This work quantitatively evaluates the effects induced by susceptibility characteristics of materials commonly used in dental practice on the quality of head MR images in a clinical 1.5T device. The proposed evaluation procedure measures the image artifacts induced by susceptibility in MR images by providing an index consistent with the global degradation as perceived by the experts. Susceptibility artifacts were evaluated in a near-clinical setup, using a phantom with susceptibility and geometric characteristics similar to that of a human head. We tested different dentist materials, called PAL Keramit, Ti6Al4V-ELI, Keramit NP, ILOR F, Zirconia and used different clinical MR acquisition sequences, such as “classical” SE and fast, gradient, and diffusion sequences. The evaluation is designed as a matching process between reference and artifacts affected images recording the same scene. The extent of the degradation induced by susceptibility is then measured in terms of similarity with the corresponding reference image. The matching process involves a multimodal registration task and the use an adequate similarity index psychophysically validated, based on correlation coefficient. The proposed analyses are integrated within a computer-supported procedure that interactively guides the users in the different phases of the evaluation method. 2-Dimensional and 3-dimensional indexes are used for each material and each acquisition sequence. From these, we drew a ranking of the materials, averaging the results obtained. Zirconia and ILOR F appear to be the best choice from the susceptibility artefacts point of view, followed, in order, by PAL Keramit, Ti6Al4V-ELI and Keramit NP.
In this work a fully automatic algorithm to detect brain tumors by using symmetry analysis is proposed. In
recent years a great effort of the research in field of medical imaging was focused on brain tumors segmentation.
The quantitative analysis of MRI brain tumor allows to obtain useful key indicators of disease progression.
The complex problem of segmenting tumor in MRI can be successfully addressed by considering modular and
multi-step approaches mimicking the human visual inspection process. The tumor detection is often an essential
preliminary phase to solvethe segmentation problem successfully. In visual analysis of the MRI, the first
step of the experts cognitive process, is the detection of an anomaly respect the normal tissue, whatever its
nature. An healthy brain has a strong sagittal symmetry, that is weakened by the presence of tumor. The
comparison between the healthy and ill hemisphere, considering that tumors are generally not symmetrically
placed in both hemispheres, was used to detect the anomaly. A clustering method based on energy minimization
through Graph-Cut is applied on the volume computed as a difference between the left hemisphere and
the right hemisphere mirrored across the symmetry plane. Differential analysis involves the loss the knowledge
of the tumor side. Through an histogram analysis the ill hemisphere is recognized. Many experiments
are performed to assess the performance of the detection strategy on MRI volumes in presence of tumors varied
in terms of shapes positions and intensity levels. The experiments showed good results also in complex situations.
Performance comparison of functional Magnetic Resonance Imaging (fMRI) software tools is a very difficult task. In
this paper, a framework for comparison of fMRI analysis results obtained with different software packages is proposed.
An objective evaluation is possible only after pre-processing steps that normalize input data in a standard domain.
Segmentation and registration algorithms are implemented in order to classify voxels belonging to brain or not, and to
find the non rigid transformation that best aligns the volume under inspection with a standard one. Through the
definitions of intersection and union of fuzzy logic an index was defined which quantify information overlap between
Statistical Parametrical Maps (SPMs). Direct comparison between fMRI results can only highlight differences. In order
to assess the best result, an index that represents the goodness of the activation detection is required. The transformation
of the activation map in a standard domain allows the use of a functional Atlas for labeling the active voxels. For each
functional area the Activation Weighted Index (AWI) that identifies the mean activation level of whole area was defined.
By means of this brief, but comprehensive description, it is easy to find a metric for the objective evaluation of a fMRI
analysis tools. Trough the first evaluation method the situations where the SPMs are inconsistent were identified. The
result of AWI analysis suggest which tool has higher sensitivity and specificity. The proposed method seems a valid
evaluation tool when applied to an adequate number of patients.
In computer vision, stereoscopic image analysis is a well-known technique capable of extracting the third (vertical) dimension. Starting from this knowledge, the Remote Sensing (RS) community has spent increasing efforts on the exploitation of Ikonos one-meter resolution stereo imagery for high accuracy 3D surface modelling and elevation data extraction. In previous works our team investigated the potential of neural adaptive learning to solve the correspondence problem in the presence of occlusions. In this paper we present an experimental evaluation of an improved version of the neural based stereo matching method when applied to Ikonos one-meter resolution stereo images affected by occlusion problems. Disparity maps generated with the proposed approach are compared with those obtained by an alternative stereo matching algorithm implemented in a (non-)commercial image processing software toolbox. To compare competing disparity maps, quality metrics recommended by the evaluation methodology proposed by Scharstein and Szelinski (2002, IJCV, 47, 7-42) are adopted.
Hyperspectral imaging is becoming an important analytical tool for generating land-use map. High dimensionality in hyperspectral remote sensing data, on one hand, provides us with more potential discrimination power for classification tasks. On the other hand, the classification performance improves up to a limited point as additional features are added, and then deteriorates due to the limited number of training samples. Proceeding from these considerations, the present work is aimed to systematically evaluate the robustness of novel classification techniques in classifying hyperspectral data under the twofold condition of high dimensionality and minimal training. We consider in the study a neural adaptive model based on Multi Layer Perceptron (MLP). Accuracy has been evaluated experimentally, classifying MIVIS Hyperspectral data to identify different typology of vegetation in Ticino Regional Park. A performance analysis has been conducted comparing the novel approach with Support Vector Machine and conventional statistical and neural techniques. The adaptive model shows advantages especially when mixed data are presented to the classifiers in combination with minimal training conditions.
In this paper, we propose a method able to fuse spectral information with spatial contextual information in order to solve “operationally” classification problem. The salient aspect of the method is the integration of heterogeneous data within a Multi-Layer Perceptron model. Spatial and spectral relationships are not explicitly formalized in an attempt to limit design and computational complexity; raw data are instead presented directly as input to the neural network classifier. The method in particular addresses new open problems in processing hyperspectral and high resolution data finding solution for multisource analysis. Experimental results in real domain show this fusing approach is able to produce accurate classification. The method in fact is able to handle the problem of a volumetric mixture typical of natural forest ecosystems identifying the different surfaces present under the tree canopy. The understory map, produced by the neural classification method, was used as input to the inversion of radiative transfer models that show a significant increase in the retrieval of important biophysical vegetation parameter.
Contextual classification methods, which require the extraction of complex spatial information over a range of scales, from fine details in local areas to large features that extend across the image, are necessary in many remote sensing image classification studies. This work presents a supervised adaptive object recognition model which integrates scale-space filtering techniques for feature extraction within a neural classification procedure based on multilayer perceptron (MLP). The salient aspect of the model is the integration within the back-propagation learning task of the search of the most adequate filter parameters. The experimental evaluation of the method has been conducted coping with object recognition in high-resolution remote sensing imagery. To investigate whether the strategy can be considered an alternative to conventional procedures the results were compared with those obtained by a well known contextual classification scheme.
In order to move towards a more adequate classification methodology one issue that has received particular attention within the remote sensing community is the development of soft classification models in alternative to conventional hard classification techniques. In soft classification, pattern indeterminacy must be connected with different forms of uncertainty such as vagueness, ambiguity, resulting in gradual strength of membership to classes. The work is focused on the use of soft classification techniques for production of soft maps in which grades of membership to classes are the final, meaningful outputs. When soft land cover maps are generated, grades of membership are correlated to the percentages of coverage; when maps specifying more abstract themes are generated grades have to represent the human natural approximation with which patterns matches with cognitive categories. Despite the availability of several soft classification techniques, soft thematic mapping has not being very often employed and the majority of classifications are still based on hard paradigms and maps are presented in discrete form. Significant problems in the use of these techniques limit their diffusion. The aim of this paper is to analyze the above limitations in an attempt of contributing to their overcoming.
The aim of the work is to propose a methodology for spatial/spectral analysis of urban patterns using neural network. To address the problem of spectral ambiguity and spatial complexity related to built-up patterns a two-stage classification procedure based on Multi-Layer Perceptron, is proposed. The first stage is devoted to generate discriminating features for problematic patterns by a supervised soft classification It uses a moving window to evaluate the neighbouring influences during the classification. The spatial relationships among the window pixels to be classified are not explicitly formalised, but the corresponding window is directly presented as input to the neural network classifier. The generated features are used in the second stage for complete land cover mapping. For an experimental evaluation the strategy has been applied to the classification of natural colour aerial photographs acquired over heterogeneous landscape, including urban patterns, and characterised by high spatial resolution and low spectral information. The proposed methodology for the extraction of urban patterns proved to be accurate and robust besides transferable.
Land cover-mapping gives base for complicated tasks and high accuracy maps are necessary for reliable global estimations. Land cover mapping involves classification; its accuracy is often affected by mixture presence, which increases with pixel size. Using hard classification approach mixed pixels are source of errors because are treated as pure ones and obtained maps describe scene as made up by mosaic of homogeneous areas. Soft classifications, computing partial belongings of pixels to several categories, are useful tools for dealing with mixture. Two soft classifiers, one based on fuzzy-statistical and one on fuzzy neural network approach, are applied to the classification of NOAA images for snow cover estimation. Results are compared with the traditional hard classifier maximum likelihood. The analysis shows that accuracy of hard classifiers is greatly affected by increasing of pixel size. Soft classifiers perform better accuracy then hard classifier in areal estimation. Particularly fuzzy-statistical classifier gives better results then fuzzy neural network but it requires mixture information that fuzzy neural network does not need. Fuzzy neural network results the best tool to classify low resolution images for the evaluation of snow covered area as it performs the best balancing between minimal requested ground truth and high accuracy.
Within the soft classification context, the vagueness conveyed by the grades of membership in classes leads us to conceive classification statements as less exclusive than in conventional hard classification, and to compare them in the light of more relaxed, flexible conditions, which results in degrees of matching. This paper proposes a new evaluation method which uses fuzzy set theory to extend the applicability of the traditional error matrix method to the evaluation of soft classifiers. It is designed to cope with those situations in which classification and/or reference data are expressed in multimembership form and the grades of membership represent different levels of approximation to intrinsically vague classes. To verify the applicability of the method we conducted a remote sensing study on a highly complex real scene of the Venice lagoon (Italy). Alternative evaluation procedures, such as the traditional confusion matrix and the Standard errors of estimate, have been developed for this application in order to demonstrate the value and the advantages of the proposed measures as compared with other approaches.
KEYWORDS: Fuzzy logic, Probability theory, Data modeling, Performance modeling, Remote sensing, Chemical elements, Transparency, Digital imaging, Neurons, Neural networks
This paper presents a novel neural model based on back- propagation for fuzzy Dempster-Shafer (FDS) classifiers. The salient aspect of the approach is the integration within a neuro-fuzzy system of knowledge structures and inferences for evidential reasoning based on Dempster-Shafer theory. In this context the learning task may be formulated as the search the most adequate 'ingredients' of the fuzzy and Dempster-Shafer frameworks such as the fuzzy aggregation operators for fusing data from different sources and focal elements and basic probability assignments for describing the contributions of evidence in the inference scheme. The new neural model allows to establish a complete correspondence between connectionist elements and fuzzy and Dempster-Shafer ingredients ensuring both a high level of interpretability and transparency and high performances in classification. A network-to-rule translation procedure is allowed for extracting Fuzzy Dempster-Shafer classification rules from the structure of the trained network. To evaluate the performances in real domains where the conditions of lack of specificity in data are prevalent, the proposed model has been applied to a multisource remote sensing classification problem. The numerical results are shown here and compared with those obtained by symbolic FDS and pure neuro-fuzzy classification procedure.
This paper presents a hybrid strategy for the classification of multisource remote sensing images basing on a knowledge representation framework which integrates fuzzy logic and Dempster-Shafer theory and is capable of dealing with possibilistic and credibilistic forms of uncertainty in an unified way. Within the strategy, the salient, innovative aspect here proposed is the use of a novel neural network model for refinement of fuzzy Dempster-Shafer classification rules. The approach has been evaluated by developing real- world applications in the field of water vulnerability assessment and fire risk assessment. Numerical results obtained show that classification benefit from the integration of neural and symbolic frameworks.
This paper reports on an experimental study designed for the in-depth investigation of how a supervised neuro-fuzzy classifier evaluates partial membership in land cover classes. The system is based on the Fuzzy Multilayer Perceptron model proposed by Pal and Mitra to which modifications in distance measures adopted for computing gradual membership to fuzzy class are introduced. During the training phase supervised learning is used to assign output class membership to pure training vectors (full membership to one land cover class); the model supports a procedure to automatically compute fuzzy output membership values for mixed training pixels. The classifier has been evaluated by conducting two experiments. The first employed simulated tests images which include pure and mixed pixels of known geometry and radiometry. The second experiment was conducted on a highly complex real scene of the Venice lagoon (Italy) where water and wetland merge into one another, at sub-pixel level. Accuracy of the results produced by the classifier was evaluated and compared using evaluation tools specifically defined and implemented to extend conventional descriptive and analytical statistical estimators to the case of multi-membership in classes. Results obtained demonstrated in the specific context of mixed pixels that the classification benefits from the integration of neural and fuzzy techniques.
Mixed pixels, which do not follow a known statistical distribution that could be parameterized, are a major source of inconvenience in classification of remote sensing images. This paper reports on an experimental study designed for the in-depth investigation of how and why two neuro-fuzzy classification schemes, whose properties are complementary, estimate sub-pixel land cover composition from remotely sensed data. The first classifier is based on the fuzzy multilayer perceptron proposed by Pal and Mitra: the second classifier consists of a two-stage hybrid (TSH) learning scheme whose unsupervised first stage is based on the fully self- organizing simplified adaptive resonance theory clustering network proposed by Baraldi. Results of the two neuro-fuzzy classifiers are assessed by means of specific evaluation tools designed to extend conventional descriptive and analytical statistical estimators to the case of multi-membership in classes. When a synthetic data set consisting of pure and mixed pixels is processed by the two neuro-fuzzy classifiers, experimental result show that: i) the two neuro- fuzzy classifiers perform better than the traditional MLP; ii) classification accuracies of the two neuro-fuzzy classifiers are comparable; and iii) the TSH classifier requires to train less background knowledge than FMLP.
This paper presents a multistrategy fuzzy learning method to the generation and refinement of multisource remote sensing classification rules. The learning procedure uses theoretical knowledge in the form of fuzzy production rules and a set of training examples, or pixels, assigned to fuzzy classes to developed a method for accurately classifying pixels not seen during training. The strategy is organized to preserve the advantages of direct elicitation techniques and empirical learning strategies while avoiding the disadvantages these present when used as monostrategy learning method. The performance of the methodology has been evaluated applying it to the actual environmental problem of fire risk mapping in Mediterranean areas, using an approach in which information describing risk factors are mainly extracted, by means of classification procedures, from satellite remotely sensed images. Results achieved, quantitatively and qualitatively evaluated by experts, proves that the method proposed provides adequate solutions for multiple feature evaluation and accurate discrimination between coexisting borderline cases, which generally are main problems when dealing with multisource remote sensing classification tasks.
In this study we propose the application of a fuzzy hybrid methodology for the classification of wetlands in the Venice lagoon: one of the most delicate examples of these types of ecosystems in the world. The identification of wetlands in these transitional areas is not a trivial task, since they are characterized by mixed signatures, depending on the amount of water, bare soil and vegetation components mainly present in the ground pixel. On the other hand, the importance of the maintaining of wetland extents by the use of remote sensing data justifies new efforts in order to increase result reliability, overtaking those obtained by traditional classification techniques. In this work, a fuzzy hybrid methodology has been applied in a specific area of the Venice lagoon, by using Landsat Thematic Mapper images and a set of color aerial photographs, at a higher geometric resolution, taken simultaneously with the satellite images classification results have been judged by experts a reliable basis for further multisource data analyses and accurate mapping procedure.
Our objective was to develop a knowledge-based strategy for the classification, considered a cognitive process, of multisource data including remote sensing images. The main feature of our approach is the use of fuzzy sets as the representation framework. This strategy supports two supervised image classification procedures, one based on a fuzzy statistical classifier and the other on a feed-forward fuzzy trained neural network. Approximate reasoning techniques, based on fuzzy production rules, are applied to model the multifactorial evaluation process in which results from the classification of remote-sensing images are integrated with other data. An example of multisource remote-sensing data classification applied in fire prevention is presented together with numerical results and an experimental verification of the approach.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.