Matching Items (25)
Filtering by
- All Subjects: Computer vision
- Genre: Academic theses
- Genre: Masters Thesis
- Creators: Li, Baoxin
Description
With the introduction of compressed sensing and sparse representation,many image processing and computer vision problems have been looked at in a new way. Recent trends indicate that many challenging computer vision and image processing problems are being solved using compressive sensing and sparse representation algorithms. This thesis assays some applications of compressive sensing and sparse representation with regards to image enhancement, restoration and classication. The first application deals with image Super-Resolution through compressive sensing based sparse representation. A novel framework is developed for understanding and analyzing some of the implications of compressive sensing in reconstruction and recovery of an image through raw-sampled and trained dictionaries. Properties of the projection operator and the dictionary are examined and the corresponding results presented. In the second application a novel technique for representing image classes uniquely in a high-dimensional space for image classification is presented. In this method, design and implementation strategy of the image classification system through unique affine sparse codes is presented, which leads to state of the art results. This further leads to analysis of some of the properties attributed to these unique sparse codes. In addition to obtaining these codes, a strong classier is designed and implemented to boost the results obtained. Evaluation with publicly available datasets shows that the proposed method outperforms other state of the art results in image classication. The final part of the thesis deals with image denoising with a novel approach towards obtaining high quality denoised image patches using only a single image. A new technique is proposed to obtain highly correlated image patches through sparse representation, which are then subjected to matrix completion to obtain high quality image patches. Experiments suggest that there may exist a structure within a noisy image which can be exploited for denoising through a low-rank constraint.
ContributorsKulkarni, Naveen (Author) / Li, Baoxin (Thesis advisor) / Ye, Jieping (Committee member) / Sen, Arunabha (Committee member) / Arizona State University (Publisher)
Created2011
Description
Surgery as a profession requires significant training to improve both clinical decision making and psychomotor proficiency. In the medical knowledge domain, tools have been developed, validated, and accepted for evaluation of surgeons' competencies. However, assessment of the psychomotor skills still relies on the Halstedian model of apprenticeship, wherein surgeons are observed during residency for judgment of their skills. Although the value of this method of skills assessment cannot be ignored, novel methodologies of objective skills assessment need to be designed, developed, and evaluated that augment the traditional approach. Several sensor-based systems have been developed to measure a user's skill quantitatively, but use of sensors could interfere with skill execution and thus limit the potential for evaluating real-life surgery. However, having a method to judge skills automatically in real-life conditions should be the ultimate goal, since only with such features that a system would be widely adopted. This research proposes a novel video-based approach for observing surgeons' hand and surgical tool movements in minimally invasive surgical training exercises as well as during laparoscopic surgery. Because our system does not require surgeons to wear special sensors, it has the distinct advantage over alternatives of offering skills assessment in both learning and real-life environments. The system automatically detects major skill-measuring features from surgical task videos using a computing system composed of a series of computer vision algorithms and provides on-screen real-time performance feedback for more efficient skill learning. Finally, the machine-learning approach is used to develop an observer-independent composite scoring model through objective and quantitative measurement of surgical skills. To increase effectiveness and usability of the developed system, it is integrated with a cloud-based tool, which automatically assesses surgical videos upload to the cloud.
ContributorsIslam, Gazi (Author) / Li, Baoxin (Thesis advisor) / Liang, Jianming (Thesis advisor) / Dinu, Valentin (Committee member) / Greenes, Robert (Committee member) / Smith, Marshall (Committee member) / Kahol, Kanav (Committee member) / Patel, Vimla L. (Committee member) / Arizona State University (Publisher)
Created2013
Description
Diabetic retinopathy (DR) is a common cause of blindness occurring due to prolonged presence of diabetes. The risk of developing DR or having the disease progress is increasing over time. Despite advances in diabetes care over the years, DR remains a vision-threatening complication and one of the leading causes of blindness among American adults. Recent studies have shown that diagnosis based on digital retinal imaging has potential benefits over traditional face-to-face evaluation. Yet there is a dearth of computer-based systems that can match the level of performance achieved by ophthalmologists. This thesis takes a fresh perspective in developing a computer-based system aimed at improving diagnosis of DR images. These images are categorized into three classes according to their severity level. The proposed approach explores effective methods to classify new images and retrieve clinically-relevant images from a database with prior diagnosis information associated with them. Retrieval provides a novel way to utilize the vast knowledge in the archives of previously-diagnosed DR images and thereby improve a clinician's performance while classification can safely reduce the burden on DR screening programs and possibly achieve higher detection accuracy than human experts. To solve the three-class retrieval and classification problem, the approach uses a multi-class multiple-instance medical image retrieval framework that makes use of spectrally tuned color correlogram and steerable Gaussian filter response features. The results show better retrieval and classification performances than prior-art methods and are also observed to be of clinical and visual relevance.
ContributorsChandakkar, Parag Shridhar (Author) / Li, Baoxin (Thesis advisor) / Turaga, Pavan (Committee member) / Frakes, David (Committee member) / Arizona State University (Publisher)
Created2012
Description
Video object segmentation (VOS) is an important task in computer vision with a lot of applications, e.g., video editing, object tracking, and object based encoding. Different from image object segmentation, video object segmentation must consider both spatial and temporal coherence for the object. Despite extensive previous work, the problem is still challenging. Usually, foreground object in the video draws more attention from humans, i.e. it is salient. In this thesis we tackle the problem from the aspect of saliency, where saliency means a certain subset of visual information selected by a visual system (human or machine). We present a novel unsupervised method for video object segmentation that considers both low level vision cues and high level motion cues. In our model, video object segmentation can be formulated as a unified energy minimization problem and solved in polynomial time by employing the min-cut algorithm. Specifically, our energy function comprises the unary term and pair-wise interaction energy term respectively, where unary term measures region saliency and interaction term smooths the mutual effects between object saliency and motion saliency. Object saliency is computed in spatial domain from each discrete frame using multi-scale context features, e.g., color histogram, gradient, and graph based manifold ranking. Meanwhile, motion saliency is calculated in temporal domain by extracting phase information of the video. In the experimental section of this thesis, our proposed method has been evaluated on several benchmark datasets. In MSRA 1000 dataset the result demonstrates that our spatial object saliency detection is superior to the state-of-art methods. Moreover, our temporal motion saliency detector can achieve better performance than existing motion detection approaches in UCF sports action analysis dataset and Weizmann dataset respectively. Finally, we show the attractive empirical result and quantitative evaluation of our approach on two benchmark video object segmentation datasets.
ContributorsWang, Yilin (Author) / Li, Baoxin (Thesis advisor) / Wang, Yalin (Committee member) / Cleveau, David (Committee member) / Arizona State University (Publisher)
Created2013
Description
Facial Expressions Recognition using the Convolution Neural Network has been actively researched upon in the last decade due to its high number of applications in the human-computer interaction domain. As Convolution Neural Networks have the exceptional ability to learn, they outperform the methods using handcrafted features. Though the state-of-the-art models achieve high accuracy on the lab-controlled images, they still struggle for the wild expressions. Wild expressions are captured in a real-world setting and have natural expressions. Wild databases have many challenges such as occlusion, variations in lighting conditions and head poses. In this work, I address these challenges and propose a new model containing a Hybrid Convolutional Neural Network with a Fusion Layer. The Fusion Layer utilizes a combination of the knowledge obtained from two different domains for enhanced feature extraction from the in-the-wild images. I tested my network on two publicly available in-the-wild datasets namely RAF-DB and AffectNet. Next, I tested my trained model on CK+ dataset for the cross-database evaluation study. I prove that my model achieves comparable results with state-of-the-art methods. I argue that it can perform well on such datasets because it learns the features from two different domains rather than a single domain. Last, I present a real-time facial expression recognition system as a part of this work where the images are captured in real-time using laptop camera and passed to the model for obtaining a facial expression label for it. It indicates that the proposed model has low processing time and can produce output almost instantly.
ContributorsChhabra, Sachin (Author) / Li, Baoxin (Thesis advisor) / Venkateswara, Hemanth (Committee member) / Srivastava, Siddharth (Committee member) / Arizona State University (Publisher)
Created2019
Description
Increased LV wall thickness is frequently encountered in transthoracicechocardiography (TTE). While accurate and early diagnosis is clinically important,
given the differences in available therapeutic options and prognosis, an extensive workup
is often required for establishing the diagnosis. I propose the first echo-based, automated
deep learning model with a fusion architecture to facilitate the evaluation and diagnosis
of increased left ventricular (LV) wall thickness. Patients with an established diagnosis
for increased LV wall thickness (hypertrophic cardiomyopathy (HCM), cardiac
amyloidosis (CA), and hypertensive heart disease (HTN)/others) between 1/2015 to
11/2019 at Mayo Clinic Arizona were identified. The cohort was divided into
80%/10%/10% for training, validation, and testing sets, respectively. Six baseline TTE
views were used to optimize a pre-trained InceptionResnetV2 model, each model output
was used to train a meta-learner under a fusion architecture. Model performance was
assessed by multiclass area under the receiver operating characteristic curve (AUROC).
A total of 586 patients were used for the final analysis (194 HCM, 201 CA, and 191
HTN/others). The mean age was 55.0 years, and 57.8% were male. Among the individual
view-dependent models, the apical 4 chamber model had the best performance (AUROC:
HCM: 0.94, CA: 0.73, and HTN/other: 0.87). The final fusion model outperformed all the
view-dependent models (AUROC: CA: 0.90, HCM: 0.93, and HTN/other: 0.92). I
successfully established an automatic end-to-end deep learning model framework that
accurately differentiates the major etiologies of increased LV wall thickness, including
HCM and CA from the background of HTN/other diagnoses.
ContributorsLi, James Shuyue (Author) / Patel, Bhavik (Thesis advisor) / Li, Baoxin (Thesis advisor) / Banerjee, Imon (Committee member) / Arizona State University (Publisher)
Created2022
Description
This dissertation presents novel solutions for improving the generalization capabilities of deep learning based computer vision models. Neural networks are known to suffer a large drop in performance when tested on samples from a different distribution than the one on which they were trained. The proposed solutions, based on latent space geometry and meta-learning, address this issue by improving the robustness of these models to distribution shifts. Through the use of geometrical alignment, state-of-the-art domain adaptation and source-free test-time adaptation strategies are developed. Additionally, geometrical alignment can allow classifiers to be progressively adapted to new, unseen test domains without requiring retraining of the feature extractors. The dissertation also presents algorithms for enabling in-the-wild generalization without needing access to any samples from the target domain. Other causes of poor generalization, such as data scarcity in critical applications and training data with high levels of noise and variance, are also explored. To address data scarcity in fine-grained computer vision tasks such as object detection, novel context-aware augmentations are suggested. While the first four chapters focus on general-purpose computer vision models, strategies are also developed to improve robustness in specific applications. The efficiency of training autonomous agents for visual navigation is improved by incorporating semantic knowledge, and the integration of domain experts' knowledge allows for the realization of a low-cost, minimally invasive generalizable automated rehabilitation system. Lastly, new tools for explainability and model introspection using counter-factual explainers trained through interval-based uncertainty calibration objectives are presented.
ContributorsThopalli, Kowshik (Author) / Turaga, Pavan (Thesis advisor) / Thiagarajan, Jayaraman J (Committee member) / Li, Baoxin (Committee member) / Yang, Yezhou (Committee member) / Arizona State University (Publisher)
Created2023
Description
Image denoising, a fundamental task in computer vision, poses significant challenges due to its inherently inverse and ill-posed nature. Despite advancements in traditional methods and supervised learning approaches, particularly in medical imaging such as Medical Resonance Imaging (MRI) scans, the reliance on paired datasets and known noise distributions remains a practical hurdle. Recent progress in noise statistical independence theory and diffusion models has revitalized research interest, offering promising avenues for unsupervised denoising. However, existing methods often yield overly smoothed results or introduce hallucinated structures, limiting their clinical applicability. This thesis tackles the core challenge of progressing towards unsupervised denoising of MRI scans. It aims to retain intricate details without smoothing or introducing artificial structures, thus ensuring the production of high-quality MRI images. The thesis makes a three-fold contribution: Firstly, it presents a detailed analysis of traditional techniques, early machine learning algorithms for denoising, and new statistical-based models, with an extensive evaluation study on self-supervised denoising methods highlighting their limitations. Secondly, it conducts an evaluation study on an emerging class of diffusion-based denoising methods, accompanied by additional empirical findings and discussions on their effectiveness and limitations, proposing solutions to enhance their utility. Lastly, it introduces a novel approach, Unsupervised Multi-stage Ensemble Deep Learning with diffusion models for denoising MRI scans (MEDL). Leveraging diffusion models, this approach operates independently of signal or noise priors and incorporates weighted rescaling of multi-stage reconstructions to balance over-smoothing and hallucination tendencies. Evaluation using benchmark datasets demonstrates an average gain of 1dB and 2% in PSNR and SSIM metrics, respectively, over existing approaches.
ContributorsVora, Sahil (Author) / Li, Baoxin (Thesis advisor) / Wang, Yalin (Committee member) / Zhou, Yuxiang (Committee member) / Arizona State University (Publisher)
Created2024
Description
Computer vision technology automatically extracts high level, meaningful information from visual data such as images or videos, and the object recognition and detection algorithms are essential in most computer vision applications. In this dissertation, we focus on developing algorithms used for real life computer vision applications, presenting innovative algorithms for object segmentation and feature extraction for objects and actions recognition in video data, and sparse feature selection algorithms for medical image analysis, as well as automated feature extraction using convolutional neural network for blood cancer grading.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
To detect and classify objects in video, the objects have to be separated from the background, and then the discriminant features are extracted from the region of interest before feeding to a classifier. Effective object segmentation and feature extraction are often application specific, and posing major challenges for object detection and classification tasks. In this dissertation, we address effective object flow based ROI generation algorithm for segmenting moving objects in video data, which can be applied in surveillance and self driving vehicle areas. Optical flow can also be used as features in human action recognition algorithm, and we present using optical flow feature in pre-trained convolutional neural network to improve performance of human action recognition algorithms. Both algorithms outperform the state-of-the-arts at their time.
Medical images and videos pose unique challenges for image understanding mainly due to the fact that the tissues and cells are often irregularly shaped, colored, and textured, and hand selecting most discriminant features is often difficult, thus an automated feature selection method is desired. Sparse learning is a technique to extract the most discriminant and representative features from raw visual data. However, sparse learning with \textit{L1} regularization only takes the sparsity in feature dimension into consideration; we improve the algorithm so it selects the type of features as well; less important or noisy feature types are entirely removed from the feature set. We demonstrate this algorithm to analyze the endoscopy images to detect unhealthy abnormalities in esophagus and stomach, such as ulcer and cancer. Besides sparsity constraint, other application specific constraints and prior knowledge may also need to be incorporated in the loss function in sparse learning to obtain the desired results. We demonstrate how to incorporate similar-inhibition constraint, gaze and attention prior in sparse dictionary selection for gastroscopic video summarization that enable intelligent key frame extraction from gastroscopic video data. With recent advancement in multi-layer neural networks, the automatic end-to-end feature learning becomes feasible. Convolutional neural network mimics the mammal visual cortex and can extract most discriminant features automatically from training samples. We present using convolutinal neural network with hierarchical classifier to grade the severity of Follicular Lymphoma, a type of blood cancer, and it reaches 91\% accuracy, on par with analysis by expert pathologists.
Developing real world computer vision applications is more than just developing core vision algorithms to extract and understand information from visual data; it is also subject to many practical requirements and constraints, such as hardware and computing infrastructure, cost, robustness to lighting changes and deformation, ease of use and deployment, etc.The general processing pipeline and system architecture for the computer vision based applications share many similar design principles and architecture. We developed common processing components and a generic framework for computer vision application, and a versatile scale adaptive template matching algorithm for object detection. We demonstrate the design principle and best practices by developing and deploying a complete computer vision application in real life, building a multi-channel water level monitoring system, where the techniques and design methodology can be generalized to other real life applications. The general software engineering principles, such as modularity, abstraction, robust to requirement change, generality, etc., are all demonstrated in this research.
ContributorsCao, Jun (Author) / Li, Baoxin (Thesis advisor) / Liu, Huan (Committee member) / Zhang, Yu (Committee member) / Zhang, Junshan (Committee member) / Arizona State University (Publisher)
Created2018
Description
Mixture of experts is a machine learning ensemble approach that consists of individual models that are trained to be ``experts'' on subsets of the data, and a gating network that provides weights to output a combination of the expert predictions. Mixture of experts models do not currently see wide use due to difficulty in training diverse experts and high computational requirements. This work presents modifications of the mixture of experts formulation that use domain knowledge to improve training, and incorporate parameter sharing among experts to reduce computational requirements.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
First, this work presents an application of mixture of experts models for quality robust visual recognition. First it is shown that human subjects outperform deep neural networks on classification of distorted images, and then propose a model, MixQualNet, that is more robust to distortions. The proposed model consists of ``experts'' that are trained on a particular type of image distortion. The final output of the model is a weighted sum of the expert models, where the weights are determined by a separate gating network. The proposed model also incorporates weight sharing to reduce the number of parameters, as well as increase performance.
Second, an application of mixture of experts to predict visual saliency is presented. A computational saliency model attempts to predict where humans will look in an image. In the proposed model, each expert network is trained to predict saliency for a set of closely related images. The final saliency map is computed as a weighted mixture of the expert networks' outputs, with weights determined by a separate gating network. The proposed model achieves better performance than several other visual saliency models and a baseline non-mixture model.
Finally, this work introduces a saliency model that is a weighted mixture of models trained for different levels of saliency. Levels of saliency include high saliency, which corresponds to regions where almost all subjects look, and low saliency, which corresponds to regions where some, but not all subjects look. The weighted mixture shows improved performance compared with baseline models because of the diversity of the individual model predictions.
ContributorsDodge, Samuel Fuller (Author) / Karam, Lina (Thesis advisor) / Jayasuriya, Suren (Committee member) / Li, Baoxin (Committee member) / Turaga, Pavan (Committee member) / Arizona State University (Publisher)
Created2018