Computer Engineering Commons^™

Uncovering And Mitigating Spurious Features In Domain Generalization, Saeed Karimi, Hamdi̇ Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Domain generalization (DG) techniques strive to attain the ability to generalize to an unfamiliar target domain solely based on training data originating from the source domains. Despite the increasing attention given to learning from multiple training domains through the application of various forms of invariance across those domains, the enhancements observed in comparison to ERM are nearly insignificant under specified evaluation rules. In this paper, we demonstrate that the disentanglement of spurious and invariant features is a challenging task in conventional training since ERM simply minimizes the loss and does not exploit invariance among domains. To address this issue, we …

Motion Magnification-Inspired Feature Manipulation For Deepfake Detection, Aydamir Mirzayev, Hamdi Di̇bekli̇oğlu

Turkish Journal of Electrical Engineering and Computer Sciences

Recent advances in deep learning, increased availability of large-scale datasets, and improvement of accelerated graphics processing units facilitated creation of an unprecedented amount of synthetically generated media content with impressive visual quality. Although such technology is used predominantly for entertainment, there is widespread practice of using deepfake technology for malevolent ends. This potential for malicious use necessitates the creation of detection methods capable of reliably distinguishing manipulated video content. In this work we aim to create a learning-based detection method for synthetically generated videos. To this end, we attempt to detect spatiotemporal inconsistencies by leveraging a learning-based magnification-inspired feature manipulation …

Computer Aided Diagnosis System For Breast Cancer Using Deep Learning., Asma Baccouche

Electronic Theses and Dissertations

The recent rise of big data technology surrounding the electronic systems and developed toolkits gave birth to new promises for Artificial Intelligence (AI). With the continuous use of data-centric systems and machines in our lives, such as social media, surveys, emails, reports, etc., there is no doubt that data has gained the center of attention by scientists and motivated them to provide more decision-making and operational support systems across multiple domains. With the recent breakthroughs in artificial intelligence, the use of machine learning and deep learning models have achieved remarkable advances in computer vision, ecommerce, cybersecurity, and healthcare. Particularly, numerous …

Applied Deep Learning: Case Studies In Computer Vision And Natural Language Processing, Md Reshad Ul Hoque

Electrical & Computer Engineering Theses & Dissertations

Deep learning has proved to be successful for many computer vision and natural language processing applications. In this dissertation, three studies have been conducted to show the efficacy of deep learning models for computer vision and natural language processing. In the first study, an efficient deep learning model was proposed for seagrass scar detection in multispectral images which produced robust, accurate scars mappings. In the second study, an arithmetic deep learning model was developed to fuse multi-spectral images collected at different times with different resolutions to generate high-resolution images for downstream tasks including change detection, object detection, and land cover …

Lapnitor: A Web Service That Protects Your Laptop From Theft., Michael Ameteku

Williams Honors College, Honors Research Projects

Laptop theft is an issue worldwide. According to an article from 2018, Security Boulevard stated that a laptop is stolen every 53 seconds. Using a laptop's camera, we can monitor the surroundings of the laptop and reduce a laptop's probability of being stolen. According to the University of Pittsburgh, a laptop has a 1-in- 10 chance of being stolen and nearly half of these thefts occur in offices or classrooms. These thefts mostly occur when a laptop owner leaves their device unattended for a certain period of time to maybe go visit the restroom or attend to a call when …

Magic: The Gathering Card Virtualizer, Vincent Garbonick, Jacen C. Conlan, Jaret A. Varn

Williams Honors College, Honors Research Projects

Any well-versed Magic: The Gathering (MTG) player or collector knows how difficult it can be to keep track of all cards in their collection. Some spend hours searching for that one specific card, and others are constantly scouring the internet for how much their collection costs. However, this issue does not only affect casual fans. Resale companies spend hours a day determining the costs of cards, and tournament judges painstakingly check players’ decks to ensure they are not cheating. To assist with these struggles, the design team proposed to create the MTG Card Virtualizer. This device scans MTG playing cards …

Towards Semantic Integration Of Machine Vision Systems To Aid Manufacturing Event Understanding, Kaishu Xia, Clint Saidy, Max Kirkpatrick, Noble Anumbe, Amit Sheth, Ramy Harik

Publications

A manufacturing paradigm shift from conventional control pyramids to decentralized, service-oriented, and cyber-physical systems (CPSs) is taking place in today’s 4th industrial revolution. Generally accepted roles and implementation recipes of cyber systems are expected to be standardized in the future of manufacturing industry. The authors intend to develop a novel CPS-enabled control architecture that accommodates: (1) intelligent information systems involving domain knowledge, empirical model, and simulation; (2) fast and secured industrial communication networks; (3) cognitive automation by rapid signal analytics and machine learning (ML) based feature extraction; (4) interoperability between machine and human. Semantic integration of process indicators is fundamental …

A Quantitative Validation Of Multi-Modal Image Fusion And Segmentation For Object Detection And Tracking, Nicholas Lahaye, Michael J. Garay, Brian D. Bue, Hesham El-Askary, Erik Linstead

Mathematics, Physics, and Computer Science Faculty Articles and Research

In previous works, we have shown the efficacy of using Deep Belief Networks, paired with clustering, to identify distinct classes of objects within remotely sensed data via cluster analysis and qualitative analysis of the output data in comparison with reference data. In this paper, we quantitatively validate the methodology against datasets currently being generated and used within the remote sensing community, as well as show the capabilities and benefits of the data fusion methodologies used. The experiments run take the output of our unsupervised fusion and segmentation methodology and map them to various labeled datasets at different levels of global …

‘Digits’ App - Smartphone Augmented Reality For Hand Telerehabilitation, Hongdao Dong, Edward Ho, Herbert Shin, Tania Banerjee, Geoffrey Masschelein, Jacob Davidson, Sandrine De Ribaupierre, Roy Eagleson, Caitlin Symonette

Electrical and Computer Engineering Publications

Hand telerehabilitation currently has limitations for accurate and remote assessment of range of motion (ROM) in small finger joints. ‘DIGITS’ application utilises the front smartphone camera to measure finger ROM in a reliable and rapid assessment protocol. Our initial beta-phase testing examined the consistency of our software measurements to in-person goniometry. 6 to 9 degrees of difference existed between the smartphone application recorded data versus the in-person measurements. This range is within acceptable 7 to 9 degree tolerance for interrater goniometry measurements. The effect of environmental factors such as hand distance, lightings and hand orientation was evaluated. The intraclass correlation …

A Deep Transfer Learning Based Model For Automatic Detection Of Covid-19from Chest X-Rays, Prateek Chhikara, Prakhar Gupta, Prabhjot Singh, Tarunpreet Bhatia

Turkish Journal of Electrical Engineering and Computer Sciences

Deep learning in medical imaging has revolutionized the way we interpret medical data, as high computational devices' capabilities are far more than their creators. With the pandemic causing havoc for the second straight year, the findings in our paper will allow researchers worldwide to use and create state-of-the-art models to detect affected persons before it reaches the R number. The paper proposes an automated diagnostic tool using the deep learning models on chest x-rays as an input to reach a point where we surpass this pandemic (COVID-19 disease). A deep transfer learning-based model for automatic detection of COVID-19 from chest …

Bibliometric Review On Image Based Plant Phenotyping, Shrikrishna Ulhas Kolhar, Jayant Jagtap

Library Philosophy and Practice (e-journal)

Plant phenotyping is a quantitative description of structural, physiological and temporal traits of plants resulting from interaction of plant genotypes with the environment. A rapid development is in progress in the field of image-based plant phenotyping. Plant phenotyping has wide range of applications in plant breeding research, plant growth prediction, biotic and abiotic stress analysis, crop management and early disease detection. The main motive is to provide detailed bibliometric review in order to know the available literature and current research trends in the area of plant phenotyping using plant images. The bibliometric analysis is primarily based on Scopus, web of …

Navigating In Numerous Video Data: User Interface Design For An On-Camera Video Analytics Engine, Sabriya Maryam Alam

The Journal of Purdue Undergraduate Research

Video analytics powered by artificial intelligence shows high promise in making our society smarter. Harnessing large amounts of video data, however, requires the development of processing systems demonstrating high performance and high efficiency. To this end, this work has contributed to a video analytics system powered by artificial intelligence for object detection and recognition. Rather than streaming all the video frames to the cloud, the system analyzes images on-camera and only returns those of interest to the cloud. This edge analytics research-grade software is available, but it lacks a simple web interface for general use by scientists, engineers, and other …

Past To Present (P2p): Road Thermal Image Colorization, Yuseong Park

Electronic Theses and Dissertations

Thermal image colorization into realistic RGB image is a challenging task. Thermal cameras are easily to detect objects in particular situation (e.g. darkness and fog) that the human eyes cannot detect. However, it is difficult to interpret the thermal image with human eyes. Enhancing thermal image colorization is an important task to improve these areas. The results of the existing colorization method still have color ambiguities, distortion, and blurriness problems. This paper focused on thermal image colorization using pix2pix network architecture based on Generative Adversarial Net (GAN). Pix2pix is a model that transforms thermal image into RGB image, but our …

Deep Temporal Motion Descriptor (Dtmd) For Human Action Recognition, Nudrat Nida, Muhammad Haroon Yousaf, Aun Irtaza, Sergio A. Velastin

Turkish Journal of Electrical Engineering and Computer Sciences

Spatiotemporal features have significant importance in human action recognition, as they provide the actor's shape and motion characteristics specific to each action class. This paper presents a new deep spatiotemporal human action representation, the deep temporal motion descriptor (DTMD), which shares the attributes of holistic and deep learned features. To generate the DTMD descriptor, the actor?s silhouettes are gathered into single motion templates by applying motion history images. These motion templates capture the spatiotemporal movements of the actor and compactly represent the human actions using a single 2D template. Then deep convolutional neural networks are used to compute discriminative deep …

Amodal Instance Segmentation And Multi-Object Tracking With Deep Pixel Embedding, Yanfeng Liu

Department of Electrical and Computer Engineering: Dissertations, Theses, and Student Research

This thesis extends upon the representational output of semantic instance segmentation by explicitly including both visible and occluded parts. A fully convolutional network is trained to produce consistent pixel-level embedding across two layers such that, when clustered, the results convey the full spatial extent and depth ordering of each instance. Results demonstrate that the network can accurately estimate complete masks in the presence of occlusion and outperform leading top-down bounding-box approaches.

The model is further extended to produce consistent pixel-level embeddings across two consecutive image frames from a video to simultaneously perform amodal instance segmentation and multi-object tracking. No post-processing …

Multi-Pig Part Detection And Association With A Fully-Convolutional Network, Eric T. Psota, Mateusz Mittek, Lance C. Pérez, Ty Schmidt, Benny Mote

Department of Electrical and Computer Engineering: Faculty Publications

Computer vision systems have the potential to provide automated, non-invasive monitoring of livestock animals, however, the lack of public datasets with well-defined targets and evaluation metrics presents a significant challenge for researchers. Consequently, existing solutions often focus on achieving task-specific objectives using relatively small, private datasets. This work introduces a new dataset and method for instance-level detection of multiple pigs in group-housed environments. The method uses a single fully-convolutional neural network to detect the location and orientation of each animal, where both body part locations and pairwise associations are represented in the image space. Accompanying this method is a new …

Elimination Of Useless Images From Raw Camera-Trap Data, Ulaş Tekeli̇, Yalin Baştanlar

Turkish Journal of Electrical Engineering and Computer Sciences

Camera-traps are motion triggered cameras that are used to observe animals in nature. The number of images collected from camera-traps has increased significantly with the widening use of camera-traps thanks to advances in digital technology. A great workload is required for wild-life researchers to group and label these images. We propose a system to decrease the amount of time spent by the researchers by eliminating useless images from raw camera-trap data. These images are too bright, too dark, blurred, or they contain no animals. To eliminate bright, dark, and blurred images we employ techniques based on image histograms and fast …

Leveraging Eye Structure And Motion To Build A Low-Power Wearable Gaze Tracking System, Addison Mayberry

Doctoral Dissertations

Clinical studies have shown that features of a person's eyes can function as an effective proxy for cognitive state and neurological function. Technological advances in recent decades have allowed us to deepen this understanding and discover that the actions of the eyes are in fact very tightly coupled to the operation of the brain. Researchers have used camera-based eye monitoring technology to exploit this connection and analyze mental state across across many different metrics of interest. These range from simple things like attention and scene processing, to impairments such as a fatigue or substance use, and even significant mental disorders …

Collision Avoidance Smartphone, Matt Columbres, Aaron Parisi, Joey Schnecker, Luis Wong

Electrical Engineering

There are many instances in day-to-day life where people cannot or would rather not pay full attention to their surroundings. Walking while preoccupied with a smartphone or walking while blind are excellent examples where technology could be used to make the task of avoiding 2collisions reactive, instead of proactive. A device which monitors a user’s surroundings and notifies the user when a potential collision is detected (and, additionally, notifying them as to where the obstacle is with respect to them) could be used to make walking distracted less of a hazard for the user and those around the user and …

Assessing The Importance Of Features For Detection Of Hard Exudates In Retinal Images, Kemal Akyol, Baha Şen, Şafak Bayir, Hasan Basri̇ Çakmak

Turkish Journal of Electrical Engineering and Computer Sciences

Diabetes disrupts the operation of the eye and leads to vision loss, affecting particularly the nerve layer and capillary vessels in this layer by changes in the blood vessels of the retina.~Suddenly loss and blurred vision problems occur in the image, depending on the phase of the disease, called diabetic retinopathy. Hard exudates are one of the primary signs of diabetic retinopathy. Automatic recognition of hard exudates in retinal images can contribute to detection of the disease. We present an automatic screening system for the detection of hard exudates. This system consists of two main steps. Firstly, the features were …

Control Of A Powered Ankle-Foot Prosthesis: From Perception To Impedance Modulation, Guilherme Aramizo Ribeiro

Dissertations, Master's Theses and Master's Reports

Active ankle prostheses controllers are demonstrating gaining smart features to improve the safety and comfort offor users. The perception of user intention to modulate the ankle dynamics is a well-known example of such feature. But not much work focused on the perception of the environment, nor how the environment should be included in the mechanical design and control of the prosthesisprostheses. The proposed work aims to improve the feasibility of integrate the environment perception integration intoto the prostheses controllersler, and to define the desired ankle dynamics, as mechanical impedance, duringof the human walk on different environmental settings. As a preliminary …

Designing A Bayer Filter With Smooth Hue Transition Interpolation Using The Xilinx System Generator, Zhiqiang Li, Peter Revesz

CSE Conference and Workshop Papers

This paper describes the design of a Bayer filter with smooth hue transition using the System Generator for DSP. We describe and compare experimentally two different designs, one based on a MATLAB implementation and the other based on a modification of the Bayer filter using bilinear interpolation.

Team Omnimouse, Derek J. Halman, Josh B. Porter, Steven A. Silver, Ian S. Stemper

Computer Engineering

INFORMATION, DATA, FIGURES AND DRAWINGS EMBODIED IN THIS DOCUMENT ARE STRICTLY CONFIDENTIAL AND ARE SUPPLIED ON THE UNDERSTANDING THAT THEY WILL NOT BE DISCLOSED TO THIRD PARTIES WITHOUT THE PRIOR WRITTEN CONSENT OF QUALITY OF LIFE PLUS.

Joint Source-Channel Coding For Error Resilient Transmission Of Static 3d Models, Mehmet Oğuz Bi̇ci̇, Andrey Norkin, Gözde Akar

Turkish Journal of Electrical Engineering and Computer Sciences

In this paper, performance analysis of joint source-channel coding techniques for error-resilient transmission of three dimensional (3D) models are presented. In particular, packet based transmission scenarios are analyzed. The packet loss resilient methods are classified into two groups according to progressive compression schemes employed: Compressed Progressive Meshes (CPM) based methods and wavelet based methods. In the first group, layers of CPM algorithm are protected unequally by Forward Error Correction (FEC) using Reed Solomon (RS) codes. In the second group, embedded bitstream obtained from wavelet based coding is protected unequally with FEC as well. Both groups of methods are scalable with …

Electronic Image Stabilization For Mobile Robotic Vision Systems, Michael John Smith

Theses and Dissertations

When a camera is affixed on a dynamic mobile robot, image stabilization is the first step towards more complex analysis on the video feed. This thesis presents a novel electronic image stabilization (EIS) algorithm for small inexpensive highly dynamic mobile robotic platforms with onboard camera systems. The algorithm combines optical flow motion parameter estimation with angular rate data provided by a strapdown inertial measurement unit (IMU). A discrete Kalman filter in feedforward configuration is used for optimal fusion of the two data sources. Performance evaluations are conducted by a simulated video truth model (capturing the effects of image translation, rotation, …

A Subspace Projection Methodology For Nonlinear Manifold Based Face Recognition, Praveen Sankaran

Electrical & Computer Engineering Theses & Dissertations

A novel feature extraction method that utilizes nonlinear mapping from the original data space to the feature space is presented in this dissertation. Feature extraction methods aim to find compact representations of data that are easy to classify. Measurements with similar values are grouped to same category, while those with differing values are deemed to be of separate categories. For most practical systems, the meaningful features of a pattern class lie in a low dimensional nonlinear constraint region (manifold) within the high dimensional data space. A learning algorithm to model this nonlinear region and to project patterns to this feature …

Human Identification Using Gait, Murat Eki̇nci̇

Turkish Journal of Electrical Engineering and Computer Sciences

Gait refers to the style of walking of an individual. This paper presents a view-invariant approach for human identification at a distance, using gait recognition. Recognition of a person from their gait is a biometric of increasing interest. Based on principal component analysis (PCA), this paper describes a simple, but efficient approach to gait recognition. Binarized silhouettes of a motion object are represented by 1-D signals, which are the basic image features called distance vectors. The distance vectors are differences between the bounding box and silhouette, and are extracted using 4 projections of the silhouette. Based on normalized correlation of …

Knowledge-Based Navigation For Autonomous Road Vehicles, Murat Eki̇nci̇, Franches W.J.Gibbs, Barry T. Thomas

Turkish Journal of Electrical Engineering and Computer Sciences

This paper presents a computer vision system for an autonomous road vehicle (ARV) that is capable of negotiating complex road networks including road junctions in real time. The ultimate aim of the system is to enable the vehicle to drive automatically along a given complex road network whose geometric description is known. This computer vision system includes three main techniques which are necessary for an ARV: a) road following, b) road junction detection, c) manoeuvring at the road junction. The road following algorithm presents a method of executing a number of algorithms using different methods concurrently, fusing their outputs together …

Adaptive Shape From Shading, Ati̇lla Gülteki̇n, Muhi̇tti̇n Gökmen

Turkish Journal of Electrical Engineering and Computer Sciences

Extracting surface orientation and surface depth from one or more images is one of the classic problems in computer vision. Shape-from-shading (SFS) deals with the recovery of 3-D shape from a single shaded image. The shape is recovered by minimizing an energy functional involving constraints such as smoothness. In this constrained problem, although the smoothness constraint helps to stabilize the minimization process, it pushes the reconstruction toward a smooth surface. In this paper, we present a new adaptive shape-from-shading method which reduces this oversmoothing by controlling the smoothness spatially over the image space. In order to improve the quality of …