Graphics and Human Computer Interfaces Commons^™

Deep Learning Image Analysis To Isolate And Characterize Different Stages Of S-Phase In Human Cells, Kevin A. Boyd, Rudranil Mitra, John Santerre, Christopher L. Sansam

SMU Data Science Review

Abstract. This research used deep learning for image analysis by isolating and characterizing distinct DNA replication patterns in human cells. By leveraging high-resolution microscopy images of multiple cells stained with 5-Ethynyl-2′-deoxyuridine (EdU), a replication marker, this analysis utilized Convolutional Neural Networks (CNNs) to perform image segmentation and to provide robust and reliable classification results. First multiple cells in a field of focus were identified using a pretrained CNN called Cellpose. After identifying the location of each cell in the image a python script was created to crop out each cell into individual .tif files. After careful annotation, a CNN was …

Enhanced Privacy-Enabled Face Recognition Using Κ-Identity Optimization, Ryan Karl

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

Facial recognition is becoming more and more prevalent in the daily lives of the common person. Law enforcement utilizes facial recognition to find and track suspects. The newest smartphones have the ability to unlock using the user's face. Some door locks utilize facial recognition to allow correct users to enter restricted spaces. The list of applications that use facial recognition will only increase as hardware becomes more cost-effective and more computationally powerful. As this technology becomes more prevalent in our lives, it is important to understand and protect the data provided to these companies. Any data transmitted should be encrypted …

Fine-Grained Domain Adaptive Crowd Counting Via Point-Derived Segmentation, Yongtuo Liu, Dan Xu, Sucheng Ren, Hanjie Wu, Hongmin Cai, Shengfeng He

Research Collection School Of Computing and Information Systems

Due to domain shift, a large performance drop is usually observed when a trained crowd counting model is deployed in the wild. While existing domain-adaptive crowd counting methods achieve promising results, they typically regard each crowd image as a whole and reduce domain discrepancies in a holistic manner, thus limiting further improvement of domain adaptation performance. To this end, we propose to untangle domain-invariant crowd and domain-specific background from crowd images and design a fine-grained domain adaption method for crowd counting. Specifically, to disentangle crowd from background, we propose to learn crowd segmentation from point-level crowd counting annotations in a …

Curricular Contrastive Regularization For Physics-Aware Single Image Dehazing, Yu Zheng, Jiahui Zhan, Shengfeng He, Yong Du

Research Collection School Of Computing and Information Systems

Considering the ill-posed nature, contrastive regularization has been developed for single image dehazing, introducing the information from negative images as a lower bound. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clear (i.e., positive) image, leaving the solution space still under-constricted. Moreover, the interpretability of deep dehazing models is underexplored towards the physics of the hazing process. In this paper, we propose a novel curricular contrastive regularization targeted at a consensual contrastive space as opposed to a non-consensual one. Our negatives, which provide better lower-bound constraints, can be assembled from 1) the hazy …

High-Resolution Face Swapping Via Latent Semantics Disentanglement, Yangyang Xu, Bailin Deng, Junle Wang, Yanqing Jing, Jia Pan, Shengfeng He

Research Collection School Of Computing and Information Systems

We present a novel high-resolution face swapping method using the inherent prior knowledge of a pre-trained GAN model. Although previous research can leverage generative priors to produce high-resolution results, their quality can suffer from the entangled semantics of the latent space. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator, deriving structure at-tributes from the shallow layers and appearance attributes from the deeper ones. Identity and pose information within the structure attributes are further separated by introducing a landmark-driven structure transfer latent direction. The disentangled latent code produces rich generative features that incorporate feature blending …

Gauging The State-Of-The-Art For Foresight Weight Pruning On Neural Networks, Noah James

Computer Science and Computer Engineering Undergraduate Honors Theses

The state-of-the-art for pruning neural networks is ambiguous due to poor experimental practices in the field. Newly developed approaches rarely compare to each other, and when they do, their comparisons are lackluster or contain errors. In the interest of stabilizing the field of pruning, this paper initiates a dive into reproducing prominent pruning algorithms across several architectures and datasets. As a first step towards this goal, this paper shows results for foresight weight pruning across 6 baseline pruning strategies, 5 modern pruning strategies, random pruning, and one legacy method (Optimal Brain Damage). All strategies are evaluated on 3 different architectures …

Projecting Your View Attentively: Monocular Road Scene Layout Estimation Via Cross-View Transformation, Weixiang Yang, Qi Li, Wenxi Liu, Yuanlong Yu, Yuexin Ma, Shengfeng He, Jia Pan

Research Collection School Of Computing and Information Systems

HD map reconstruction is crucial for autonomous driving. LiDAR-based methods are limited due to the deployed expensive sensors and time-consuming computation. Camera-based methods usually need to separately perform road segmentation and view transformation, which often causes distortion and the absence of content. To push the limits of the technology, we present a novel framework that enables reconstructing a local map formed by road layout and vehicle occupancy in the bird's-eye view given a front-view monocular image only. In particular, we propose a cross-view transformation module, which takes the constraint of cycle consistency between views into account and makes full use …

Reciprocal Transformations For Unsupervised Video Object Segmentation, Sucheng Ren, Wenxi Liu, Yongtuo Liu, Haoxin Chen, Guoqiang Han, Shengfeng He

Research Collection School Of Computing and Information Systems

Unsupervised video object segmentation (UVOS) aims at segmenting the primary objects in videos without any human intervention. Due to the lack of prior knowledge about the primary objects, identifying them from videos is the major challenge of UVOS. Previous methods often regard the moving objects as primary ones and rely on optical flow to capture the motion cues in videos, but the flow information alone is insufficient to distinguish the primary objects from the background objects that move together. This is because, when the noisy motion features are combined with the appearance features, the localization of the primary objects is …

Fakepolisher: Making Deepfakes More Detection-Evasive By Shallow Reconstruction, Yihao Huang, Felix Juefei-Xu, Run Wang, Qing Guo, Lei Ma, Xiaofei Xie, Jianwen Li, Weikai Miao, Yang Liu, Geguang Pu

Research Collection School Of Computing and Information Systems

At this moment, GAN-based image generation methods are still imperfect, whose upsampling design has limitations in leaving some certain artifact patterns in the synthesized image. Such artifact patterns can be easily exploited (by recent methods) for difference detection of real and GAN-synthesized images. However, the existing detection methods put much emphasis on the artifact patterns, which can become futile if such artifact patterns were reduced.Towards reducing the artifacts in the synthesized images, in this paper, we devise a simple yet powerful approach termed FakePolisher that performs shallow reconstruction of fake images through a learned linear dictionary, intending to effectively and …

Computer Vision-Based Traffic Sign Detection And Extraction: A Hybrid Approach Using Gis And Machine Learning, Zihao Wu

Electronic Theses and Dissertations

Traffic sign detection and positioning have drawn considerable attention because of the recent development of autonomous driving and intelligent transportation systems. In order to detect and pinpoint traffic signs accurately, this research proposes two methods. In the first method, geo-tagged Google Street View images and road networks were utilized to locate traffic signs. In the second method, both traffic signs categories and locations were identified and extracted from the location-based GoPro video. TensorFlow is the machine learning framework used to implement these two methods. To that end, 363 stop signs were detected and mapped accurately using the first method (Google …

Formresnet: Formatted Residual Learning For Image Restoration, Jianbo Jiao, Wei-Chih Tu, Shengfeng He

Research Collection School Of Computing and Information Systems

In this paper, we propose a deep CNN to tackle the image restoration problem by learning the structured residual. Previous deep learning based methods directly learn the mapping from corrupted images to clean images, and may suffer from the gradient exploding/vanishing problems of deep neural networks. We propose to address the image restoration problem by learning the structured details and recovering the latent clean image together, from the shared information between the corrupted image and the latent image. In addition, instead of learning the pure difference (corruption), we propose to add a 'residual formatting layer' to format the residual to …

Thinking Outside The Box: Computing 3d Volume In 2d, Alexandra D. Morris

Senior Projects Fall 2017

This project explores how to compute 3D volume of cardboard boxes in 2D without a calibrated camera. Computer vision techniques to obtain 3D volume typically require camera calibration, the standard method for mapping 3D points to 2D. We created our own solution that doesn’t rely on camera calibration and obtains the areas of each box with unknown dimensions with the help of a chessboard pattern placed on each box side. The solution is a proportion that given the box area in pixels, chessboard pattern in pixels, and the chessboard pattern in inches, determines the box area in inches. We tested …

Real-Time, Non-Contact Heart Rate Monitor, Daniel Blike

Computer Engineering

No abstract provided.

Exemplar-Driven Top-Down Saliency Detection Via Deep Association, Shengfeng He, Rynson W. H. Lau, Qingxiong Yang

Research Collection School Of Computing and Information Systems

Top-down saliency detection is a knowledge-driven search task. While some previous methods aim to learn this "knowledge" from category-specific data, others transfer existing annotations in a large dataset through appearance matching. In contrast, we propose in this paper a locateby-exemplar strategy. This approach is challenging, as we only use a few exemplars (up to 4) and the appearances among the query object and the exemplars can be very different. To address it, we design a two-stage deep model to learn the intra-class association between the exemplars and query objects. The first stage is for learning object-to-object association, and the second …

Un Indicator De Incluziune Cu Aplicaţii În Computer Vision, Florentin Smarandache, Ovidiu Ilie Sandru

Branch Mathematics and Statistics Faculty and Staff Publications

În aceasta lucrare vom prezenta un procedeu de algoritmizare a operatiilor necesare deplasarii automate a unui obiect predefinit dintr-o imagine video data intr-o regiune tinta a acelei imagini, menit a facilita realizarea de aplicatii software specializate in rezolvarea acestui gen de probleme.

Oriented Object Proposals, Shengfeng He, Rynson W. H. Lau

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to generate oriented object proposals (OOPs) to reduce the detection error caused by various orientations of the object. To this end, we propose to efficiently locate object regions according to pixelwise object probability, rather than measuring the objectness from a set of sampled windows. We formulate the proposal generation problem as a generative probabilistic model such that object proposals of different shapes (i.e., sizes and orientations) can be produced by locating the local maximum likelihoods. The new approach has three main advantages. First, it helps the object detector handle objects of different …

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.

Computer Sketch Recognition, Richard Steigerwald

Master's Theses

Tens of thousands of years ago, humans drew sketches that we can see and identify even today. Sketches are the oldest recorded form of human communication and are still widely used. The universality of sketches supersedes that of culture and language. Despite the universal accessibility of sketches by humans, computers are unable to interpret or even correctly identify the contents of sketches drawn by humans with a practical level of accuracy.

In my thesis, I demonstrate that the accuracy of existing sketch recognition techniques can be improved by optimizing the classification criteria. Current techniques classify a 20,000 sketch crowd-sourced dataset …

3design - Holographic Telecollaboration Interface, Thomas W. De Wit, Mark Gill, Scott Freemon, Preston Garland

Chancellor’s Honors Program Projects

No abstract provided.

Identifying Robust Sift Features For Improved Image Alignment, Sanjay Abhinav Vemuri

Graduate Theses and Dissertations

In this thesis, we will study different ways to improve feature matching by increasing the quality and reducing the number of SIFT features. We created an algorithm to identify robust SIFT features by evaluating how invariant individual feature points are to changes in scale. This allows us to exclude poor SIFT feature points from the matching process and obtain better matching results in reduced time. We also developed techniques consider scale ratios and changes in object orientation when performing feature matching. This allows us to exclude false-positive feature matches and obtain better image alignment results.

An Architecture For Online Semantic Labeling On Ugvs, Arne Suppe, Luis Navarro-Serment, Daniel Munoz, Drew Bagnell, Martial Hebert

Research Collection School Of Computing and Information Systems

We describe an architecture to provide online semantic labeling capabilities to field robots operating in urban environments. At the core of our system is the stacked hierarchical classifier developed by Munoz et al.,1 which classifies regions in monocular color images using models derived from hand labeled training data. The classifier is trained to identify buildings, several kinds of hard surfaces, grass, trees, and sky. When taking this algorithm into the real world, practical concerns with difficult and varying lighting conditions require careful control of the imaging process. First, camera exposure is controlled by software, examining all of the image’s pixels, …

Three-Dimensional Scene Reconstruction Using Multiple Microsoft Kinects, Matt Miller

Graduate Theses and Dissertations

The Microsoft Kinect represents a leap forward in the form of cheap, consumer friendly, depth sensing cameras. Through the use of the depth information as well as the accompanying RGB camera image, it becomes possible to represent the scene, what the camera sees, as a three-dimensional geometric model. In this thesis, we explore how to obtain useful data from the Kinect, and how to use it for the creation of a three-dimensional geometric model of the scene. We develop and test multiple ways of improving the depth information received from the Kinect, in order to create smoother three-dimensional models. We …

Enhancement Technique For Aerial Images, Sertan Erkanli, Ahmet Gungor Pakfiliz, Jiang Li

Electrical & Computer Engineering Faculty Publications

Recently, we proposed an enhancement technique for uniformly and non-uniformly illuminated dark images that provides high color accuracy and better balance between the luminance and the contrast in images to improve the visual representations of digital images. In this paper we define an improved version of the proposed algorithm to enhance aerial images in order to reduce the gap between direct observation of a scene and its recorded image.

Using Computer Vision To Create A 3d Representation Of A Snooker Table For Televised Competition Broadcasting, Hao Guo, Brian Mac Namee

Conference papers

The Snooker Extraction and 3D Builder (SE3DB) is designed to be used as a viewer aid in televised snooker broadcasting. Using a single camera positioned over a snooker table, the system creates a virtual 3D model of the table which can be used to allow audiences view the table from any angle. This would be particularly useful in allowing viewers to determine if particular shots are possible or not. This paper will describe the design, development and evaluation of this system. Particular focus in the paper will be given to the techniques used to recognise and locate the balls on …

Using Linear Features For Aerial Image Sequence Mosaiking, Caixia Wang

Electronic Theses and Dissertations

With recent advances in sensor technology and digital image processing techniques, automatic image mosaicking has received increased attention in a variety of geospatial applications, ranging from panorama generation and video surveillance to image based rendering. The geometric transformation used to link images in a mosaic is the subject of image orientation, a fundamental photogrammetric task that represents a major research area in digital image analysis. It involves the determination of the parameters that express the location and pose of a camera at the time it captured an image. In aerial applications the typical parameters comprise two translations (along the x …

Arbitrary Views Of High-Dimensional Space And Data, Andrew Ellerton

Theses : Honours

Computer generated images of three dimensional scenes objects are the result of parallel/perspective projections of the objects onto a two dimensional plane. The computational techniques may be extended to project n-dimensional hyperobjects onto (n-1) dimensions, for n > 3. Projection to one less dimension may be applied recursively for data of any high dimension until that data is two-dimensional, when it may be directed to a computer screen or to some other two-dimensional output device. Arbitrary specification of eye location, target location, field-of-view angles and other parameters provide flexibility, so that data may be viewed-and hence perceived-in previously unavailable ways. However, …