Akshaya Mishra | University of Waterloo (original) (raw)

Papers by Akshaya Mishra

Research paper thumbnail of Decoupled active contour (DAC) for boundary detection

Abstract The accurate detection of object boundaries via active contours is an ongoing research t... more Abstract The accurate detection of object boundaries via active contours is an ongoing research topic in computer vision. Most active contours converge toward some desired contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. Such an approach is elegant, but suffers from a slow convergence rate and frequently misconverges in the presence of noise or complex contours.

Research paper thumbnail of Sparse Reconstruction of Breast MRI using Homotopic $ L_0 $ Minimization in a Regional Sparsified Domain

Abstract The use of magnetic resonance imaging (MRI) for early breast examination and screening o... more Abstract The use of magnetic resonance imaging (MRI) for early breast examination and screening of asymptomatic women has become increasing popular, given its ability to provide detailed tissue characteristics that cannot be obtained using other imaging modalities such as mammography and ultrasound.

Research paper thumbnail of NONPARAMETRIC SAMPLE-BASED METHODS FOR IMAGE UNDERSTANDING

This chapter presents a nonparametric framework for image understanding based on models construct... more This chapter presents a nonparametric framework for image understanding based on models constructed via conditional sampling. Rather than modeling imaging data as a lattice of fixed values (one intensity per pixel), or as a set of parametric distributions (such as a Gaussian distribution), we explore the modeling of imaging data as a lattice of nonparametric conditional probability distributions estimated via random sampling.

Research paper thumbnail of Decoupled Deformable Model For 2D/3D Boundary Identification

Abstract: The accurate detection of static object boundaries such as contours or surfaces and dyn... more Abstract: The accurate detection of static object boundaries such as contours or surfaces and dynamic tunnels of moving objects via deformable models is an ongoing research topic in computer vision. Most deformable models attempt to converge towards a desired solution by minimizing the sum of internal (prior) and external (measurement) energy terms.

Research paper thumbnail of Intra-retinal layer segmentation in optical coherence tomography images

Abstract Retinal layer thickness, evaluated as a function of spatial position from optical cohere... more Abstract Retinal layer thickness, evaluated as a function of spatial position from optical coherence tomography (OCT) images is an important diagnostics marker for many retinal diseases. However, due to factors such as speckle noise, low image contrast, irregularly shaped morphological features such as retinal detachments, macular holes, and drusen, accurate segmentation of individual retinal layers is difficult. To address this issue, a computer method for retinal layer segmentation from OCT images is presented.

Research paper thumbnail of Improved interactive medical image segmentation using enhanced intelligent scissors (eis)

Abstract A novel interactive approach called Enhanced Intelligent Scissors (EIS) is presented for... more Abstract A novel interactive approach called Enhanced Intelligent Scissors (EIS) is presented for segmenting regions of interest in medical images. The proposed interactive medical image segmentation algorithm addresses the issues associated with segmenting medical images and allows for fast, robust, and flexible segmentation without requiring accurate manual tracing.

Research paper thumbnail of Robust snake convergence based on dynamic programming

Abstract The extraction of contours using deformable models, such as snakes, is a problem of grea... more Abstract The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes have been widely studied and many methods are available. In most cases, the snake converges towards the optimal contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. This approach is elegant, but frequently mis-converges in the presence of noise or complex contours.

Research paper thumbnail of A novel algorithm for extraction of the layers of the cornea

Abstract Accurate corneal layer boundary extraction from optical coherence tomograms can provide ... more Abstract Accurate corneal layer boundary extraction from optical coherence tomograms can provide precise layer thickness measurements required in the analysis of corneal disease. This paper establishes a novel approach to precisely obtain the five primary corneal layer boundaries. The proposed method determines correspondence relationships between the layer boundaries to facilitate robust boundary extraction in the presence of noise and artifacts.

Research paper thumbnail of Shape-guided active contour based segmentation and tracking of lumbar vertebrae in video fluoroscopy using complex wavelets

Abstract This paper presents a novel shape-guided active contour based approach for segmenting an... more Abstract This paper presents a novel shape-guided active contour based approach for segmenting and tracking lumbar vertebrae in video fluoroscopy using complex-valued wavelets. representations.

Research paper thumbnail of General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery

An important image post-processing step for optical coherence tomography (OCT) images is speckle ... more An important image post-processing step for optical coherence tomography (OCT) images is speckle noise reduction. Noise in OCT images is multiplicative in nature and is difficult to suppress due to the fact that in addition the noise component, OCT speckle also carries structural information about the imaged object. To address this issue, a novel speckle noise reduction algorithm was developed.

Research paper thumbnail of An adaptive Monte Carlo approach to nonlinear image denoising

Abstract This paper introduces a novel stochastic approach to image denoising using an adaptive M... more Abstract This paper introduces a novel stochastic approach to image denoising using an adaptive Monte Carlo scheme. Random samples are generated from the image field using a spatially-adaptive importance sampling approach. Samples are then represented using Gaussian probability distributions and a sample rejection scheme is performed based on a chi 2 statistical hypothesis test. The remaining samples are then aggregated based on Pearson Type VII statistics to create a non-linear estimate of the denoised image.

Research paper thumbnail of Evaluation of hypoxic swelling of human cornea with high speed, ultrahigh resolution optical coherence tomography

ABSTRACT Hypoxia induced corneal swelling was observed and evaluated in healthy human volunteers ... more ABSTRACT Hypoxia induced corneal swelling was observed and evaluated in healthy human volunteers by use of high speed, ultrahigh resolution optical coherence tomography (UHROCT). Two dimensional corneal images were acquired at a speed of 47,000 A-scans/s with 3µm x 10µm (axial x lateral) resolution in corneal tissue. The UHROCT tomograms showed clear visualization of all corneal layers, including the Bowman's layer and the Descemet's membrane–Endothelium complex.

Research paper thumbnail of Novel interactive approach to intra-retinal layer segmentation from optical coherence tomography images

Abstract: Retinal layer thickness, evaluated as a function of spatial position from optical coher... more Abstract: Retinal layer thickness, evaluated as a function of spatial position from optical coherence tomography (OCT) images is an important diagnostics marker for many retinal diseases. However, due to factors such as speckle noise, low image contrast, irregularly shaped morphological features such as retinal detachments, macular holes, and drusen, accurate segmentation of individual retinal layers is difficult.

Research paper thumbnail of Stochastic image denoising based on Markov-chain Monte Carlo sampling

Abstract A novel stochastic approach based on Markov-chain Monte Carlo sampling is investigated f... more Abstract A novel stochastic approach based on Markov-chain Monte Carlo sampling is investigated for the purpose of image denoising. The additive image denoising problem is formulated as a Bayesian least squares problem, where the goal is to estimate the denoised image given the noisy image as the measurement and an estimated posterior. The posterior is estimated using a nonparametric importance-weighted Markov-chain Monte Carlo sampling approach based on an adaptive Geman–McClure objective function.

Research paper thumbnail of VizDraw: A Platform to Convert Online Hand-Drawn Graphics into Computer Graphics

Abstract. With the adoption of tablet-based data entry devices, there is considerable interest in... more Abstract. With the adoption of tablet-based data entry devices, there is considerable interest in methods for converting hand-drawn sketches of flow charts, graphs and block diagram into accurate machine interpretations, a conversion process with many applications in engineering, presentations, and simulations. However, the recognition of hand-drawn graphics is a great challenge due to the visual similarity of many system components. This is complicated due to the significant differences in drawing styles between users.

Research paper thumbnail of A Robust Modular Wavelet Network Based Symbol Classifier

Abstract. This paper presents a robust automatic shape classifier using modular wavelet networks ... more Abstract. This paper presents a robust automatic shape classifier using modular wavelet networks (MWNs). A shape descriptor is constructed based on a combination of global geometric features (modified Zernike moments and circularity features) and local intensity features (ordered histogram of image gradient orientations). The proposed method utilizes a supervised modular wavelet network to perform shape classification based on the extracted shape descriptors.

Research paper thumbnail of Accurate boundary localization using dynamic programming on snakes

Abstract The extraction of contours using deformable models, such as snakes, is a problem of grea... more Abstract The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes have been widely studied, and many methods are available. In most cases, the snake converges towards the optimal contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. This approach is elegant, but frequently mis-converges in the presence of noise or complex contours.

Research paper thumbnail of Decoupled Active Surface for Volumetric Image Segmentation

Abstract Finding the surface of a volumetric 3D object is a fundamental problem in computer visio... more Abstract Finding the surface of a volumetric 3D object is a fundamental problem in computer vision. Energy minimizing splines, such as active surfaces, have been used to carry out such tasks, evolving under the influence of internal and external energies until the model converges to a desired surface. The present deformable model based surface extraction techniques are computationally expensive and are generally unreliable in identifying the surfaces of noisy, high-curvature and cluttered 3D objects.

Research paper thumbnail of A cellular automata based semi-automatic algorithm for segmentation of choroidal blood vessels from ultrahigh resolution optical coherence images of rat retina

ABSTRACT Abnormal changes in choroidal blood flow have been linked to various retinal diseases, s... more ABSTRACT Abnormal changes in choroidal blood flow have been linked to various retinal diseases, such as Diabetic Retinopathy (DR) and Age related Macular Degeneration (AMD), which at later stages can lead to blindness. Therefore non-invasive and precise evaluation of choroidal blood flow can aid the diagnosis, treatment and monitoring of retinal disease progression.

Research paper thumbnail of KPAC: A kernel-based parametric active contour method for fast image segmentation

Abstract Object boundary detection has been a topic of keen interest to the signal processing and... more Abstract Object boundary detection has been a topic of keen interest to the signal processing and pattern recognition community. A popular approach for object boundary detection is parametric active contours. Existing parametric active contour approaches often suffer from slower convergence rates, difficulty dealing with complex high curvature boundaries, and are prone to being trapped in local optima in the presence of noise and background clutter.

Research paper thumbnail of Decoupled active contour (DAC) for boundary detection

Abstract The accurate detection of object boundaries via active contours is an ongoing research t... more Abstract The accurate detection of object boundaries via active contours is an ongoing research topic in computer vision. Most active contours converge toward some desired contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. Such an approach is elegant, but suffers from a slow convergence rate and frequently misconverges in the presence of noise or complex contours.

Research paper thumbnail of Sparse Reconstruction of Breast MRI using Homotopic $ L_0 $ Minimization in a Regional Sparsified Domain

Abstract The use of magnetic resonance imaging (MRI) for early breast examination and screening o... more Abstract The use of magnetic resonance imaging (MRI) for early breast examination and screening of asymptomatic women has become increasing popular, given its ability to provide detailed tissue characteristics that cannot be obtained using other imaging modalities such as mammography and ultrasound.

Research paper thumbnail of NONPARAMETRIC SAMPLE-BASED METHODS FOR IMAGE UNDERSTANDING

This chapter presents a nonparametric framework for image understanding based on models construct... more This chapter presents a nonparametric framework for image understanding based on models constructed via conditional sampling. Rather than modeling imaging data as a lattice of fixed values (one intensity per pixel), or as a set of parametric distributions (such as a Gaussian distribution), we explore the modeling of imaging data as a lattice of nonparametric conditional probability distributions estimated via random sampling.

Research paper thumbnail of Decoupled Deformable Model For 2D/3D Boundary Identification

Abstract: The accurate detection of static object boundaries such as contours or surfaces and dyn... more Abstract: The accurate detection of static object boundaries such as contours or surfaces and dynamic tunnels of moving objects via deformable models is an ongoing research topic in computer vision. Most deformable models attempt to converge towards a desired solution by minimizing the sum of internal (prior) and external (measurement) energy terms.

Research paper thumbnail of Intra-retinal layer segmentation in optical coherence tomography images

Abstract Retinal layer thickness, evaluated as a function of spatial position from optical cohere... more Abstract Retinal layer thickness, evaluated as a function of spatial position from optical coherence tomography (OCT) images is an important diagnostics marker for many retinal diseases. However, due to factors such as speckle noise, low image contrast, irregularly shaped morphological features such as retinal detachments, macular holes, and drusen, accurate segmentation of individual retinal layers is difficult. To address this issue, a computer method for retinal layer segmentation from OCT images is presented.

Research paper thumbnail of Improved interactive medical image segmentation using enhanced intelligent scissors (eis)

Abstract A novel interactive approach called Enhanced Intelligent Scissors (EIS) is presented for... more Abstract A novel interactive approach called Enhanced Intelligent Scissors (EIS) is presented for segmenting regions of interest in medical images. The proposed interactive medical image segmentation algorithm addresses the issues associated with segmenting medical images and allows for fast, robust, and flexible segmentation without requiring accurate manual tracing.

Research paper thumbnail of Robust snake convergence based on dynamic programming

Abstract The extraction of contours using deformable models, such as snakes, is a problem of grea... more Abstract The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes have been widely studied and many methods are available. In most cases, the snake converges towards the optimal contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. This approach is elegant, but frequently mis-converges in the presence of noise or complex contours.

Research paper thumbnail of A novel algorithm for extraction of the layers of the cornea

Abstract Accurate corneal layer boundary extraction from optical coherence tomograms can provide ... more Abstract Accurate corneal layer boundary extraction from optical coherence tomograms can provide precise layer thickness measurements required in the analysis of corneal disease. This paper establishes a novel approach to precisely obtain the five primary corneal layer boundaries. The proposed method determines correspondence relationships between the layer boundaries to facilitate robust boundary extraction in the presence of noise and artifacts.

Research paper thumbnail of Shape-guided active contour based segmentation and tracking of lumbar vertebrae in video fluoroscopy using complex wavelets

Abstract This paper presents a novel shape-guided active contour based approach for segmenting an... more Abstract This paper presents a novel shape-guided active contour based approach for segmenting and tracking lumbar vertebrae in video fluoroscopy using complex-valued wavelets. representations.

Research paper thumbnail of General Bayesian estimation for speckle noise reduction in optical coherence tomography retinal imagery

An important image post-processing step for optical coherence tomography (OCT) images is speckle ... more An important image post-processing step for optical coherence tomography (OCT) images is speckle noise reduction. Noise in OCT images is multiplicative in nature and is difficult to suppress due to the fact that in addition the noise component, OCT speckle also carries structural information about the imaged object. To address this issue, a novel speckle noise reduction algorithm was developed.

Research paper thumbnail of An adaptive Monte Carlo approach to nonlinear image denoising

Abstract This paper introduces a novel stochastic approach to image denoising using an adaptive M... more Abstract This paper introduces a novel stochastic approach to image denoising using an adaptive Monte Carlo scheme. Random samples are generated from the image field using a spatially-adaptive importance sampling approach. Samples are then represented using Gaussian probability distributions and a sample rejection scheme is performed based on a chi 2 statistical hypothesis test. The remaining samples are then aggregated based on Pearson Type VII statistics to create a non-linear estimate of the denoised image.

Research paper thumbnail of Evaluation of hypoxic swelling of human cornea with high speed, ultrahigh resolution optical coherence tomography

ABSTRACT Hypoxia induced corneal swelling was observed and evaluated in healthy human volunteers ... more ABSTRACT Hypoxia induced corneal swelling was observed and evaluated in healthy human volunteers by use of high speed, ultrahigh resolution optical coherence tomography (UHROCT). Two dimensional corneal images were acquired at a speed of 47,000 A-scans/s with 3µm x 10µm (axial x lateral) resolution in corneal tissue. The UHROCT tomograms showed clear visualization of all corneal layers, including the Bowman's layer and the Descemet's membrane–Endothelium complex.

Research paper thumbnail of Novel interactive approach to intra-retinal layer segmentation from optical coherence tomography images

Abstract: Retinal layer thickness, evaluated as a function of spatial position from optical coher... more Abstract: Retinal layer thickness, evaluated as a function of spatial position from optical coherence tomography (OCT) images is an important diagnostics marker for many retinal diseases. However, due to factors such as speckle noise, low image contrast, irregularly shaped morphological features such as retinal detachments, macular holes, and drusen, accurate segmentation of individual retinal layers is difficult.

Research paper thumbnail of Stochastic image denoising based on Markov-chain Monte Carlo sampling

Abstract A novel stochastic approach based on Markov-chain Monte Carlo sampling is investigated f... more Abstract A novel stochastic approach based on Markov-chain Monte Carlo sampling is investigated for the purpose of image denoising. The additive image denoising problem is formulated as a Bayesian least squares problem, where the goal is to estimate the denoised image given the noisy image as the measurement and an estimated posterior. The posterior is estimated using a nonparametric importance-weighted Markov-chain Monte Carlo sampling approach based on an adaptive Geman–McClure objective function.

Research paper thumbnail of VizDraw: A Platform to Convert Online Hand-Drawn Graphics into Computer Graphics

Abstract. With the adoption of tablet-based data entry devices, there is considerable interest in... more Abstract. With the adoption of tablet-based data entry devices, there is considerable interest in methods for converting hand-drawn sketches of flow charts, graphs and block diagram into accurate machine interpretations, a conversion process with many applications in engineering, presentations, and simulations. However, the recognition of hand-drawn graphics is a great challenge due to the visual similarity of many system components. This is complicated due to the significant differences in drawing styles between users.

Research paper thumbnail of A Robust Modular Wavelet Network Based Symbol Classifier

Abstract. This paper presents a robust automatic shape classifier using modular wavelet networks ... more Abstract. This paper presents a robust automatic shape classifier using modular wavelet networks (MWNs). A shape descriptor is constructed based on a combination of global geometric features (modified Zernike moments and circularity features) and local intensity features (ordered histogram of image gradient orientations). The proposed method utilizes a supervised modular wavelet network to perform shape classification based on the extracted shape descriptors.

Research paper thumbnail of Accurate boundary localization using dynamic programming on snakes

Abstract The extraction of contours using deformable models, such as snakes, is a problem of grea... more Abstract The extraction of contours using deformable models, such as snakes, is a problem of great interest in computer vision, particular in areas of medical imaging and tracking. Snakes have been widely studied, and many methods are available. In most cases, the snake converges towards the optimal contour by minimizing a sum of internal (prior) and external (image measurement) energy terms. This approach is elegant, but frequently mis-converges in the presence of noise or complex contours.

Research paper thumbnail of Decoupled Active Surface for Volumetric Image Segmentation

Abstract Finding the surface of a volumetric 3D object is a fundamental problem in computer visio... more Abstract Finding the surface of a volumetric 3D object is a fundamental problem in computer vision. Energy minimizing splines, such as active surfaces, have been used to carry out such tasks, evolving under the influence of internal and external energies until the model converges to a desired surface. The present deformable model based surface extraction techniques are computationally expensive and are generally unreliable in identifying the surfaces of noisy, high-curvature and cluttered 3D objects.

Research paper thumbnail of A cellular automata based semi-automatic algorithm for segmentation of choroidal blood vessels from ultrahigh resolution optical coherence images of rat retina

ABSTRACT Abnormal changes in choroidal blood flow have been linked to various retinal diseases, s... more ABSTRACT Abnormal changes in choroidal blood flow have been linked to various retinal diseases, such as Diabetic Retinopathy (DR) and Age related Macular Degeneration (AMD), which at later stages can lead to blindness. Therefore non-invasive and precise evaluation of choroidal blood flow can aid the diagnosis, treatment and monitoring of retinal disease progression.

Research paper thumbnail of KPAC: A kernel-based parametric active contour method for fast image segmentation

Abstract Object boundary detection has been a topic of keen interest to the signal processing and... more Abstract Object boundary detection has been a topic of keen interest to the signal processing and pattern recognition community. A popular approach for object boundary detection is parametric active contours. Existing parametric active contour approaches often suffer from slower convergence rates, difficulty dealing with complex high curvature boundaries, and are prone to being trapped in local optima in the presence of noise and background clutter.