Image Re-Ranking Acceleration on GPUs

Huge image collections are becoming available lately. In this scenario, the use of Content-Based Image Retrieval (CBIR) systems has emerged as a promising approach to support image searches. The objective of CBIR systems is to retrieve the most similar images in a collection, given a query image, by taking into account image visual properties such as texture, color, and shape. In these systems, the effectiveness of the retrieval process depends heavily on the accuracy of ranking approaches. Recently, re-ranking approaches have been proposed to improve the effectiveness of CBIR systems by taking into account the relationships among images. The re-ranking approaches consider the relationships among all images in a given dataset. These approaches typically demands a huge amount of computational power, which hampers its use in practical situations. On the other hand, these methods can be massively parallelized. In this paper, we propose to speedup the computation of the RL-Sim algorithm, a recently proposed image re-ranking approach, by using the computational power of Graphics Processing Units (GPU). GPUs are emerging as relatively inexpensive parallel processors that are becoming available on a wide range of computer systems. We address the image re-ranking performance challenges by proposing a parallel solution designed to fit the computational model of GPUs. We conducted an experimental evaluation considering different implementations and devices. Experimental results demonstrate that significant performance gains can be obtained. Our approach achieves speedups of 7x from serial implementation considering the overall algorithm and up to 36x on its core steps.

Effect of digitization parameters on periapical radiographic image quality with regard to anatomic landmarks

The aim of this study was to evaluate the influence of digitization parameters on periapical radiographic image quality, with regard to anatomic landmarks. Digitized images (n = 160) were obtained using a flatbed scanner with resolutions of 300, 600 and 2400 dpi. The radiographs of 2400 dpi were decreased to 300 and 600 dpi before storage. Digitizations were performed with and without black masking using 8-bit and 16-bit grayscale and saved in TIFF format. Four anatomic landmarks were classified by two observers (very good, good, moderate, regular, poor), in two random sessions. Intraobserver and interobserver agreements were evaluated by Kappa statistics. Inter and intraobserver agreements ranged according to the anatomic landmarks and resolution used. The results obtained demonstrated that the cement enamel junction was the anatomic landmark that presented the poorest concordance. The use of black masking provided better results in the digitized image. The use of a mask to cover radiographs during digitization is necessary. Therefore, the concordance ranged from regular to moderate for the intraobserver evaluation and concordance ranged from regular to poor for interobserver evaluation.

Fluorescence Level of Composites Assessed by Computer Processing of Digital Images - ScanWhite

The human dentition is naturally translucent, opalescent and fluorescent. Differences between the level of fluorescence of tooth structure and restorative materials may result in distinct metameric properties and consequently perceptible disparate esthetic behavior, which impairs the esthetic result of the restorations, frustrating both patients and staff. In this study, we evaluated the level of fluorescence of different composites (Durafill in tones A2 (Du), Charisma in tones A2 (Ch), Venus in tone A2 (Ve), Opallis enamel and dentin in tones A2 (OPD and OPE), Point 4 in tones A2 (P4), Z100 in tones A2 ( Z1), Z250 in tones A2 (Z2), Te-Econom in tones A2 (TE), Tetric Ceram in tones A2 (TC), Tetric Ceram N in tones A1, A2, A4 (TN1, TN2, TN4), Four seasons enamel and dentin in tones A2 (and 4SD 4SE), Empress Direct enamel and dentin in tones A2 (EDE and EDD) and Brilliant in tones A2 (Br)). Cylindrical specimens were prepared, coded and photographed in a standardized manner with a Canon EOS digital camera (400 ISO, 2.8 aperture and 1/ 30 speed), in a dark environment under the action of UV light (25 W). The images were analyzed with the software ScanWhite©-DMC/Darwin systems. The results showed statistical differences between the groups (p < 0.05), and between these same groups and the average fluorescence of the dentition of young (18 to 25 years) and adults (40 to 45 years) taken as control. It can be concluded that: Composites Z100, Z250 (3M ESPE) and Point 4 (Kerr) do not match with the fluorescence of human dentition and the fluorescence of the materials was found to be affected by their own tone.

Applying enhancement filters in the pre-processing of images of lymphoma

Lymphoma is a type of cancer that affects the immune system, and is classified as Hodgkin or non-Hodgkin. It is one of the ten types of cancer that are the most common on earth. Among all malignant neoplasms diagnosed in the world, lymphoma ranges from three to four percent of them. Our work presents a study of some filters devoted to enhancing images of lymphoma at the pre-processing step. Here the enhancement is useful for removing noise from the digital images. We have analysed the noise caused by different sources like room vibration, scraps and defocusing, and in the following classes of lymphoma: follicular, mantle cell and B-cell chronic lymphocytic leukemia. The filters Gaussian, Median and Mean-Shift were applied to different colour models (RGB, Lab and HSV). Afterwards, we performed a quantitative analysis of the images by means of the Structural Similarity Index. This was done in order to evaluate the similarity between the images. In all cases we have obtained a certainty of at least 75%, which rises to 99% if one considers only HSV. Namely, we have concluded that HSV is an important choice of colour model at pre-processing histological images of lymphoma, because in this case the resulting image will get the best enhancement.

Image segmentation through combined methods: watershed transform, unsupervised distance learning and normalized cut

Research on image processing has shown that combining segmentation methods may lead to a solid approach to extract semantic information from different sort of images. Within this context, the Normalized Cut (NCut) is usually used as a final partitioning tool for graphs modeled in some chosen method. This work explores the Watershed Transform as a modeling tool, using different criteria of the hierarchical Watershed to convert an image into an adjacency graph. The Watershed is combined with an unsupervised distance learning step that redistributes the graph weights and redefines the Similarity matrix, before the final segmentation step using NCut. Adopting the Berkeley Segmentation Data Set and Benchmark as a background, our goal is to compare the results obtained for this method with previous work to validate its performance.

Image segmentation using morphological watershed applied to cartography

Image segmentation is a process frequently used in several different areas including Cartography. Feature extraction is a very troublesome task, and successful results require more complex techniques and good quality data. The aims of this paper is to study Digital Image Processing techniques, with emphasis in Mathematical Morphology, to use Remote Sensing imagery, making image segmentation, using morphological operators, mainly the multi-scale morphological gradient operator. In the segmentation process, pre-processing operators of Mathematical Morphology were used, and the multi-scales gradient was implemented to create one of the images used as marker image. Orbital image of the Landsat satellite, sensor TM was used. The MATLAB software was used in the implementation of the routines. With the accomplishment of tests, the performance of the implemented operators was verified and carried through the analysis of the results. The extration of linear feature, using mathematical morphology techniques, can contribute in cartographic applications, as cartographic products updating. The comparison to the best result obtained was performed by means of the morphology with conventional techniques of features extraction. © Springer-Verlag 2004.

Riverbed: A Novel User-Steered Image Segmentation Method Based on Optimum Boundary Tracking

This paper presents an optimum user-steered boundary tracking approach for image segmentation, which simulates the behavior of water flowing through a riverbed. The riverbed approach was devised using the image foresting transform with a never-exploited connectivity function. We analyze its properties in the derived image graphs and discuss its theoretical relation with other popular methods such as live wire and graph cuts. Several experiments show that riverbed can significantly reduce the number of user interactions (anchor points), as compared to live wire for objects with complex shapes. This paper also includes a discussion about how to combine different methods in order to take advantage of their complementary strengths.

REALISTIC IVUS IMAGE GENERATION IN DIFFERENT INTRALUMINAL PRESSURES

Intravascular ultrasound (IVUS) phantoms are important to calibrate and evaluate many IVUS imaging processing tasks. However, phantom generation is never the primary focus of related works; hence, it cannot be well covered, and is usually based on more than one platform, which may not be accessible to investigators. Therefore, we present a framework for creating representative IVUS phantoms, for different intraluminal pressures, based on the finite element method and Field II. First, a coronary cross-section model is selected. Second, the coronary regions are identified to apply the properties. Third, the corresponding mesh is generated. Fourth, the intraluminal force is applied and the deformation computed. Finally, the speckle noise is incorporated. The framework was tested taking into account IVUS contrast, noise and strains. The outcomes are in line with related studies and expected values. Moreover, the framework toolbox is freely accessible and fully implemented in a single platform. (E-mail: fernando.okara@gmail.com) (c) 2012 World Federation for Ultrasound in Medicine & Biology.

Processing and mechanical properties evaluation of glass fiber-reinforced PTFE laminates

A specific manufacturing process to obtain continuous glass fiber-reinforced RIFE laminates was studied and some of their mechanical properties were evaluated. Young's modulus and maximum strength were measured by three-point bending test and tensile test using the Digital Image Correlation (DIC) technique. Adhesion tests, thermal analysis and microscopy were used to evaluate the fiber-matrix adhesion, which is very dependent on the sintering time. The composite material obtained had a Young's modulus of 14.2 GPa and ultimate strength of 165 MPa, which corresponds to approximately 24 times the modulus and six times the ultimate strength of pure RIFE. These results show that the RIFE composite, manufactured under specific conditions, has great potential to provide structural parts with a performance suitable for application in structural components. (C) 2012 Elsevier Ltd. All rights reserved.

Fuzzy Connectedness Image Segmentation in Graph Cut Formulation: A Linear-Time Algorithm and a Comparative Analysis

A deep theoretical analysis of the graph cut image segmentation framework presented in this paper simultaneously translates into important contributions in several directions. The most important practical contribution of this work is a full theoretical description, and implementation, of a novel powerful segmentation algorithm, GC(max). The output of GC(max) coincides with a version of a segmentation algorithm known as Iterative Relative Fuzzy Connectedness, IRFC. However, GC(max) is considerably faster than the classic IRFC algorithm, which we prove theoretically and show experimentally. Specifically, we prove that, in the worst case scenario, the GC(max) algorithm runs in linear time with respect to the variable M=|C|+|Z|, where |C| is the image scene size and |Z| is the size of the allowable range, Z, of the associated weight/affinity function. For most implementations, Z is identical to the set of allowable image intensity values, and its size can be treated as small with respect to |C|, meaning that O(M)=O(|C|). In such a situation, GC(max) runs in linear time with respect to the image size |C|. We show that the output of GC(max) constitutes a solution of a graph cut energy minimization problem, in which the energy is defined as the a"" (a) norm ayenF (P) ayen(a) of the map F (P) that associates, with every element e from the boundary of an object P, its weight w(e). This formulation brings IRFC algorithms to the realm of the graph cut energy minimizers, with energy functions ayenF (P) ayen (q) for qa[1,a]. Of these, the best known minimization problem is for the energy ayenF (P) ayen(1), which is solved by the classic min-cut/max-flow algorithm, referred to often as the Graph Cut algorithm. We notice that a minimization problem for ayenF (P) ayen (q) , qa[1,a), is identical to that for ayenF (P) ayen(1), when the original weight function w is replaced by w (q) . Thus, any algorithm GC(sum) solving the ayenF (P) ayen(1) minimization problem, solves also one for ayenF (P) ayen (q) with qa[1,a), so just two algorithms, GC(sum) and GC(max), are enough to solve all ayenF (P) ayen (q) -minimization problems. We also show that, for any fixed weight assignment, the solutions of the ayenF (P) ayen (q) -minimization problems converge to a solution of the ayenF (P) ayen(a)-minimization problem (ayenF (P) ayen(a)=lim (q -> a)ayenF (P) ayen (q) is not enough to deduce that). An experimental comparison of the performance of GC(max) and GC(sum) algorithms is included. This concentrates on comparing the actual (as opposed to provable worst scenario) algorithms' running time, as well as the influence of the choice of the seeds on the output.

Seeking tools for image fusion between computed tomography, structural and functional magnetic resonance methods for applications in neurosurgery

OBJECTIVE: To evaluate tools for the fusion of images generated by tomography and structural and functional magnetic resonance imaging. METHODS: Magnetic resonance and functional magnetic resonance imaging were performed while a volunteer who had previously undergone cranial tomography performed motor and somatosensory tasks in a 3-Tesla scanner. Image data were analyzed with different programs, and the results were compared. RESULTS: We constructed a flow chart of computational processes that allowed measurement of the spatial congruence between the methods. There was no single computational tool that contained the entire set of functions necessary to achieve the goal. CONCLUSION: The fusion of the images from the three methods proved to be feasible with the use of four free-access software programs (OsiriX, Register, MRIcro and FSL). Our results may serve as a basis for building software that will be useful as a virtual tool prior to neurosurgery.

Hyperspectral image compression onboard next-generation satellites: implementation solutions on GPU and FPGAs

Programa de doctorado: Ingeniería de Telecomunicación Avanzada

Path planning for image based visual servoing

This thesis deals with Visual Servoing and its strictly connected disciplines like projective geometry, image processing, robotics and non-linear control. More specifically the work addresses the problem to control a robotic manipulator through one of the largely used Visual Servoing techniques: the Image Based Visual Servoing (IBVS). In Image Based Visual Servoing the robot is driven by on-line performing a feedback control loop that is closed directly in the 2D space of the camera sensor. The work considers the case of a monocular system with the only camera mounted on the robot end effector (eye in hand configuration). Through IBVS the system can be positioned with respect to a 3D fixed target by minimizing the differences between its initial view and its goal view, corresponding respectively to the initial and the goal system configurations: the robot Cartesian Motion is thus generated only by means of visual informations. However, the execution of a positioning control task by IBVS is not straightforward because singularity problems may occur and local minima may be reached where the reached image is very close to the target one but the 3D positioning task is far from being fulfilled: this happens in particular for large camera displacements, when the the initial and the goal target views are noticeably different. To overcame singularity and local minima drawbacks, maintaining the good properties of IBVS robustness with respect to modeling and camera calibration errors, an opportune image path planning can be exploited. This work deals with the problem of generating opportune image plane trajectories for tracked points of the servoing control scheme (a trajectory is made of a path plus a time law). The generated image plane paths must be feasible i.e. they must be compliant with rigid body motion of the camera with respect to the object so as to avoid image jacobian singularities and local minima problems. In addition, the image planned trajectories must generate camera velocity screws which are smooth and within the allowed bounds of the robot. We will show that a scaled 3D motion planning algorithm can be devised in order to generate feasible image plane trajectories. Since the paths in the image are off-line generated it is also possible to tune the planning parameters so as to maintain the target inside the camera field of view even if, in some unfortunate cases, the feature target points would leave the camera images due to 3D robot motions. To test the validity of the proposed approach some both experiments and simulations results have been reported taking also into account the influence of noise in the path planning strategy. The experiments have been realized with a 6DOF anthropomorphic manipulator with a fire-wire camera installed on its end effector: the results demonstrate the good performances and the feasibility of the proposed approach.

Adaptive multiscale biological signal processing

Biological processes are very complex mechanisms, most of them being accompanied by or manifested as signals that reflect their essential characteristics and qualities. The development of diagnostic techniques based on signal and image acquisition from the human body is commonly retained as one of the propelling factors in the advancements in medicine and biosciences recorded in the recent past. It is a fact that the instruments used for biological signal and image recording, like any other acquisition system, are affected by non-idealities which, by different degrees, negatively impact on the accuracy of the recording. This work discusses how it is possible to attenuate, and ideally to remove, these effects, with a particular attention toward ultrasound imaging and extracellular recordings. Original algorithms developed during the Ph.D. research activity will be examined and compared to ones in literature tackling the same problems; results will be drawn on the base of comparative tests on both synthetic and in-vivo acquisitions, evaluating standard metrics in the respective field of application. All the developed algorithms share an adaptive approach to signal analysis, meaning that their behavior is not dependent only on designer choices, but driven by input signal characteristics too. Performance comparisons following the state of the art concerning image quality assessment, contrast gain estimation and resolution gain quantification as well as visual inspection highlighted very good results featured by the proposed ultrasound image deconvolution and restoring algorithms: axial resolution up to 5 times better than algorithms in literature are possible. Concerning extracellular recordings, the results of the proposed denoising technique compared to other signal processing algorithms pointed out an improvement of the state of the art of almost 4 dB.

Statistical methods for biomedical signal analysis and processing

Statistical modelling and statistical learning theory are two powerful analytical frameworks for analyzing signals and developing efficient processing and classification algorithms. In this thesis, these frameworks are applied for modelling and processing biomedical signals in two different contexts: ultrasound medical imaging systems and primate neural activity analysis and modelling. In the context of ultrasound medical imaging, two main applications are explored: deconvolution of signals measured from a ultrasonic transducer and automatic image segmentation and classification of prostate ultrasound scans. In the former application a stochastic model of the radio frequency signal measured from a ultrasonic transducer is derived. This model is then employed for developing in a statistical framework a regularized deconvolution procedure, for enhancing signal resolution. In the latter application, different statistical models are used to characterize images of prostate tissues, extracting different features. These features are then uses to segment the images in region of interests by means of an automatic procedure based on a statistical model of the extracted features. Finally, machine learning techniques are used for automatic classification of the different region of interests. In the context of neural activity signals, an example of bio-inspired dynamical network was developed to help in studies of motor-related processes in the brain of primate monkeys. The presented model aims to mimic the abstract functionality of a cell population in 7a parietal region of primate monkeys, during the execution of learned behavioural tasks.