Anomaly Detection in Noisy Images

Finding rare events in multidimensional data is an important detection problem that has applications in many fields, such as risk estimation in insurance industry, finance, flood prediction, medical diagnosis, quality assurance, security, or safety in transportation. The occurrence of such anomalies is so infrequent that there is usually not enough training data to learn an accurate statistical model of the anomaly class. In some cases, such events may have never been observed, so the only information that is available is a set of normal samples and an assumed pairwise similarity function. Such metric may only be known up to a certain number of unspecified parameters, which would either need to be learned from training data, or fixed by a domain expert. Sometimes, the anomalous condition may be formulated algebraically, such as a measure exceeding a predefined threshold, but nuisance variables may complicate the estimation of such a measure. Change detection methods used in time series analysis are not easily extendable to the multidimensional case, where discontinuities are not localized to a single point. On the other hand, in higher dimensions, data exhibits more complex interdependencies, and there is redundancy that could be exploited to adaptively model the normal data. In the first part of this dissertation, we review the theoretical framework for anomaly detection in images and previous anomaly detection work done in the context of crack detection and detection of anomalous components in railway tracks. In the second part, we propose new anomaly detection algorithms. The fact that curvilinear discontinuities in images are sparse with respect to the frame of shearlets, allows us to pose this anomaly detection problem as basis pursuit optimization. Therefore, we pose the problem of detecting curvilinear anomalies in noisy textured images as a blind source separation problem under sparsity constraints, and propose an iterative shrinkage algorithm to solve it. Taking advantage of the parallel nature of this algorithm, we describe how this method can be accelerated using graphical processing units (GPU). Then, we propose a new method for finding defective components on railway tracks using cameras mounted on a train. We describe how to extract features and use a combination of classifiers to solve this problem. Then, we scale anomaly detection to bigger datasets with complex interdependencies. We show that the anomaly detection problem naturally fits in the multitask learning framework. The first task consists of learning a compact representation of the good samples, while the second task consists of learning the anomaly detector. Using deep convolutional neural networks, we show that it is possible to train a deep model with a limited number of anomalous examples. In sequential detection problems, the presence of time-variant nuisance parameters affect the detection performance. In the last part of this dissertation, we present a method for adaptively estimating the threshold of sequential detectors using Extreme Value Theory on a Bayesian framework. Finally, conclusions on the results obtained are provided, followed by a discussion of possible future work.

MICROFLUIDIC ASSAY PERFORMANCE ENHANCEMENT USING POROUS VOLUMETRIC DETECTION ELEMENTS FOR IMPEDEMETRIC AND OPTICAL SENSING

Microfluidic technologies have great potential to help create automated, cost-effective, portable devices for rapid point of care (POC) diagnostics in diverse patient settings. Unfortunately commercialization is currently constrained by the materials, reagents, and instrumentation required and detection element performance. While most microfluidic studies utilize planar detection elements, this dissertation demonstrates the utility of porous volumetric detection elements to improve detection sensitivity and reduce assay times. Impedemetric immunoassays were performed utilizing silver enhanced gold nanoparticle immunoconjugates (AuIgGs) and porous polymer monolith or silica bead bed detection elements within a thermoplastic microchannel. For a direct assay with 10 µm spaced electrodes the detection limit was 0.13 fM AuIgG with a 3 log dynamic range. The same assay was performed with electrode spacing of 15, 40, and 100 µm with no significant difference between configurations. For a sandwich assay the detection limit was10 ng/mL with a 4 log dynamic range. While most impedemetric assays rely on expensive high resolution electrodes to enhance planar senor performance, this study demonstrates the employment of porous volumetric detection elements to achieve similar performance using lower resolution electrodes and shorter incubation times. Optical immunoassays were performed using porous volumetric capture elements perfused with refractive index matching solutions to limit light scattering and enhance signal. First, fluorescence signal enhancement was demonstrated with a porous polymer monolith within a silica capillary. Next, transmission enhancement of a direct assay was demonstrated by infusing aqueous sucrose solutions through silica bead beds with captured silver enhanced AuIgGs yielding a detection limit of 0.1 ng/mL and a 5 log dynamic range. Finally, ex situ functionalized porous silica monolith segments were integrated into thermoplastic channels for a reflectance based sandwich assay yielding a detection limit of 1 ng/mL and a 5 log dynamic range. The simple techniques for optical signal enhancement and ex situ element integration enable development of sensitive, multiplexed microfluidic sensors. Collectively the demonstrated experiments validate the use of porous volumetric detection elements to enhance impedemetric and optical microfluidic assays. The techniques rely on commercial reagents, materials compatible with manufacturing, and measurement instrumentation adaptable to POC diagnostics.

Efficient Image and Video Representations for Retrieval

Image (Video) retrieval is an interesting problem of retrieving images (videos) similar to the query. Images (Videos) are represented in an input (feature) space and similar images (videos) are obtained by finding nearest neighbors in the input representation space. Numerous input representations both in real valued and binary space have been proposed for conducting faster retrieval. In this thesis, we present techniques that obtain improved input representations for retrieval in both supervised and unsupervised settings for images and videos. Supervised retrieval is a well known problem of retrieving same class images of the query. We address the practical aspects of achieving faster retrieval with binary codes as input representations for the supervised setting in the first part, where binary codes are used as addresses into hash tables. In practice, using binary codes as addresses does not guarantee fast retrieval, as similar images are not mapped to the same binary code (address). We address this problem by presenting an efficient supervised hashing (binary encoding) method that aims to explicitly map all the images of the same class ideally to a unique binary code. We refer to the binary codes of the images as `Semantic Binary Codes' and the unique code for all same class images as `Class Binary Code'. We also propose a new class­ based Hamming metric that dramatically reduces the retrieval times for larger databases, where only hamming distance is computed to the class binary codes. We also propose a Deep semantic binary code model, by replacing the output layer of a popular convolutional Neural Network (AlexNet) with the class binary codes and show that the hashing functions learned in this way outperforms the state­ of ­the art, and at the same time provide fast retrieval times. In the second part, we also address the problem of supervised retrieval by taking into account the relationship between classes. For a given query image, we want to retrieve images that preserve the relative order i.e. we want to retrieve all same class images first and then, the related classes images before different class images. We learn such relationship aware binary codes by minimizing the similarity between inner product of the binary codes and the similarity between the classes. We calculate the similarity between classes using output embedding vectors, which are vector representations of classes. Our method deviates from the other supervised binary encoding schemes as it is the first to use output embeddings for learning hashing functions. We also introduce new performance metrics that take into account the related class retrieval results and show significant gains over the state­ of­ the art. High Dimensional descriptors like Fisher Vectors or Vector of Locally Aggregated Descriptors have shown to improve the performance of many computer vision applications including retrieval. In the third part, we will discuss an unsupervised technique for compressing high dimensional vectors into high dimensional binary codes, to reduce storage complexity. In this approach, we deviate from adopting traditional hyperplane hashing functions and instead learn hyperspherical hashing functions. The proposed method overcomes the computational challenges of directly applying the spherical hashing algorithm that is intractable for compressing high dimensional vectors. A practical hierarchical model that utilizes divide and conquer techniques using the Random Select and Adjust (RSA) procedure to compress such high dimensional vectors is presented. We show that our proposed high dimensional binary codes outperform the binary codes obtained using traditional hyperplane methods for higher compression ratios. In the last part of the thesis, we propose a retrieval based solution to the Zero shot event classification problem - a setting where no training videos are available for the event. To do this, we learn a generic set of concept detectors and represent both videos and query events in the concept space. We then compute similarity between the query event and the video in the concept space and videos similar to the query event are classified as the videos belonging to the event. We show that we significantly boost the performance using concept features from other modalities.

A NOVEL NON-LETHAL LAPAROSCOPIC APPROACH TO DETECT INTERSEX (TESTICULAR OOCYTES) IN LARGEMOUTH BASS (MICROPTERUS SALMOIDES) AND SMALLMOUTH BASS (MICROPTERUS DOLOMIEU)

The appearance of testicular oocytes (TO) in wild fish populations has received considerable attention in the scientific literature and public media. Current methods to quantify TO are lethal; instead, a non-lethal alternative was examined. Laparoscopic insertion into the genital pore allowed internal visualization of the gonad and detection of TO by collecting five testis biopsies in smallmouth bass Micropterus dolomieu and largemouth bass Micropterus salmoides. Overall, biopsies quantified similar levels of TO detection and severity to conventional transverse sectioning with less than 10% mortality. Suitability of surgical anesthetics, tricaine methanesulfonate and electronarcosis were examined in laboratory and field applications. Electronarcosis had the added benefit of rapid sex identification and immediate release of female fish with minimal trauma, representing significant benefits when sampling small or compromised populations. Laparoscopy may be useful for monitoring the prevalence and severity of TO in these fish species when lethal sampling is not a desired outcome.

Generating Discriminative Objective Proposals via Submodular Ranking

Object recognition has long been a core problem in computer vision. To improve object spatial support and speed up object localization for object recognition, generating high-quality category-independent object proposals as the input for object recognition system has drawn attention recently. Given an image, we generate a limited number of high-quality and category-independent object proposals in advance and used as inputs for many computer vision tasks. We present an efficient dictionary-based model for image classification task. We further extend the work to a discriminative dictionary learning method for tensor sparse coding. In the first part, a multi-scale greedy-based object proposal generation approach is presented. Based on the multi-scale nature of objects in images, our approach is built on top of a hierarchical segmentation. We first identify the representative and diverse exemplar clusters within each scale. Object proposals are obtained by selecting a subset from the multi-scale segment pool via maximizing a submodular objective function, which consists of a weighted coverage term, a single-scale diversity term and a multi-scale reward term. The weighted coverage term forces the selected set of object proposals to be representative and compact; the single-scale diversity term encourages choosing segments from different exemplar clusters so that they will cover as many object patterns as possible; the multi-scale reward term encourages the selected proposals to be discriminative and selected from multiple layers generated by the hierarchical image segmentation. The experimental results on the Berkeley Segmentation Dataset and PASCAL VOC2012 segmentation dataset demonstrate the accuracy and efficiency of our object proposal model. Additionally, we validate our object proposals in simultaneous segmentation and detection and outperform the state-of-art performance. To classify the object in the image, we design a discriminative, structural low-rank framework for image classification. We use a supervised learning method to construct a discriminative and reconstructive dictionary. By introducing an ideal regularization term, we perform low-rank matrix recovery for contaminated training data from all categories simultaneously without losing structural information. A discriminative low-rank representation for images with respect to the constructed dictionary is obtained. With semantic structure information and strong identification capability, this representation is good for classification tasks even using a simple linear multi-classifier.