A comparative study of preprocessing mismatch effects in color image based face recognition

Advances in structural finite element analysis (FEA) and medical imaging have made it possible to investigate the in vivo biomechanics of human organs such as blood vessels, for which organ geometries at the zero-pressure level need to be recovered. Although FEA-based inverse methods are available for zero-pressure geometry estimation, these methods typically require iterative computation, which are time-consuming and may be not suitable for time-sensitive clinical applications. In this study, by using machine learning (ML) techniques, we developed an ML model to estimate the zero-pressure geometry of human thoracic aorta given 2 pressurized geometries of the same patient at 2 different blood pressure levels. For the ML model development, a FEA-based method was used to generate a dataset of aorta geometries of 3125 virtual patients. The ML model, which was trained and tested on the dataset, is capable of recovering zero-pressure geometries consistent with those generated by the FEA-based method. Thus, this study demonstrates the feasibility and great potential of using ML techniques as a fast surrogate of FEA-based inverse methods to recover zero-pressure geometries of human organs.

A machine learning approach as a surrogate of finite element analysis–based inverse method to estimate the zero-pressure geometry of human thoracic aorta

A mixed intelligent condition monitoring method for nuclear power plant

Computational modeling of visual attention is an active area of research. These models have been successfully employed in applications such as robotics. However, most computational models of visual attention are developed in the context of natural scenes, and their role with medical images is not well investigated. As radiologists interpret a large number of clinical images in a limited time, an efficient strategy to deploy their visual attention is necessary. Visual saliency maps, highlighting image regions that differ dramatically from their surroundings, are expected to be predictive of where radiologists fixate their gaze. We compared 16 state-of-art saliency models over three medical imaging modalities. The estimated saliency maps were evaluated against radiologists' eye movements. The results show that the models achieved competitive accuracy using three metrics, but the rank order of the models varied significantly across the three modalities. Moreover, the model ranks on the medical images were all considerably different from the model ranks on the benchmark MIT300 dataset of natural images. Thus, modality-specific tuning of saliency models is necessary to make them valuable for applications in fields such as medical image compression and radiology education.

/pdf/comparative-study-of-computational-visual-attention-models-2g0f0tqggr.pdf

Comparative study of computational visual attention models on two-dimensional medical images.

In this paper, we propose a new color face recognition (FR) method which effectively employs feature selection algorithm in order to find the set of optimal color components (from various color models) for FR purpose. The proposed FR method is also designed to improve FR accuracy by combining the selected color components at the feature level. The effectiveness of the proposed color FR method has been successfully demonstrated using two public CMU-PIE and Color FERET face databases (DB). In our comparative experiments, traditional grayscale-based FR, previous color-based FR, and popular local binary pattern (LBP) based FR methods were compared with the proposed method. Experimental results show that our color FR method performs better than the aforementioned three different FR approaches. In particular, the proposed method can achieve 7.81% and 18.57% improvement in FR performance on the CMU-PIE and Color FERET DB, respectively, compared to representative color-based FR solutions previously developed.

/pdf/color-component-feature-selection-in-feature-level-fusion-cu0r5ycih7.pdf

Color component feature selection in feature-level fusion based color face recognition

In this work we study the landscape of squared loss of an Autoencoder when the data generative model is that of “Sparse Coding”/“Dictionary Learning”. The neural net considered is an $\mathbb{R}^{n}\rightarrow \mathbb{R}^{n}$ mapping and has a single ReLU activation layer of size $h > n$ . The net has access to vectors $y\in \mathbb{R}^{n}$ obtained as $y=A^{\ast}x^{\ast}$ where $x^{\ast}\in \mathbb{R}^{h}$ are sparse high dimensional vectors and $A^{\ast}\in \mathbb{R}^{n\times h}$ is an overcomplete incoherent matrix. Under very mild distributional assumptions on $x^{\ast}$ , we prove that the norm of the expected gradient of the squared loss function is asymptotically (in sparse code dimension) negligible for all points in a small neighborhood of $A^{\ast}$ . This is supported with experimental evidence using synthetic data. We conduct experiments to suggest that $A^{\ast}$ sits at the bottom of a well in the landscape and we also give experiments showing that gradient descent on this loss function gets columnwise very close to the original dictionary even with far enough initialization. Along the way we prove that a layer of ReLU gates can be set up to automatically recover the support of the sparse codes. Since this property holds independent of the loss function we believe that it could be of independent interest. A full version of this paper is accessible at: https://arxiv.org/abs/1708.03735

Sparse Coding and Autoencoders

Network traffic data associated with data requests to computer applications based on static policies is collected. An optimization order is established among network parameters. A first network parameter of a higher rank in the optimization order is estimated based on the collected network traffic data before one or more other network parameters of lower ranks are estimated. Optimal values for the other network parameters are estimated based at least in part on the estimated first optimal value for the first network parameter. The estimated first optimal value of the first network parameter and the estimated optimal values for the other network parameters are propagated to be used by user devices to make new data requests to the computer applications.

Simultaneous optimization of multiple TCP parameters to improve download outcomes for network-based mobile applications

An adaptive multi-phase approach to estimating network parameters is presented. By gathering and aggregating raw network traffic data and comparing against default network parameters, a training data set may be generated. A black box optimization may be used in tandem with a supervised learning algorithm to bias towards better choices and eventually pick network parameters which optimize performance. Data delivery strategies are applied to deliver content using the optimized network policies based on the estimated parameters.

Adaptive multi-phase network policy optimization

The goal of this study was to assess if stereoscopic viewing of breast tomosynthesis projection images impacted mass
detection performance when compared to monoscopic viewing. The dataset for this study, provided by Hologic, Inc.,
contained 47 craniocaudal cases (23 biopsy proven malignant masses and 24 normals). Two projection images that were
separated by 8 degrees were chosen to form a stereoscopic pair. The images were preprocessed to enhance their contrast
and were presented on a stereoscopic display. Three experienced breast imagers participated in a blinded observer study
as readers. Each case was shown twice to each reader - once in the stereoscopic mode, and once in the monoscopic mode
in a random order. The readers were asked to make a binary decision on whether they saw a mass for which they would
initiate a diagnostic workup or not, and also report the location of the mass and provide a confidence score in the range
of 0-100. The binary decisions were analyzed using the sensitivity-specificity measure, while the confidence scores were
analyzed using the Receiver Operating Characteristic curve (ROC). We also report a statistical analysis of the difference
in partial AUC values greater than 95% sensitivity between the stereoscopic and monoscopic modes.

http://live.ece.utexas.edu/publications/2012/muralidharmarkey12.pdf

Stereoscopic versus monoscopic detection of masses on breast tomosynthesis projection images

In this paper, chromatic information is integrated with an Adaboost learner to address non linearities in face patterns and illumination variations in training databases for face recognition (FR). An LDA based learner is boosted and the integrated framework is tested on a large database of images having severe pose and illumination variations. The increased dimensionality of color induces a small sample size problem when used with an LDA based learner. The integrated framework is tested on a number of learning scenarios in order to examine this effect. Experimental results show that integrating color into the boosting framework produces a high performing FR system for a range of learning scenarios.

/pdf/boosting-chromatic-information-for-face-recognition-4prw5h8vru.pdf

Ganapathi Tejaswini

Papers

Sparse Coding and Autoencoders

Simultaneous optimization of multiple TCP parameters to improve download outcomes for network-based mobile applications

Adaptive multi-phase network policy optimization

Stereoscopic versus monoscopic detection of masses on breast tomosynthesis projection images

Boosting chromatic information for face recognition