Some Information Geometric Aspects of Cyber Security by Face Recognition.

Secure user access to devices and datasets is widely enabled by fingerprint or face recognition. Organization of the necessarily large secure digital object datasets, with objects having content that may consist of images, text, video or audio, involves efficient classification and feature retrieval processing. This usually will require multidimensional methods applicable to data that is represented through a family of probability distributions. Then information geometry is an appropriate context in which to provide for such analytic work, whether with maximum likelihood fitted distributions or empirical frequency distributions. The important provision is of a natural geometric measure structure on families of probability distributions by representing them as Riemannian manifolds. Then the distributions are points lying in this geometrical manifold, different features can be identified and dissimilarities computed, so that neighbourhoods of objects nearby a given example object can be constructed. This can reveal clustering and projections onto smaller eigen-subspaces which can make comparisons easier to interpret. Geodesic distances can be used as a natural dissimilarity metric applied over data described by probability distributions. Exploring this property, we propose a new face recognition method which scores dissimilarities between face images by multiplying geodesic distance approximations between 3-variate RGB Gaussians representative of colour face images, and also obtaining joint probabilities. The experimental results show that this new method is more successful in recognition rates than published comparative state-of-the-art methods.

An Adaptive Face Tracker with Application in Yawning Detection.

In this work, we propose an adaptive face tracking scheme that compensates for possible face tracking errors during its operation. The proposed scheme is equipped with a tracking divergence estimate, which allows to detect early and minimize the face tracking errors, so the tracked face is not missed indefinitely. When the estimated face tracking error increases, a resyncing mechanism based on Constrained Local Models (CLM) is activated to reduce the tracking errors by re-estimating the tracked facial features' locations (e.g., facial landmarks). To improve the Constrained Local Model (CLM) feature search mechanism, a Weighted-CLM (W-CLM) is proposed and used in resyncing. The performance of the proposed face tracking method is evaluated in the challenging context of driver monitoring using yawning detection and talking video datasets. Furthermore, an improvement in a yawning detection scheme is proposed. Experiments suggest that our proposed face tracking scheme can obtain a better performance than comparable state-of-the-art face tracking methods and can be successfully applied in yawning detection.

Identifying the most relevant tablet regions in the image detection of counterfeit medicines.

This paper proposes a novel image-based approach to detect counterfeit medicines and identify the most relevant regions of the tablet in the task of classification. Images of medicine tablets undergo an initial pre-processing step which (i) removes the background to find the region of interest, (ii) clusters individual pixels into super-pixels, and (iii) extracts features containing color and texture information. The classification relying on Support Vector Machine (SVM) defines the class the respective image will be inserted into. The task of identifying the relevant regions of the tablets for counterfeiting detection is performed using the concept of support vectors, generating a heat map that indicates the regions that contribute the most to the classification purpose. Two datasets containing images of authentic and counterfeit tablets of Cialis and Viagra were used to validate our propositions, achieving correct classification rates of 100% on both datasets. Regarding the task of identifying the most relevant regions, our proposition outperformed the traditional LIME (Local Interpretable Model-agnostic Explanations) method by yielding more robust explanations.

Interactive modeling and evaluation of tumor growth.

This paper addresses the need to quantify tumor growth and detect changes as this information is relevant to manage the patient treatment and to aid biotechnological efforts to cure cancer (Silva et al. 2008). An interactive tumor segmentation technique is used to recover the shape and size of tumors without imposing shape constraints. This segmentation algorithm provides good convergence, is robust to the initialization conditions, and requires simple and intuitive user interactions. A parametric approach to model tumor growth analytically is proposed in this paper. The preliminary experimental results are encouraging. The segmentation method is shown to be robust and simple to use, even in situations where the tumor boundary definition is challenging. Also, the experiments indicate that the proposed model potentially can be used to extrapolate the available data and help predict the tumor size (assuming unconstrained growth). Additionally, the proposed method potentially can provide a quantitative reference to compare the tumor shrinkage rate in cancer treatments.

Phase-adaptive superresolution of mammographic images using complex wavelets.

This correspondence describes a new superresolution approach for enhancing the resolution of mammographic images using complex wavelet frequency information. This method allows regions of interest of a mammographic image to be viewed in enhanced resolution while reducing the patient exposure to radiation. The proposed method exploits the structural characteristics of breast tissues being imaged and produces higher resolution mammographic images with sufficient visual fidelity that fine image details can be discriminated more easily. In our approach, the superresolution problem is formulated as a constrained optimization problem using a third-order Markov prior model and adapts the priors based on the phase variations of the low-resolution mammographic images. Experimental results indicate the proposed method is more effective at preserving the visual information when compared with existing resolution enhancement methods.

A morphological approach for the fovea location in color fundus images.

This paper presents a novel method for the detection of the fovea center in color fundus images. The method was evaluated using a set of 89 images from the DIARETDB1 project, which contains images presenting normal and pathological situations. Using the Mean Absolute Distance (MAD) as a metric, we report 7.37+/-8.89 (mean +/- standard deviation) detection performance for the fovea center which represents an improvement in comparison to other state-of-the-art methods in the literature.

Lossless and near-lossless digital angiography coding using a two-stage motion compensation approach.

This paper presents a two-stage motion compensation coding scheme for image sequences in hemodynamics. The first stage of the proposed method implements motion compensation, and the second stage corrects local pixel intensity distortions with a context adaptive linear predictor. The proposed method is robust to the local intensity distortions and the noise that often degrades these image sequences, providing lossless and near-lossless quality. Our experiments with lossless compression of 12bits/pixel studies indicate that, potentially, our approach can perform 3.8%, 2% and 1.6% better than JPEG-2000, JPEG-LS and the method proposed by Scharcanski [1], respectively. The performance tends to improve for near-lossless compression. Therefore, this work presents experimental evidence that for coding image sequences in hemodynamics, an adequate motion compensation scheme can be more efficient than the still-image coding methods often used nowadays.

Denoising and enhancing digital mammographic images for visual screening.

Dense regions in digital mammographic images are usually noisy and have low contrast, and their visual screening is difficult. This paper describes a new method for mammographic image noise suppression and enhancement, which can be effective particularly for screening image dense regions. Initially, the image is preprocessed to improve its local contrast and the discrimination of subtle details. Next, image noise suppression and edge enhancement are performed based on the wavelet transform. At each resolution, coefficients associated with noise are modelled by Gaussian random variables; coefficients associated with edges are modelled by Generalized Laplacian random variables, and a shrinkage function is assembled based on posterior probabilities. The shrinkage functions at consecutive scales are combined, and then applied to the wavelets coefficients. Given a resolution of analysis, the image denoising process is adaptive (i.e. does not require further parameter adjustments), and the selection of a gain factor provides the desired detail enhancement. The enhancement function was designed to avoid introducing artifacts in the enhancement process, which is essential in mammographic image analysis. Our preliminary results indicate that our method allows to enhance local contrast, and detect microcalcifications and other suspicious structures in situations where their detection would be difficult otherwise. Compared to other approaches, our method requires less parameter adjustments by the user.

A framework for medical visual information exchange on the web.

The web has become such an extensive health information repository in the world that it is increasingly difficult to search for relevant medical information. Most medical information available on the web is not peer reviewed, and is retrieved imprecisely by current web search mechanisms (i.e. based on keywords). This paper presents the MedISeek metadata model that allows one to describe medical visual information (i.e. medical images) of different modalities, including their properties, components, relationships and authorship. The model uses the web architecture and supports the international classification of diseases and related health problems (i.e. ICD-10). An RDF schema (Resource Description Framework (RDF), http://www.w3.org/RDF/.) derived from this metadata model is integrated to each medical image, and specifies the semantics of each property in the image. Thus, relevant information can be extracted directly from the images, and data integrity is better preserved in the web. A prototype, presented here, has been built to validate the metadata model, and the mechanism for medical visual information exchange on the web. Our preliminary experimental results indicate that authorized users of our system have been able to describe, store and retrieve medical images and their associated diagnostic information.

Lung nodule segmentation in chest computed tomography using a novel background estimation method.

BACKGROUND: Lung cancer results in the highest number of cancer deaths worldwide. The segmentation of lung nodules is an important task in computer systems to help physicians differentiate malignant lesions from benign lesions. However, it has already been observed that this may be a difficult task, especially when nodules are connected to an anatomical structure. METHODS: This paper proposes a method to estimate the background of the nodule area and how this estimation is used to facilitate the segmentation task. RESULTS: Our experiments indicate more than 99% of accuracy with less than 1% of false positive rate (FPR). CONCLUSIONS: The proposed methods achieved better results than a state-of-the-art approach, indicating potential to be used in medical image processing systems.

Automatic framework for extraction and characterization of wetting front propagation using tomographic image sequences of water infiltrated soils.

This paper presents a new automatic framework for extracting and characterizing the dynamic shape of the 3D wetting front and its propagation, based in a sequence of tomographic images acquired as water (moisture) infiltrates in unsaturated soils. To the best of the authors' knowledge, the shape of the 3D wetting front and its propagation and progress over time has not been previously produced as a whole by methods in existing literature. The proposed automatic framework is composed two important and integrated modules: i) extraction of the 3D wetting front, and ii) characterization and description of the 3D wetting front to obtain important information about infiltration process. The 3D wetting front surface is segmented from 3D CT imagery provided as input via a 3D stochastic region merging strategy using quadric-regressed bilateral space-scale representations. Based on the 3D segmentation results, the normal directions at local curvature maxima of the wetting front surface are computed for 3D images of soil moisture, and its propagation is analyzed at the local directions in sites of maximal water adsorption, and described using histograms of curvature changes over time in response to sample saturation. These curvature change descriptors provide indirect measurements of moisture infiltration in soils, and soil saturation. Results using a field tomograph equipment specific for soil studies are encouraging, and suggest that the proposed automatic framework can be applied to estimate the infiltration of water in soils in 3D and in time.

Adaptive image denoising using scale and space consistency.

This paper proposes a new method for image denoising with edge preservation, based on image multiresolution decomposition by a redundant wavelet transform. In our approach, edges are implicitly located and preserved in the wavelet domain, whilst image noise is filtered out. At each resolution level, the image edges are estimated by gradient magnitudes (obtained from the wavelet coefficients), which are modeled probabilistically, and a shrinkage function is assembled based on the model obtained. Joint use of space and scale consistency is applied for better preservation of edges. The shrinkage functions are combined to preserve edges that appear simultaneously at several resolutions, and geometric constraints are applied to preserve edges that are not isolated. The proposed technique produces a filtered version of the original image, where homogeneous regions appear separated by well-defined edges. Possible applications include image presegmentation, and image denoising.

A coarse-to-fine approach for segmenting melanocytic skin lesions in standard camera images.

Melanoma is a type of malignant melanocytic skin lesion, and it is among the most life threatening existing cancers if not treated at an early stage. Computer-aided prescreening systems for melanocytic skin lesions is a recent trend to detect malignant melanocytic skin lesions in their early stages, and lesion segmentation is an important initial processing step. A good definition of the lesion area and its border is very important for discriminating between benign and malignant cases. In this paper, we propose to segment melanocytic skin lesions using a sequence of steps. We start by pre-segmenting the skin lesion, creating a new image representation (channel) where the lesion features are more evident. This new channel is thresholded, and the lesion border pre-detection is refined using an active-contours algorithm followed by morphological operations. Our experimental results based on a publicly available dataset suggest that our method potentially can be more accurate than comparable state-of-the-art methods proposed in literature.

Hysteroscopy video summarization and browsing by estimating the physician's attention on video segments.

Specialists often need to browse through libraries containing many diagnostic hysteroscopy videos searching for similar cases, or even to review the video of one particular case. Video searching and browsing can be used in many situations, like in case-based diagnosis when videos of previously diagnosed cases are compared, in case referrals, in reviewing the patient records, as well as for supporting medical research (e.g. in human reproduction). However, in terms of visual content, diagnostic hysteroscopy videos contain lots of information, but only a reduced number of frames are actually useful for diagnosis/prognosis purposes. In order to facilitate the browsing task, we propose in this paper a technique for estimating the clinical relevance of video segments in diagnostic hysteroscopies. Basically, the proposed technique associates clinical relevance with the attention attracted by a diagnostic hysteroscopy video segment during the video acquisition (i.e. during the diagnostic hysteroscopy conducted by a specialist). We show that the resulting video summary allows specialists to browse the video contents nonlinearly, while avoiding spending time on spurious visual information. In this work, we review state-of-art methods for summarizing general videos and how they apply to diagnostic hysteroscopy videos (considering their specific characteristics), and conclude that our proposed method contributes to the field with a summarization and representation method specific for video hysteroscopies. The experimental results indicate that our method tends to produce compact video summaries without discarding clinically relevant information.

Automated prescreening of pigmented skin lesions using standard cameras.

This paper describes a new method for classifying pigmented skin lesions as benign or malignant. The skin lesion images are acquired with standard cameras, and our method can be used in telemedicine by non-specialists. Each acquired image undergoes a sequence of processing steps, namely: (1) preprocessing, where shading effects are attenuated; (2) segmentation, where a 3-channel image representation is generated and later used to distinguish between lesion and healthy skin areas; (3) feature extraction, where a quantitative representation for the lesion area is generated; and (4) lesion classification, producing an estimate if the lesion is benign or malignant (melanoma). Our method was tested on two publicly available datasets of pigmented skin lesion images. The preliminary experimental results are promising, and suggest that our method can achieve a classification accuracy of 96.71%, which is significantly better than the accuracy of comparable methods available in the literature.

Fisher-Tippett region-merging approach to transrectal ultrasound prostate lesion segmentation.

In this paper, a computerized approach to segmenting prostate lesions in transrectal ultrasound (TRUS) images is presented. The segmentation of prostate lesions from TRUS images is very challenging due to issues, such as poor contrast, low SNRs, and irregular shape variations. To address these issues, a novel approach is employed to segment the lesions from the surrounding prostate, where region merging is performed via a region-merging likelihood function based on regional statistics, as well as Fisher-Tippett statistics. Experimental results using TRUS prostate images demonstrate that the proposed Fisher-Tippett region-merging approach achieves more accurate segmentation of prostate lesions when compared to other segmentation methods.

Automatic skin lesion segmentation via iterative stochastic region merging.

An automatic method for segmenting skin lesions in conventional macroscopic images is presented. The images are acquired with conventional cameras, without the use of a dermoscope. Automatic segmentation of skin lesions from macroscopic images is a very challenging problem due to factors such as illumination variations, irregular structural and color variations, the presence of hair, as well as the occurrence of multiple unhealthy skin regions. To address these factors, a novel iterative stochastic region-merging approach is employed to segment the regions corresponding to skin lesions from the macroscopic images, where stochastic region merging is initialized first on a pixel level, and subsequently on a region level until convergence. A region merging likelihood function based on the regional statistics is introduced to determine the merger of regions in a stochastic manner. Experimental results show that the proposed system achieves overall segmentation error of under 10% for skin lesions in macroscopic images, which is lower than that achieved by existing methods.

Fovea center detection based on the retina anatomy and mathematical morphology.

In this work, we present a new fovea center detection method for color eye fundus images. This method is based on known anatomical constraints on the relative locations of retina structures, and mathematical morphology. The detection of this anatomical feature is a prerequisite for the computer aided diagnosis of several retinal diseases, such as Diabetic Macular Edema. The proposed method is adaptive to local illumination changes, and it is robust to local disturbances introduced by pathologies in digital color eye fundus images (e.g. exudates). Our experimental results using the DRIVE image database indicate that our method is able to detect the fovea center in 37 out of 37 images (i.e. with a success rate of 100%). Using the DIARETDB1 database, our method was able to detect the fovea center in 92.13% of all tested cases (i.e. in 82 out of 89 images). These results indicate that our approach potentially can achieve a better performance than comparable methods proposed in the literature.

An ICA-based method for the segmentation of pigmented skin lesions in macroscopic images.

Segmentation is an important step in computer-aided diagnostic systems for pigmented skin lesions, since that a good definition of the lesion area and its boundary at the image is very important to distinguish benign from malignant cases. In this paper a new skin lesion segmentation method is proposed. This method uses Independent Component Analysis to locate skin lesions in the image, and this location information is further refined by a Level-set segmentation method. Our method was evaluated in 141 images and achieved an average segmentation error of 16.55%, lower than the results for comparable state-of-the-art methods proposed in literature.

Video segmentation based on motion coherence of particles in a video sequence.

This work describes an approach for object-oriented video segmentation based on motion coherence. Using a tracking process based on adaptively sampled points (namely, particles), 2-D motion patterns are identified with an ensemble clustering approach. Particles are clustered to obtain a pixel-wise segmentation in space and time domains. The segmentation result is mapped to an image spatio-temporal feature space. Thus, the different constituent parts of the scene that move coherently along the video sequence are mapped to volumes in this spatio-temporal space. These volumes make the redundancy in the temporal sense more explicit, leading to potential gains in video coding applications. The proposed solution is robust and more generic than similar approaches for 2-D video segmentation found in the literature. In order to illustrate the potential advantages of using the proposed motion segmentation approach in video coding applications, the PSNR of the temporal predictions and the entropies of prediction errors obtained in our experiments are presented, and compared with other methods. Our experiments with real and synthetic sequences suggest that our method also could be used in other image processing and computer vision tasks, besides video coding, such as video information retrieval and video understanding.