of exudates and other abnormalities. In this paper, we present a new unsupervised vessel segmentation approach to address this problem. A novel inpainting filter, called neighborhood estimator before filling, is proposed to inpaint exudates in a way that nearby false positives are significantly reduced during vessel enhancement. Retinal vascular enhancement is achieved with a multiple-scale Hessian approach. Experimental results show that the proposed vessel segmentation method outperforms state-of-the-art algorithms reported in the recent literature, both visually and in terms of quantitative measurements, with overall mean accuracy of 95.62% on the STARE dataset and 95.81% on the HRF dataset.

One of the major sources of energy waste in wireless sensor networks (WSNs) is idle listening, that is, the cost of actively listening for potential packets. This article focuses on reducing idle-listening time via a dynamic duty-cycling technique which aims at optimizing the sleep interval between consecutive wake-ups. We considered a receiver-initiated MAC method for WSNs in which the sender waits for a beacon signal from the receiver before starting to transmit. Since each sender receives beacon signals from several nodes, the data are routed on multiple paths in a data collection network. In this context, we propose an optimization framework for minimizing the energy waste of the most power-hungry node of the network. To this aim, we first derive an analytic model that predicts nodes' energy consumption. Then, we use the model to derive a distributed optimization technique. Simulation results via NS-2 simulator are included to illustrate the accuracy of the model, and numerical results assess the validity of the proposed scheme.

One of the major sources of energy waste in a Wireless Sensor Network (WSN) is idle listening, i.e., the cost of actively listening for potential packets. This paper focuses on reducing the idle-listening time via a dynamic duty cycling technique which aims at optimizing the sleep interval between consecutive wakeups. We considered receiver-initiated MAC method for WSNs, in which the sender waits for a beacon signal from the receiver before starting to transmit. In this context, we propose an optimization framework for minimizing the energy waste of the most power hungry node of the network. To this aims, we first derive an analytic model that predicts nodes' energy consumption. Then, we use the model to derive an heuristic distributed optimization technique. Simulation results via NS-2 simulator are included to illustrate the accuracy of the model, and to assess the validity of the proposed scheme.

Automatic recognition of human activities is important for the development of next generation video-surveillance systems. In this paper we address the specific problem of automatically detecting violent interpersonal acts in monocular colour video streams. Unlikely previous approaches, only little knowledge is assumed about the acquisition setup and about the content of the acquired scenes. So the proposed approach is suitable in a wide range of practical cases. Reliability and general-purpose applicability is achieved by analysing low-level features (like the spatial-temporal behaviour of coloured stains), and by measuring some warping and motion parameters. In this way it is not necessary to extract accurate target silhouettes, that is a critical task because of occlusions and overcrowding that are typical during interpersonal contacts. A suitable index called maximum warping energy (MWE) has been defined to describe the localized spatial-temporal complexity of colour conformations. Our experiments show that aggressive activities give significantly higher MWE values if compared with safe actions like: walking, running, embracing or handshaking. So it is possible to distinguish violent acts from normal behaviours even in presence of many people and crowded environments. Homography is used to improve robustness by verifying the real targets nearness. False interactions because of perspective-induced occlusions are discarded.

Increased mobility and internationalization open new challenges to develop effective traffic monitoring and control systems. This is true for automatic license plate recognition architectures that, nowadays, must handle plates from different countries with different character sets and syntax. While much emphasis has been put on the license plate localization and segmentation, little attention has been devoted to the huge amount of samples that are needed to train the character recognition algorithms. Nevertheless, these samples are difficult to get when dealing with an international-wide scenario that involves many different countries and the related legislations. This paper reports a new algorithm for License Plate recognition, developed under a joint research funded by Autostrade per l'Italia S.p.A., the main Italian highways company. The research aimed at achieving improved recognition rates when dealing with vehicles coming from different European and nearby states. Extensive experimental tests have been performed on a database of about 7.000 images comprising License Plates picked up by portals spread nationally. The overall rate of correct classification is 98.1%.

Color is an important source of information for: image comparisons, retrieval, and analysis. Unfortunately, color is strongly affected by many factors and a suitable color recovery preprocessing step is necessary to fully exploit the power of chromatic features. This paper describes a new hybrid technique for color recovery, which gives improved performance even in presence of sensible environmental changes. The technique combines one of the most effective retinex algorithm (McCann99) with the gray-world transformation applied at multiple resolutions. A non linear post processing step is also proposed that improves the final color balance and range. Extensive experimental tests have been performed both on synthetic and real images, that confirm the robustness and the enhanced color recovery capability with respect to other on the edge techniques. The proposed method has been used in a real time system for the automatic recognition of those plates that denote vehicles for dangerous-goods transportation. Some results about this last system are reported in the paper.

This paper describes an automatic real-time video surveillance system, capable of autonomously learning and signaling anomalous activities of moving objects. To obtain these capabilities, an improved version of the altruistic vector quantization algorithm (AVQ) is proposed. The modified AVQ automatically evaluates the number of trajectory prototypes, and improves the representativeness of the prototypes themselves, so the visual events can be easily and accurately classified. Anomalous behaviors are detected if visual trajectories deviate from the self-learned representations of "typical" behaviors. The system has been implemented by means of standard PCs and TV cameras, and has been tested in many real outdoor contexts in different conditions (night and day). Currently it is used to monitor the storage areas of British Airways at the airport of Peretola (Florence, Italy), and some access gates of Autostrade per FItalia S.p.A. (the main Italian highways company). If the camera field-of-view is changed, the system automatically re-learns new "typical" behaviors and accurately detects anomalous events.

There are several models for lightness computation, as many are the retinex based theories about color constancy. This paper provides a new hybrid technique for color recovery, which combines one of the most effective retinex algorithm (McCann99) and the gray world transformation applied at multiple resolutions.. A novel post processing step is also presented that improves the final color balance and range. The experimental tests on synthetic and real images, confirm the algorithm robustness and the improved color recovery capability with respect to other on the edge algorithms.

This work describes the performance and the characteristics of a new algorithm for subpixel image classification, performed by means of a fully constrained least-squares estimator operated with a multi-resolution approach in the framework of the linear mixing model. The new algorithm takes advantage from processing the input data at two different spatial scales (resolutions), the coarser of which is obtained after image sub-sampling (filtering and decimation) that heavily mitigates the initial noise ampli- tude. Two successive data-processing steps compose the al- gorithm. Initially, the low-resolution data set is processed with a fully constrained least-squares operator and sub- pixel fractional abundances are estimated at low spatial resolution. These estimates are then utilised as constraints for classifying the high-resolution data set. Particularly the N high-resolution pixels, from whose average the coarse pixel just classified was computed, are unmixed simultane- ously, looking for the optimum of a cumulative least- squares cost-function summed over all the concerned high- resolution pixels. The added constraint imposes that for any end-member the high-resolution abundance equates on average (over the involved N pixels) that estimated at the less detailed spatial scale. In this way it is possible to appre- ciably reduce the impact of input noise on the output result. The paper thoroughly describes the structure and the mathematical properties of the new algorithm, and clearly proves its improved performance in terms of abundances' signal-to-noise ratio. Algorithm properties are investigated by processing natural and simulated hyperspectral image- data, which allowed us to accurately demonstrate the SNR gain provided by the algorithm.

We describe a system for automatic objects extraction and dynamic bitrate allocation in a second generation object based video coder, targeting surveillance sequences. We combine model-based statistical change detection with a multiresolution-based approach for object extraction. Masks are redefined at a block level resolution and refined to improve the coding quality exploiting spatio-temporal considerations. We propose a dynamic adaptation of the quantization step of the MPEG-4 coder, based on motion information of the extracted objects. The results outperform traditional frame based coders at very low bit-rates. The masks proposed dramatically improve the coding performance, even when compared to ideally extracted masks.

A new circle extraction algorithm based on possibilistic clustering is presented along with its application to automatic crater detection in remote sensing images. With respect to classical algorithms based on fuzzy shell-clustering, solutions are proposed to make circle extraction robust against noise and non-circular structures. The proposed algorithm operates by grouping edge pixels into connected subgroups, and by fitting a circle to each group through possibilistic clustering. Circles are refined through PCS clustering, and validated by means of geometrical considerations. The effectiveness of the proposed approach for crater detection is confirmed by experimental results.

The work presented in this article describes a tool for object tracking, notes insertion, and information retrieval, applicable to MPEG-2 sequences. Maximum compliance with the MPEG standard is sought, so the added information is transmitted as side information without affecting the actual video-audio stream as defined in the MPEG-2 standard. Additional processing is added to a standard sequence, allowing for automatic tracking of one object across different groups of pictures. Results show that the proposed algorithm is capable of tracking objects with a good degree of precision. Features are included to alert the human operator when objects disappear, or must be considered lost, due to an excessive change in their shape.

Applications of clustering and neural network techniques to channel equalization have revealed the classification nature of this problem. This paper illustrates an implementation of a global system for mobile communications (GSM) receiver in which channel equalization and demodulation are realized by means of the nearest neighbor (NN) classifier algorithm. The most important advantage in using such techniques is the significant reduction in terms of the computational complexity compared with the maximum likelihood sequence estimation (MLSE) equalizer. The proposed approach involves symbol-by-symbol interpretation and the knowledge of the channel is embedded in the mapping process of the received symbols over the symbols of the training sequence. This means that no explicit channel estimation need be carried out, either with correlative blocks or using neural networks thus speeding up the entire process. The performance of the proposed receiver, evaluated through a channel simulator for mobile radio communications, is compared with the results obtained by means of a 16-state Viterbi algorithm and other suboptimal receivers. It is shown that the presented algorithm increases the bit error rate (BER) compared with the MLSE demodulator, but the performance degradation, despite the simplicity of the receiver, is kept within the limits imposed by the GSM specifications.

A system devoted to ship traffic control in a harbour environment is proposed, where optic flow approach and monocular image sequences are used. In each frame the scene is segmented, moving and still objects are found, and the movement of each ship is completely tracked. Partial and/or total occlusions are correctly handled by means of suitable grouping algorithms. Quantitative motion estimation is obtained by an iterative procedure that extract precise 3D information from the monocular sequence. The implemented version of the system is able to monitor and control a harbour environment with a substantially low computational effort.

Clustering is commonly used in remote sensing image segmentation. Among the clustering techniques, pyramid-based methods generally provide better performance in discriminating among different cover classes if compared to global algorithms. When applied to single polarization synthetic aperture radar (SAR) data, though, such algorithms suffer from misinterpretation problems due to the mono-band nature of the images produced by these sensors. In this case an important feature to improve the segmentation is texture. This paper describes a wavelet-based fuzzy clustering algorithm which receives as input both the remotely sensed image and a texture image based on a fractal model, derived from the wavelet representation itself. The algorithm has been tested on X-SAR images, and the results demonstrate its potential usefulness.

We present a fast algorithm to extract a shadow model from a monocular colour scene exploiting the hue, luminosity, saturation (HLS) colour components. The method allows one to recover target shapes in diurnal scene for improved identification and it is based on the definition of a global bitmap model and a more particular strip bitmap model to identify shadow regions. Each pixel in the image is then classified as shadow or target by a comparison with these models.

This paper proposes a new algorithm which applies perceptual grouping to track discontinuous chains of symbols in digitized maps. The procedure is based on an artificial intelligence kernel that supervises three different auxiliary processes: the search strategy generation module, responsible for the strategy to scan pixels; the symbol detection module that extracts the recognized symbols; the cost function evaluation module that assigns a global quality index to each symbol by considering the whole course of the line. Selected Gestalt rules are used to optimize the grouping procedures.

The unsupervised detection of an unknown number of straight lines in digital imagery is addressed. Based on possibilistic clustering an algorithm is proposed which does not require any assumption about the number of straight lines present in the edge map. Three major modifications are introduced with respect to existing clustering-based algorithms: the use of possibilistic clustering; a more sophisticated analysis of the clusters, including the possibility of rejecting non linear clusters; a bottom up strategy to evaluate how many straight lines the image contains. The effectiveness of the proposed scheme is proved by validating it against real world imagery.

An efficient vanishing point detection algorithm for non-structured scenes is proposed. The technique relies on a voting scheme based on well-understood rules for the grouping of lines. Infinite distance vanishing points are previously detected by a basic algorithm to simplify the successive search.

When processing multidimensional remote sensing data, one of the main problem is the choice for the appropriate number of clusters; despite of the great number of good algorithms for clustering, each of them works properly only when the appropriate number of clusters is selected. As adaptive versions of the K-means, competitive learning (CL) algorithms also have a similar crucial problem; various efforts to improve the performance of CL were made with the introduction of frequency sensitive competitive learning (FSCL) and rival penalised competitive learning (RPCL). We present an improvement of the RPCL algorithm well adapted to work with every kind of real clustering data problems. The basic idea of this new algorithm is to introduce a competition also between the weights. The algorithm was tested on multiband images with different weights initial position, giving similar results.

In this comment, we report a difficulty with the-application of the possibilistic approach to fuzzy clustering (PCM) proposed by Keller and Krishnapuram (1993). In applying this algorithm we found that it has the undesirable tendency to produce coincidental clusters. Results illustrating this tendency are reported and a possible explanation for the PCM behavior is suggested.

The progress of digital electroencephalography gave rise to the problem of EEG data recording. In the paper a DPCM scheme for EEG signal compression is discussed. In particular the performance of a class of predictors based on recurrent neural networks is presented. The training strategy is accurately described and the results of a comparison with some other classical linear and static neural predictors are given. The proposed recurrent neural predictor demonstrates to be competitive with the others in offering good performance at a very low computational cost.

Modern manufacturing systems call for full-rate automated inspection of produced samples. A vision-based intelligent perception system (IPS) is presented making automated inspection of chicken meat feasible. The IPS analyzes RGB images framing the chickens after the slaughtering and plucking process and detects defects such as burns, hematomas and blisters, along with other relevant features. The vision module, which is the core of the system, operates by first extracting the chicken body from the background, then it segments the body into its anatomic subparts. Defective areas are identified by means of morphological reconstruction. Finally, defects are classified by comparing their features against the defect description contained in a reference database.

A system for coding video sequences at a low rate is presented. The system is very effective in coding sequences where motion is restricted to a not large area of each frame. Nevertheless knowledge based techniques are not used for not reducing the generalization power of the coding method. Techniques based on segmentation algorithms are used to encode both the displacement vector field and the prediction error image. Such techniques permit one to effectively distribute coding information in those areas of the image where it is required. Great care is given to a good estimation of motion of the scene objects: this is to reduce the amount of information to be coded in the prediction error image.>

The vector median filter has good filtering capabilities; nevertheless, its huge computational complexity significantly limits its practical usability. A vector median filter based on a fast approximation of the Euclidean norm is presented. The proposed algorithm couples computational and filtering effectiveness, and it is well suited for hardware implementation. Theoretical and experimental results regarding both approximation error and speed improvement prove the validity of the proposed algorithm.>

Digital high-definition TV (HDTV) signals are generally compressed to reduce transmission bandwidth requirements. A compression algorithm for the bit rate reduction of an HDTV image using the wavelet transform is presented. The major problems related to the transmission of a compressed HDTV signal are analyzed. Transmission is examined both on a noisy channel and an asynchronous transfer mode (ATM) network. The effects of channel noise on the reconstructed image are determined, and a solution to mitigate the degradation of the image quality is presented. A model for the output bit rate of the HDTV coder is derived and used to simulate the transmission of an ATM multiplexer so that the network's main performance parameters can be determined.>

The architecture of an intelligent perception system (IPS) is analyzed, and the main problems related to its practical implementation are discussed. Particular attention has been devoted to the data fusion function, which initiates the process and gives information on the actual situation with the associated uncertainties; the hypotheses function, which takes into consideration the uncertainties in the correlated data and creates the best explanations of the fused data; the option function, which creates various response alternatives for each hypothesis simulating the resulting effects; and the response function, which realizes the planned actions so producing new stimuli and initializing other processing cycles. The architecture of the IPS is presented.>

Scene analysis with processing of multiple frames is considered for automatic recognition and tracking of moving objects. The importance of taking into account information about the objects in the design of flexible systems is emphasized. This goal is reached through an object-oriented approach to problem-solving. It is shown that abstract data type and inheritance relationship definitions over real-world entities can be efficiently used for object classification purposes. This has been verified in a traffic monitoring application. An efficient algorithmic solution that satisfies the real-time constraints of the problem is proposed.>

Some special digital operators and recognition techniques are presented for digital image processing. Two complete digital systems are described. The first fast and relatively simple system uses non-linear smoothing and adaptive thresholding as a pre-processing and inertial invariant components to recognize moving objects. The second more complex system uses non-linear smoothing, edge detection and noise spike reduction as a pre-processing and FFT of the boundary distances from the centroid to recognize and track moving objects. Experiments of recognition and tracking of mechanical objects are reported.