186 resultados para De-convolution
Resumo:
As one of the most popular deep learning models, convolution neural network (CNN) has achieved huge success in image information extraction. Traditionally CNN is trained by supervised learning method with labeled data and used as a classifier by adding a classification layer in the end. Its capability of extracting image features is largely limited due to the difficulty of setting up a large training dataset. In this paper, we propose a new unsupervised learning CNN model, which uses a so-called convolutional sparse auto-encoder (CSAE) algorithm pre-Train the CNN. Instead of using labeled natural images for CNN training, the CSAE algorithm can be used to train the CNN with unlabeled artificial images, which enables easy expansion of training data and unsupervised learning. The CSAE algorithm is especially designed for extracting complex features from specific objects such as Chinese characters. After the features of articficial images are extracted by the CSAE algorithm, the learned parameters are used to initialize the first CNN convolutional layer, and then the CNN model is fine-Trained by scene image patches with a linear classifier. The new CNN model is applied to Chinese scene text detection and is evaluated with a multilingual image dataset, which labels Chinese, English and numerals texts separately. More than 10% detection precision gain is observed over two CNN models.
Resumo:
In 1972 the ionized cluster beam (ICB) deposition technique was introduced as a new method for thin film deposition. At that time the use of clusters was postulated to be able to enhance film nucleation and adatom surface mobility, resulting in high quality films. Although a few researchers reported singly ionized clusters containing 10$\sp2$-10$\sp3$ atoms, others were unable to repeat their work. The consensus now is that film effects in the early investigations were due to self-ion bombardment rather than clusters. Subsequently in recent work (early 1992) synthesis of large clusters of zinc without the use of a carrier gas was demonstrated by Gspann and repeated in our laboratory. Clusters resulted from very significant changes in two source parameters. Crucible pressure was increased from the earlier 2 Torr to several thousand Torr and a converging-diverging nozzle 18 mm long and 0.4 mm in diameter at the throat was used in place of the 1 mm x 1 mm nozzle used in the early work. While this is practical for zinc and other high vapor pressure materials it remains impractical for many materials of industrial interest such as gold, silver, and aluminum. The work presented here describes results using gold and silver at pressures of around 1 and 50 Torr in order to study the effect of the pressure and nozzle shape. Significant numbers of large clusters were not detected. Deposited films were studied by atomic force microscopy (AFM) for roughness analysis, and X-ray diffraction.^ Nanometer size islands of zinc deposited on flat silicon substrates by ICB were also studied by atomic force microscopy and the number of atoms/cm$\sp2$ was calculated and compared to data from Rutherford backscattering spectrometry (RBS). To improve the agreement between data from AFM and RBS, convolution and deconvolution algorithms were implemented to study and simulate the interaction between tip and sample in atomic force microscopy. The deconvolution algorithm takes into account the physical volume occupied by the tip resulting in an image that is a more accurate representation of the surface.^ One method increasingly used to study the deposited films both during the growth process and following, is ellipsometry. Ellipsometry is a surface analytical technique used to determine the optical properties and thickness of thin films. In situ measurements can be made through the windows of a deposition chamber. A method for determining the optical properties of a film, that is sensitive only to the growing film and accommodates underlying interfacial layers, multiple unknown underlayers, and other unknown substrates was developed. This method is carried out by making an initial ellipsometry measurement well past the real interface and by defining a virtual interface in the vicinity of this measurement. ^
Resumo:
The contributions of this dissertation are in the development of two new interrelated approaches to video data compression: (1) A level-refined motion estimation and subband compensation method for the effective motion estimation and motion compensation. (2) A shift-invariant sub-decimation decomposition method in order to overcome the deficiency of the decimation process in estimating motion due to its shift-invariant property of wavelet transform. ^ The enormous data generated by digital videos call for an intense need of efficient video compression techniques to conserve storage space and minimize bandwidth utilization. The main idea of video compression is to reduce the interpixel redundancies inside and between the video frames by applying motion estimation and motion compensation (MEMO) in combination with spatial transform coding. To locate the global minimum of the matching criterion function reasonably, hierarchical motion estimation by coarse to fine resolution refinements using discrete wavelet transform is applied due to its intrinsic multiresolution and scalability natures. ^ Due to the fact that most of the energies are concentrated in the low resolution subbands while decreased in the high resolution subbands, a new approach called level-refined motion estimation and subband compensation (LRSC) method is proposed. It realizes the possible intrablocks in the subbands for lower entropy coding while keeping the low computational loads of motion estimation as the level-refined method, thus to achieve both temporal compression quality and computational simplicity. ^ Since circular convolution is applied in wavelet transform to obtain the decomposed subframes without coefficient expansion, symmetric-extended wavelet transform is designed on the finite length frame signals for more accurate motion estimation without discontinuous boundary distortions. ^ Although wavelet transformed coefficients still contain spatial domain information, motion estimation in wavelet domain is not as straightforward as in spatial domain due to the shift variance property of the decimation process of the wavelet transform. A new approach called sub-decimation decomposition method is proposed, which maintains the motion consistency between the original frame and the decomposed subframes, improving as a consequence the wavelet domain video compressions by shift invariant motion estimation and compensation. ^
Resumo:
The distribution and abundance of the American crocodile (Crocodylus acutus) in the Florida Everglades is dependent on the timing, amount, and location of freshwater flow. One of the goals of the Comprehensive Everglades Restoration Plan (CERP) is to restore historic freshwater flows to American crocodile habitat throughout the Everglades. To predict the impacts on the crocodile population from planned restoration activities, we created a stage-based spatially explicit crocodile population model that incorporated regional hydrology models and American crocodile research and monitoring data. Growth and survival were influenced by salinity, water depth, and density-dependent interactions. A stage-structured spatial model was used with discrete spatial convolution to direct crocodiles toward attractive sources where conditions were favorable. The model predicted that CERP would have both positive and negative impacts on American crocodile growth, survival, and distribution. Overall, crocodile populations across south Florida were predicted to decrease approximately 3 % with the implementation of CERP compared to future conditions without restoration, but local increases up to 30 % occurred in the Joe Bay area near Taylor Slough, and local decreases up to 30 % occurred in the vicinity of Buttonwood Canal due to changes in salinity and freshwater flows.
Resumo:
The aim of this study was to develop a practical, versatile and fast dosimetry and radiobiological model for calculation of the 3D dose distribution and radiobiological effectiveness of radioactive stents. The algorithm was written in Matlab 6.5 programming language and is based on the dose point kernel convolution. The dosimetry and radiobiological model was applied for evaluation of the 3D dose distribution of 32P, 90Y, 188Re and 177Lu stents. Of the four, 32P delivers the highest dose, while 90Y, 188Re and 177Lu require high levels of activity to deliver a significant therapeutic dose in the range of 15-30 Gy. Results of the radiobiological model demonstrated that the same physical dose delivered by different radioisotopes produces significantly different radiobiological effects. This type of theoretical dose calculation can be useful in the development of new stent designs, the planning of animal studies and clinical trials, and clinical decisions involving individualized treatment plans.
Resumo:
Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.
Resumo:
X-ray computed tomography (CT) is a non-invasive medical imaging technique that generates cross-sectional images by acquiring attenuation-based projection measurements at multiple angles. Since its first introduction in the 1970s, substantial technical improvements have led to the expanding use of CT in clinical examinations. CT has become an indispensable imaging modality for the diagnosis of a wide array of diseases in both pediatric and adult populations [1, 2]. Currently, approximately 272 million CT examinations are performed annually worldwide, with nearly 85 million of these in the United States alone [3]. Although this trend has decelerated in recent years, CT usage is still expected to increase mainly due to advanced technologies such as multi-energy [4], photon counting [5], and cone-beam CT [6].
Despite the significant clinical benefits, concerns have been raised regarding the population-based radiation dose associated with CT examinations [7]. From 1980 to 2006, the effective dose from medical diagnostic procedures rose six-fold, with CT contributing to almost half of the total dose from medical exposure [8]. For each patient, the risk associated with a single CT examination is likely to be minimal. However, the relatively large population-based radiation level has led to enormous efforts among the community to manage and optimize the CT dose.
As promoted by the international campaigns Image Gently and Image Wisely, exposure to CT radiation should be appropriate and safe [9, 10]. It is thus a responsibility to optimize the amount of radiation dose for CT examinations. The key for dose optimization is to determine the minimum amount of radiation dose that achieves the targeted image quality [11]. Based on such principle, dose optimization would significantly benefit from effective metrics to characterize radiation dose and image quality for a CT exam. Moreover, if accurate predictions of the radiation dose and image quality were possible before the initiation of the exam, it would be feasible to personalize it by adjusting the scanning parameters to achieve a desired level of image quality. The purpose of this thesis is to design and validate models to quantify patient-specific radiation dose prospectively and task-based image quality. The dual aim of the study is to implement the theoretical models into clinical practice by developing an organ-based dose monitoring system and an image-based noise addition software for protocol optimization.
More specifically, Chapter 3 aims to develop an organ dose-prediction method for CT examinations of the body under constant tube current condition. The study effectively modeled the anatomical diversity and complexity using a large number of patient models with representative age, size, and gender distribution. The dependence of organ dose coefficients on patient size and scanner models was further evaluated. Distinct from prior work, these studies use the largest number of patient models to date with representative age, weight percentile, and body mass index (BMI) range.
With effective quantification of organ dose under constant tube current condition, Chapter 4 aims to extend the organ dose prediction system to tube current modulated (TCM) CT examinations. The prediction, applied to chest and abdominopelvic exams, was achieved by combining a convolution-based estimation technique that quantifies the radiation field, a TCM scheme that emulates modulation profiles from major CT vendors, and a library of computational phantoms with representative sizes, ages, and genders. The prospective quantification model is validated by comparing the predicted organ dose with the dose estimated based on Monte Carlo simulations with TCM function explicitly modeled.
Chapter 5 aims to implement the organ dose-estimation framework in clinical practice to develop an organ dose-monitoring program based on a commercial software (Dose Watch, GE Healthcare, Waukesha, WI). In the first phase of the study we focused on body CT examinations, and so the patient’s major body landmark information was extracted from the patient scout image in order to match clinical patients against a computational phantom in the library. The organ dose coefficients were estimated based on CT protocol and patient size as reported in Chapter 3. The exam CTDIvol, DLP, and TCM profiles were extracted and used to quantify the radiation field using the convolution technique proposed in Chapter 4.
With effective methods to predict and monitor organ dose, Chapters 6 aims to develop and validate improved measurement techniques for image quality assessment. Chapter 6 outlines the method that was developed to assess and predict quantum noise in clinical body CT images. Compared with previous phantom-based studies, this study accurately assessed the quantum noise in clinical images and further validated the correspondence between phantom-based measurements and the expected clinical image quality as a function of patient size and scanner attributes.
Chapter 7 aims to develop a practical strategy to generate hybrid CT images and assess the impact of dose reduction on diagnostic confidence for the diagnosis of acute pancreatitis. The general strategy is (1) to simulate synthetic CT images at multiple reduced-dose levels from clinical datasets using an image-based noise addition technique; (2) to develop quantitative and observer-based methods to validate the realism of simulated low-dose images; (3) to perform multi-reader observer studies on the low-dose image series to assess the impact of dose reduction on the diagnostic confidence for multiple diagnostic tasks; and (4) to determine the dose operating point for clinical CT examinations based on the minimum diagnostic performance to achieve protocol optimization.
Chapter 8 concludes the thesis with a summary of accomplished work and a discussion about future research.
Resumo:
Dynamic positron emission tomography (PET) imaging can be used to track the distribution of injected radio-labelled molecules over time in vivo. This is a powerful technique, which provides researchers and clinicians the opportunity to study the status of healthy and pathological tissue by examining how it processes substances of interest. Widely used tracers include 18F-uorodeoxyglucose, an analog of glucose, which is used as the radiotracer in over ninety percent of PET scans. This radiotracer provides a way of quantifying the distribution of glucose utilisation in vivo. The interpretation of PET time-course data is complicated because the measured signal is a combination of vascular delivery and tissue retention effects. If the arterial time-course is known, the tissue time-course can typically be expressed in terms of a linear convolution between the arterial time-course and the tissue residue function. As the residue represents the amount of tracer remaining in the tissue, this can be thought of as a survival function; these functions been examined in great detail by the statistics community. Kinetic analysis of PET data is concerned with estimation of the residue and associated functionals such as ow, ux and volume of distribution. This thesis presents a Markov chain formulation of blood tissue exchange and explores how this relates to established compartmental forms. A nonparametric approach to the estimation of the residue is examined and the improvement in this model relative to compartmental model is evaluated using simulations and cross-validation techniques. The reference distribution of the test statistics, generated in comparing the models, is also studied. We explore these models further with simulated studies and an FDG-PET dataset from subjects with gliomas, which has previously been analysed with compartmental modelling. We also consider the performance of a recently proposed mixture modelling technique in this study.
Resumo:
Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.
Resumo:
This research paper presents the work on feature recognition, tool path data generation and integration with STEP-NC (AP-238 format) for features having Free form / Irregular Contoured Surface(s) (FICS). Initially, the FICS features are modelled / imported in UG CAD package and a closeness index is generated. This is done by comparing the FICS features with basic B-Splines / Bezier curves / surfaces. Then blending functions are caculated by adopting convolution theorem. Based on the blending functions, contour offsett tool paths are generated and simulated for 5 axis milling environment. Finally, the tool path (CL) data is integrated with STEP-NC (AP-238) format. The tool path algorithm and STEP- NC data is tested with various industrial parts through an automated UFUNC plugin.
Resumo:
Photometry of moving sources typically suffers from a reduced signal-to-noise ratio (S/N) or flux measurements biased to incorrect low values through the use of circular apertures. To address this issue, we present the software package, TRIPPy: TRailed Image Photometry in Python. TRIPPy introduces the pill aperture, which is the natural extension of the circular aperture appropriate for linearly trailed sources. The pill shape is a rectangle with two semicircular end-caps and is described by three parameters, the trail length and angle, and the radius. The TRIPPy software package also includes a new technique to generate accurate model point-spread functions (PSFs) and trailed PSFs (TSFs) from stationary background sources in sidereally tracked images. The TSF is merely the convolution of the model PSF, which consists of a moffat profile, and super-sampled lookup table. From the TSF, accurate pill aperture corrections can be estimated as a function of pill radius with an accuracy of 10 mmag for highly trailed sources. Analogous to the use of small circular apertures and associated aperture corrections, small radius pill apertures can be used to preserve S/Ns of low flux sources, with appropriate aperture correction applied to provide an accurate, unbiased flux measurement at all S/Ns.
Resumo:
Thesis (Ph.D.)--University of Washington, 2016-08
Resumo:
In order to optimize frontal detection in sea surface temperature fields at 4 km resolution, a combined statistical and expert-based approach is applied to test different spatial smoothing of the data prior to the detection process. Fronts are usually detected at 1 km resolution using the histogram-based, single image edge detection (SIED) algorithm developed by Cayula and Cornillon in 1992, with a standard preliminary smoothing using a median filter and a 3 × 3 pixel kernel. Here, detections are performed in three study regions (off Morocco, the Mozambique Channel, and north-western Australia) and across the Indian Ocean basin using the combination of multiple windows (CMW) method developed by Nieto, Demarcq and McClatchie in 2012 which improves on the original Cayula and Cornillon algorithm. Detections at 4 km and 1 km of resolution are compared. Fronts are divided in two intensity classes (“weak” and “strong”) according to their thermal gradient. A preliminary smoothing is applied prior to the detection using different convolutions: three type of filters (median, average and Gaussian) combined with four kernel sizes (3 × 3, 5 × 5, 7 × 7, and 9 × 9 pixels) and three detection window sizes (16 × 16, 24 × 24 and 32 × 32 pixels) to test the effect of these smoothing combinations on reducing the background noise of the data and therefore on improving the frontal detection. The performance of the combinations on 4 km data are evaluated using two criteria: detection efficiency and front length. We find that the optimal combination of preliminary smoothing parameters in enhancing detection efficiency and preserving front length includes a median filter, a 16 × 16 pixel window size, and a 5 × 5 pixel kernel for strong fronts and a 7 × 7 pixel kernel for weak fronts. Results show an improvement in detection performance (from largest to smallest window size) of 71% for strong fronts and 120% for weak fronts. Despite the small window used (16 × 16 pixels), the length of the fronts has been preserved relative to that found with 1 km data. This optimal preliminary smoothing and the CMW detection algorithm on 4 km sea surface temperature data are then used to describe the spatial distribution of the monthly frequencies of occurrence for both strong and weak fronts across the Indian Ocean basin. In general strong fronts are observed in coastal areas whereas weak fronts, with some seasonal exceptions, are mainly located in the open ocean. This study shows that adequate noise reduction done by a preliminary smoothing of the data considerably improves the frontal detection efficiency as well as the global quality of the results. Consequently, the use of 4 km data enables frontal detections similar to 1 km data (using a standard median 3 × 3 convolution) in terms of detectability, length and location. This method, using 4 km data is easily applicable to large regions or at the global scale with far less constraints of data manipulation and processing time relative to 1 km data.
Resumo:
Processors with large numbers of cores are becoming commonplace. In order to utilise the available resources in such systems, the programming paradigm has to move towards increased parallelism. However, increased parallelism does not necessarily lead to better performance. Parallel programming models have to provide not only flexible ways of defining parallel tasks, but also efficient methods to manage the created tasks. Moreover, in a general-purpose system, applications residing in the system compete for the shared resources. Thread and task scheduling in such a multiprogrammed multithreaded environment is a significant challenge. In this thesis, we introduce a new task-based parallel reduction model, called the Glasgow Parallel Reduction Machine (GPRM). Our main objective is to provide high performance while maintaining ease of programming. GPRM supports native parallelism; it provides a modular way of expressing parallel tasks and the communication patterns between them. Compiling a GPRM program results in an Intermediate Representation (IR) containing useful information about tasks, their dependencies, as well as the initial mapping information. This compile-time information helps reduce the overhead of runtime task scheduling and is key to high performance. Generally speaking, the granularity and the number of tasks are major factors in achieving high performance. These factors are even more important in the case of GPRM, as it is highly dependent on tasks, rather than threads. We use three basic benchmarks to provide a detailed comparison of GPRM with Intel OpenMP, Cilk Plus, and Threading Building Blocks (TBB) on the Intel Xeon Phi, and with GNU OpenMP on the Tilera TILEPro64. GPRM shows superior performance in almost all cases, only by controlling the number of tasks. GPRM also provides a low-overhead mechanism, called “Global Sharing”, which improves performance in multiprogramming situations. We use OpenMP, as the most popular model for shared-memory parallel programming as the main GPRM competitor for solving three well-known problems on both platforms: LU factorisation of Sparse Matrices, Image Convolution, and Linked List Processing. We focus on proposing solutions that best fit into the GPRM’s model of execution. GPRM outperforms OpenMP in all cases on the TILEPro64. On the Xeon Phi, our solution for the LU Factorisation results in notable performance improvement for sparse matrices with large numbers of small blocks. We investigate the overhead of GPRM’s task creation and distribution for very short computations using the Image Convolution benchmark. We show that this overhead can be mitigated by combining smaller tasks into larger ones. As a result, GPRM can outperform OpenMP for convolving large 2D matrices on the Xeon Phi. Finally, we demonstrate that our parallel worksharing construct provides an efficient solution for Linked List processing and performs better than OpenMP implementations on the Xeon Phi. The results are very promising, as they verify that our parallel programming framework for manycore processors is flexible and scalable, and can provide high performance without sacrificing productivity.