Explicit Segmentation Research Articles

Are objects required for object-files? Roles of segmentation and spatiotemporal continuity in computing object persistence

Two central tasks of visual processing are (1) to segment undifferentiated retinal images into discrete objects, and (2) to represent those objects as the same persisting individuals over time and motion. Here we explore the interaction of these two types of processing in the context of object files—mid-level visual representations that “stick” to moving objects on the basis of spatiotemporal properties. Object files can be revealed by object-specific preview benefits (OSPBs), wherein a “preview” of information on a moving object speeds the recognition of that information at a later point when it appears again on the same object (compared to when it reappears on a different moving object), beyond display-wide priming. Here we explore the degree of segmentation required to establish object files in the first place. Surprisingly, we find that no explicit segmentation is required until after the previews disappear, when using purely motion-defined objects (consisting of random elements on a random background). Moreover, OSPBs are observed in such displays even after moderate (but not long) delays between the offset of the preview information and the onset of the motion. These effects indicate that object files can be established without initial static segmentation cues, so long as there is spatiotemporal continuity between the previews and the eventual appearance of the objects. We also find that top-down strategies can sometimes mimic OSPBs, but that these strategies can be eliminated by novel manipulations. We discuss how these results alter our understanding of the nature of object files, and also why researchers must take care to distinguish “true OSPBs” from “illusory OSPBs”.

Vesselness-based 2D–3D registration of the coronary arteries

Robust and accurate automated co-registration of the coronary arteries in 3D CTA and 2D X-ray angiography during percutaneous coronary interventions (PCI), in order to present a fused visualization. A novel vesselness-based similarity measure was developed, that avoids an explicit segmentation of the X-ray image. A stochastic optimizer searches the optimal registration using the similarity measure. Both simulated data and clinical data were used to investigate the accuracy and capture range of the proposed method. The experiments show that the proposed method outperforms the iterative closest point method in terms of accuracy (average residual error of 0.42 mm vs. 1.44 mm) and capture range (average 71.1 mm/20.3 degrees vs. 14.1 mm/5.2 degrees ). The proposed method has proven to be accurate and the capture range is ample for usage in PCI. Especially the absence of an explicit segmentation of the interventionally acquired X-ray images considerably aids the robustness of the method.

FACE AUTHENTICATION USING RECOGNITION-BY-PARTS, BOOSTING AND TRANSDUCTION

The paper describes an integrated recognition-by-parts architecture for reliable and robust face recognition. Reliability and robustness are characteristic of the ability to deploy full-fledged and operational biometric engines, and handling adverse image conditions that include among others uncooperative subjects, occlusion, and temporal variability, respectively. The architecture proposed is model-free and non-parametric. The conceptual framework draws support from discriminative methods using likelihood ratios. At the conceptual level it links forensics and biometrics, while at the implementation level it links the Bayesian framework and statistical learning theory (SLT). Layered categorization starts with face detection using implicit rather than explicit segmentation. It proceeds with face authentication that involves feature selection of local patch instances including dimensionality reduction, exemplar-based clustering of patches into parts, and data fusion for matching using boosting driven by parts that play the role of weak-learners. Face authentication shares the same implementation with face detection. The implementation, driven by transduction, employs proximity and typicality (ranking) realized using strangeness and p-values, respectively. The feasibility and reliability of the proposed architecture are illustrated using FRGC data. The paper concludes with suggestions for augmenting and enhancing the scope and utility of the proposed architecture.

White matter tract visualization using properties of termination coordinate eigenmaps

We present a fast and informative technique for determining colors that differentiate white matter pathways generated by deterministic diffusion tensor tractography (DTT) based on streamline termination coordinate (TC) locations in native space. In particular, terminations coordinates are mapped to a standard stereotactic space and colors are generated using a fast eigenmapping approach designed to provide a single eigenvector representing both TCs. This eigenvector is then colored by mapping the vector x-coordinate to the red channel, the y-coordinate to the green channel, and the z-coordinate to the blue channel. This visualization technique generates a TC color (TCC) map and represents a novel technique for white matter anatomical visualization that does not require explicit white matter pathway segmentation. TCC maps of the pons, cerebral peduncle, thalamus, arcuate fasciculus, and corpus callosum are demonstrated and shown to correspond well with known white matter anatomy. Furthermore, TCC maps are consistent between subjects and may be modulated by the eigenvalue of the TCC map or streamline length to provide additional visual contrast. Finally, these color maps may be generated from deterministic or probabilistic tractography data that are computed from either diffusion tensor or high angular resolution diffusion-weighted MRI acquisitions.

Linguistics and face recognition

We describe in this paper a novel biometric methodology for face recognition suitable to address pose, illumination, and expression (PIE) image variability, temporal change, flexible matching, and last but not least occlusion and disguise that are usually referred to as denial and deception. The adverse conditions listed above affect the scope and performance of biometric analysis vis-à-vis both training and testing. The conceptual framework proposed here draws support from discriminative methods using likelihood ratios. At the conceptual level it links forensics and biometrics, while at the implementation level it links the Bayesian framework and statistical learning theory. As many of the concerns listed usually affect only parts of the face, a non-parametric recognition-by-part approach is advanced here for the purpose of reliable face recognition. Recognition-by-parts facilitates authentication because it does not seek for explicit invariance. Instead, it handles variability using component-based configurations that are flexible enough to compensate among others for limited pose changes, if any, and limited occlusion and disguise. The recognition-by-parts approach proposed here supports incremental and progressive processing. It is similar in nature to modern linguistics and practical intelligence with the emphasis on semantics and pragmatics. Layered categorization starts with face detection using implicit rather than explicit segmentation. It proceeds with face authentication that involves feature selection of local patch instances including dimensionality reduction, exemplar-based clustering of patches into parts, and data fusion for matching using boosting driven by parts that play the role of weak learners. The implementation, driven by transduction, employs proximity and typicality (ranking) realized using strangeness and random deficiency p-values, respectively. The feasibility and reliability of the proposed architecture has been validated using FERET and FRGC data. The paper concludes with suggestions for augmenting and enhancing the scope and utility of the recognition-by-parts architecture.

What type of computer-assisted exercise supports young less skilled spellers in resolving problems in open and closed syllable words?

Dutch bisyllabic words containing open and closed syllables are particularly difficult to spell for children. What kind of support in spelling exercises improves the spelling of these words the most? Two extensions of a commonly used dictation exercise were tested: less skilled spellers in grade 2 (n = 50; 7 years and 10 months) either received explicit syllabic segmentation cues or received spelling cues by means of a visual preview. Comparisons between pre-, post-, and retention tests of spelling skill showed that extra syllabic cues did not show a significant improvement beyond normal spelling dictation and that visual preview was most effective as compared to the other types of training. The findings suggest that word-specific knowledge can effectively be improved by exposure to the correct letter pattern during exercises in spelling and seems to result in lasting improvement of word-specific orthographic representations, at least for 5 weeks.

A Robust Docking Strategy for a Mobile Robot Using Flow Field Divergence

We present a robust strategy for docking a mobile robot in close proximity with an upright surface using optical flow field divergence and proportional feedback control. Unlike previous approaches, we achieve this without the need for explicit segmentation of features in the image, and using complete gradient-based optical flow estimation (i.e., no affine models) in the optical flow computation. A key contribution is the development of an algorithm to compute the flow field divergence, or time-to-contact, in a manner that is robust to small rotations of the robot during ego-motion. This is done by tracking the focus of expansion of the flow field and using this to compensate for ego rotation of the image. The control law used is a simple proportional feedback, using the unfiltered flow field divergence as an input, for a dynamic vehicle model. Closed-loop stability analysis of docking under the proposed feedback is provided. Performance of the flow field divergence algorithm is demonstrated using offboard natural image sequences, and the performance of the closed-loop system is experimentally demonstrated by control of a mobile robot approaching a wall.

Discovering Phone Patterns in Spoken Utterances by Non-Negative Matrix Factorization

We present a technique to automatically discover the (word-sized) phone patterns that are present in speech utterances. These patterns are learnt from a set of phone lattices generated from the utterances. Just like children acquiring language, our system does not have prior information on what the meaningful patterns are. By applying the non-negative matrix factorization algorithm to a fixed-length high-dimensional vector representation of the speech utterances, a decomposition in terms of additive units is obtained. We illustrate that these units correspond to words in case of a small vocabulary task. Our result also raises questions about whether explicit segmentation and clustering are needed in an unsupervised learning context.

Virtual neuroendoscopy: MRI-based three-dimensional visualization of the cranial nerves in the posterior cranial fossa

This article presents the advances of three-dimensional (3D) virtual neuroendoscopy of the cranial nerves (CN) in the posterior fossa. Interactive 3D visualizations were generated and the anatomical landmarks, such as the root entry/exit zones (REZ) and cisternal segments of the CN were evaluated. Twenty patients (M:F, 6:14) with trigeminal neuralgia (TN) underwent MRI constructive interference in steady state (MRICISS) imaging and subsequent 3D visualization based on explicit segmentation of the MRICISS data and interactive evaluation with direct volume rendering including implicit segmentation. The 3D topography of the interesting CN V – X were evaluated with interactive and virtual neuroendoscopy. The anatomical landmarks of the CN V – X could be visualized in all 20 cases (100%). The systematic application of virtual neuroendoscopy could be realized in all patients for the non-invasive observation of the CN without any technical difficulties. Interactive 3D visualization using explicit and implicit techniques for segmentation, and 3D direct volume rendering is demonstrated to successfully identify 3D neurovascular relations in patients with trigeminal neuralgia. It has the ability to provide a useful tool for surgeons in the pre- and intraoperative evaluation of such cases.

Perception-based contrast enhancement of images

Study of contrast sensitivity of the human eye shows that our suprathreshold contrast sensitivity follows the Weber Law and, hence, increases proportionally with the increase in the mean local luminance. In this paper, we effectively apply this fact to design a contrast-enhancement method for images that improves the local image contrast by controlling the local image gradient with a single parameter. Unlike previous methods, we achieve this without explicit segmentation of the image, either in the spatial (multiscale) or frequency (multiresolution) domain. We pose the contrast enhancement as an optimization problem that maximizes the average local contrast of an image strictly constrained by a perceptual constraint derived directly from the Weber Law. We then propose a greedy heuristic, controlled by a single parameter, to approximate this optimization problem.

Using duration models to reduce fragmentation in audio segmentation

We investigate explicit segment duration models in addressing the problem of fragmentation in musical audio segmentation. The resulting probabilistic models are optimised using Markov Chain Monte Carlo methods; in particular, we introduce a modification to Wolff's algorithm to make it applicable to a segment classification model with an arbitrary duration prior. We apply this to a collection of pop songs, and show experimentally that the generated segmentations suffer much less from fragmentation than those produced by segmentation algorithms based on clustering, and are closer to an expert listener's annotations, as evaluated by two different performance measures.

Opacity Peeling for Direct Volume Rendering

Abstract The most important technique to visualize 3D scalar data, as they arise e.g. in medicine from tomographic measurement, is direct volume rendering. A transfer function maps the scalar values to optical properties which are used to solve the integral of light transport in participating media. Many medical data sets, especially MRI data, however, are difficult to visualize due to different tissue types being represented by the same scalar value. The main problem is that interesting structures will be occluded by less important structures because they share the same range of data values. Occlusion, however, is a view‐dependent problem and cannot be solved easily by transfer function design. This paper proposes a new method to display different entities inside the volume data in a single rendering pass. The proposed opacity peeling technique reveals structures in the data set that cannot be visualized directly by one‐or multi‐dimensional transfer functions without explicit segmentation. We also demonstrate real‐time implementations using texture mapping and multiple render targets. Categories and Subject Descriptors (according to ACM CCS): I.3.7 [Computer Graphics]: Three‐Dimensional Graphics and Realism

TU‐C‐ValA‐04: Deformable Registration Using Regularization That Accommodates Local Tissue Rigidity

Purpose: Existing methods for deformable image registration typically use homogeneous regularization to encourage global smoothness. Less work has been done to incorporate voxel‐level tissue‐specific elasticity information. Ignoring differences in elasticity can, however, result in non‐physiological registrations, such as bone warping. We propose an approach to incorporate tissue rigidity information using a spatial variant regularization. Method and Materials: Regularized image registration algorithms estimate the deformation by minimizing a cost function, consisting of a dis‐similarity metric and regularization. To account for tissue‐type‐dependent rigidity information, we incorporate into the cost function a non‐rigidity penalty: an integral of stiffness index for local deformation weighted by spatial variant regularization factor depending on tissue type. For CT data, a simple monotonic increasing function of the CT number is used as a rigidity index for local tissue type. A necessary and sufficient condition for stiff local deformation is derived, and the local non‐stiffness is measured by the deviation of local Jacobian from orthnormality using the Frobenius norm. Tensor B‐Splines are used to parameterize the deformation field. A multi‐resolution scheme and gradient‐based approach are applied for optimization. Performance was accessed by registering 3D thorax CT‐images obtained from different breathing phases. Results: Experiments with clinical data demonstrate higher accuracy for inhale‐exhale thorax CT registration with the proposed approach. We observe comparable intensity match as the unregularized approaches, but more physiologically reasonable results with respect to different tissue types; in particular bone warping phenomena is eliminated in general. Conclusion: This work provides a way to incorporate tissue‐type‐dependent information into deformable registration framework with regularization design. Inference from image intensity avoids explicit segmentation, and is robust to partial volume effect. Our formulation based on local Jacobian and Frobenius norm provides analytical expression for the regularization and its derivative. More physiological results are achieved with minor computation expense.Supported by NIH P01‐CA59827.

A 2-D/3-D model-based method to quantify the complexity of microvasculature imaged by in vivo multiphoton microscopy

This paper presents model-based information-theoretic methods to quantify the complexity of tumor microvasculature, taking into account shape, textural, and structural irregularities. The proposed techniques are completely automated, and are applicable to optical slices (3-D) or projection images (2-D). Improvements upon the prior literature include: (i) measuring local (vessel segment) as well as global (entire image) vascular complexity without requiring explicit segmentation or tracing; (ii) focusing on the vessel boundaries in the complexity estimate; and (iii) added robustness to image artifacts common to tumor microvasculature images. Vessels are modeled using a family of super-Gaussian functions that are based on the superquadric modeling primitive common in computer vision. The superquadric generalizes a simple ellipsoid by including shape parameters that allow it to approximate a cylinder with elliptical cross-sections (generalized cylinder). The super-Gaussian is obtained by composing a superquadric with an exponential function giving a form that is similar to a standard Gaussian function but with the ability to produce level sets that approximate generalized cylinders. Importantly, the super-Gaussian is continuous and differentiable so it can be fit to image data using robust non-linear regression. This fitting enables quantification of the intrinsic complexity of vessel data vis-a-vis the super-Gaussian model within a minimum message length (MML) framework. The resulting measures are expressed in units of information (bits). Synthetic and real-data examples are provided to illustrate the proposed measures.

A paradigm for controllable QoS-based medium access control in local and ad hoc wireless networks†

The carrier sense multiple access/ID countdown (CSMA/IC) is an emerging MAC protocol designed for multi-hop ad hoc wireless networks that differs from CSMA/CA. In this paper, we propose two techniques supporting differentiated service for different priority packets for CSMA/IC, differentiated fair ID countdown (DFIC) and controllable fair ID countdown (CFIC). DFIC supports absolute service differentiation among classes through the use of an explicit priority segment, while CFIC achieves prioritized access through assigning different waiting times for nodes to access the medium. Both of DFIC and CFIC can achieve fairness among nodes of same priority group. CFIC also achieves controllable relative throughout differentiation among different priority levels and can guarantee starvation-free access for all nodes.

A Strategy for Selecting Classes of Symbols from Classes of Graphemes in HMM-Based Handwritten Word Recognition

Este artigo descreve uma metodologia para seleção de classes de símbolos a partir de classesde grafemas em um sistema de reconhecimento de palavras manuscritas do extenso de cheques bancáriosbrasileiros baseado em HMM (Hidden Markov Models). Este artigo discute as definições de primitivas,grafemas e símbolos considerando um enfoque Global para o reconhecimento das palavras, o qual evita asegmentação das palavras em letras ou pseudo-letras utilizando HMM. Assim, a entrada para os modelosconsiste em uma descrição da palavra a partir de um alfabeto de símbolos gerados a partir dos grafemasextraídos das imagens das palavras, sendo esta a representação visível para o HMM. Portanto, a idéia éintroduzir uma conceituação de alto nível, tais como primitivas perceptivas (laços, ascendentes,descendentes, concavidades e convexidades) e fornecer um modo de retro-alimentação rápido e informativosobre a informação contida em cada classe de grafema, permitindo uma seleção de classes de símbolos. Oartigo apresenta o algoritmo com base na Informação Mútua (Mutual Information) e HMM, ambostrabalhando em um mesmo processo de avaliação. Os resultados experimentais demonstram que é possívelselecionar a partir de um conjunto “original” de grafemas (composto por 94 grafemas) um alfabeto desímbolos (composto por 29 símbolos). O artigo conclui que o poder discriminante dos grafemas é muitoimportante para a consolidação de um alfabeto de símbolos.

Morphological awareness in developmental dyslexia

This study examines morphological awareness in developmental dyslexia. While the poor phonological awareness of dyslexic children has been related to their difficulty in handling the alphabetical principle, less is known about their morphological awareness, which also plays an important part in reading development. The aim of this study was to analyze in more detail the implications of the phonological impairments of dyslexics in dealing with larger units of language such as morphemes. First, the performance of dyslexic children in a series of morphological tasks was compared with the performance of children matched on reading-level and chronological age. In all the tasks, the dyslexic group performed below the chronological age control group, suggesting that morphological awareness cannot be developed entirely independently of reading experience and/or phonological skills. Comparisons with the reading-age control group indicated that, while the dyslexic children were poorer in the morphemic segmentation tasks, they performed normally for their reading level in the sentence completion tasks. Furthermore, they produced more derived words in the production task. This suggests that phonological impairments prevent the explicit segmentation of affixes while allowing the development of productive morphological knowledge. A second study compared dyslexic subgroups defined by their degree of phonological impairment. Our results suggest that dyslexics develop a certain type of morphological knowledge which they use as a compensatory reading strategy.

Analysis and 3-dimensional visualization of neurovascular compression syndromes 1

Rationale and Objectives. Neurovascular compression syndromes are currently examined with 2-dimensional representations of tomographic volumes. To overcome this drawback, coarse segmentation followed by direct volume rendering of magnetic resonance (MR) data is introduced supporting a detailed 3-dimensional analysis of the related structures. Materials and Methods. This approach is based on MR-CISS (constructive interference in steady state) volumes providing the required high resolution to achieve an improved spatial understanding. In relation to the size of the involved nerves and vessels, an explicit segmentation is extremely difficult. Therefore, a semi-automatic preprocessing sequence was developed consisting of noise reduction, morphologic filtering, and volume growing. To delineate the target structures within the segmented and labeled subvolumes, interactive direct volume rendering was applied that allows delineating the target structures in the area of the cerebrospinal fluid with implicit segmentation based on predefined transfer functions assigning opacity and color values to the intensity values of the image data. For a further improved analysis, registration of the MR-CISS volumes with MR angiography is recommended to support differentiating vessels and nerves on the one side and arteries and veins on the other. Results. The presented method was applied in a consecutive series of 47 cases of different neurovascular compression syndromes, supporting the presurgical analysis of the image data. Additionally, the results were compared with the operative findings. Conclusion. Overall, this approach contributes significantly to an optimized 3-dimensional analysis and understanding of neurovascular compression syndromes. Based on the obtained results, it is of high value for the planning of surgery.

Fully automatic quantification of microarray image data.

DNA microarrays are now widely used to measure expression levels and DNA copy number in biological samples. Ratios of relative abundance of nucleic acids are derived from images of regular arrays of spots containing target genetic material to which fluorescently labeled samples are hybridized. Whereas there are a number of methods in use for the quantification of images, many of the software systems in wide use either encourage or require extensive human interaction at the level of individual spots on arrays. We present a fully automatic system for microarray image quantification. The system automatically locates both subarray grids and individual spots, requiring no user identification of any image coordinates. Ratios are computed based on explicit segmentation of each spot. On a typical image of 6000 spots, the entire process takes less than 20 sec. We present a quantitative assessment of performance on multiple replicates of genome-wide array-based comparative genomic hybridization experiments. By explicitly identifying the pixels in each spot, the system yields more accurate estimates of ratios than systems assuming spot circularity. The software, called, runs on Windows platforms and is available free of charge for academic use.

Rapid interactive 3-D imaging of the temporal bone with "direct volume rendering"

For the first time, the relatively new method of interactive direct volume rendering (dVR) allows for a fast and direct three-dimensional visualization of spiral CT data without any manual, explicit segmentation. This study was performed to prove whether dVR is capable of providing a meaningful three-dimensional visualization of the structures within the temporal bone. In ten patients a three-dimensional visualization of the structures of the inner and middle ear was performed from spiral CT data on a commercially available graphics workstation. The cochlea and semicircular canals were visualized in good quality in all patients. The ossicles and bony facial canal were visualized in good or fair quality in most cases. The time needed for the visualization of the data and all target structures was less than 15 min in all cases. Three-dimensional visualization of the structures within the temporal bone from high-resolution spiral CT data using dVR is easily performed in a very short time on standard graphics workstations. This allows integrating three-dimensional visualizations into routine clinical work.