Face detection refers to a number of techniques that identify faces in images and videos. As part of the senior project exercise at Pomona College, I explore the process of face detection using a JavaScript library called CLMtrackr. CLMtrackr works in any browser and detects faces within the video stream captured by a webcam. The focus of this paper is to explore the shortcomings in the inclusivity of the CLMtrackr library and consequently that of face detection. In my research, I have used two datasets that contain human faces with diverse backgrounds, in order to assess the accuracy of CLMtrackr. The two datasets are the MUCT and PPB. In addition, I investigate whether skin color is a key factor in determining face detection's success, to ascertain where and why a face might not be recognized within an image. While my research and work produced some inconclusive results due to a small sample size and a couple outliers in my outputs, it is clear that there is a trends toward the CLMtrackr algorithm recognizing faces with lighter skin tones more often than darker ones.

With the progress of computer technology, computers are expected to be more intelligent in the interaction with humans, presenting information according to the user's psychological and physiological characteristics. However, computer users with visual problems may encounter difficulties on the perception of icons, menus, and other graphical information displayed on the screen, limiting the efficiency of their interaction with computers. In this dissertation, a personalized and dynamic image precompensation method was developed to improve the visual performance of the computer users with ocular aberrations. The precompensation was applied on the graphical targets before presenting them on the screen, aiming to counteract the visual blurring caused by the ocular aberration of the user's eye. A complete and systematic modeling approach to describe the retinal image formation of the computer user was presented, taking advantage of modeling tools, such as Zernike polynomials, wavefront aberration, Point Spread Function and Modulation Transfer Function. The ocular aberration of the computer user was originally measured by a wavefront aberrometer, as a reference for the precompensation model. The dynamic precompensation was generated based on the resized aberration, with the real-time pupil diameter monitored. The potential visual benefit of the dynamic precompensation method was explored through software simulation, with the aberration data from a real human subject. An "artificial eye'' experiment was conducted by simulating the human eye with a high-definition camera, providing objective evaluation to the image quality after precompensation. In addition, an empirical evaluation with 20 human participants was also designed and implemented, involving image recognition tests performed under a more realistic viewing environment of computer use. The statistical analysis results of the empirical experiment confirmed the effectiveness of the dynamic precompensation method, by showing significant improvement on the recognition accuracy. The merit and necessity of the dynamic precompensation were also substantiated by comparing it with the static precompensation. The visual benefit of the dynamic precompensation was further confirmed by the subjective assessments collected from the evaluation participants.

User studies play a vital role in data visualization research because they help measure the strengths and weaknesses of different visualization techniques quantitatively. In addition, they provide insight into what makes one technique more effective than another; and they are used to validate research contributions in the field of information visualization. For example, a new algorithm, visual encoding, or interaction technique is not considered a contribution unless it has been validated to be better than the state of the art and its competing alternatives or has been validated to be useful to intended users. However, conducting user studies is challenging, time consuming, and expensive. User studies generally requires careful experimental designs, iterative refinement, recruitment of study participants, careful management of participants during the run of the studies, accurately collecting user responses, and expertise in statistical analysis of study results. There are several variables that are taken into consideration which can impact user study outcome if not carefully managed. Hence the process of conducting user studies successfully can take several weeks to months. In this dissertation, we investigated how to design an online framework that can reduce the overhead involved in conducting controlled user studies involving web-based visualizations. Our main goal in this research was to lower the overhead of evaluating data visualizations quantitatively through user studies. To this end, we leveraged current research opportunities to provide a framework design that reduces the overhead involved in designing and running controlled user studies of data visualizations. Specifically, we explored the design and implementation of an open-source framework and an online service (VisUnit) that allows visualization designers to easily configure user studies for their web-based data visualizations, deploy user studies online, collect user responses, and analyze incoming results automatically. This allows evaluations to be done more easily, cheaply, and frequently to rapidly test hypotheses about visualization designs. We evaluated the effectiveness of our framework (VisUnit) by showing that it can be used to replicate 84% of 101 controlled user studies published in IEEE Information Visualization conferences between 1995 and 2015. We evaluated the efficiency of VisUnit by showing that graduate students can use it to design sample user studies in less than an hour. Our contributions are two-fold: first, we contribute a flexible design and implementation that facilitates the creation of a wide range of user studies with limited effort; second, we provide an evaluation of our design that shows that it can be used to replicate a wide range of user studies, can be used to reduce the time evaluators spend on user studies, and can be used to support new research.

To be successful citizen science projects need to do two key things: (1) they need to meaningfully engage the public and they must also provide people with the tools, expertise, and/or training needed to participate in rigorous research that can be used by the scientific community. In some ways, these requirements are potentially at odds. Emphasis on rigor and expertise risks excluding members of the public who do not feel qualified to participate in esoteric or technically difficult scientific research. Conversely, projects that eschew rigorous methods in favor of wider participation might lead to bad data that cannot be used to draw any meaningful conclusions to expand scientific understanding. How then do those who are aiming to design successful citizen science programs create tools and processes that facilitate both active engagement and meaningful scientific results for perceived non-expert researchers? This paper uses a case study of the Outsmart Invasive Species Project (Outsmart) to explore how visual media shape the experiences of citizen scientists participating in a data collection project. Outsmart uses visual media such as photographs and videos to train users in identifying invasive species, and asks them to submit their own location-tagged pictures to a central database for review by a trained research team. Using ethnographic field observation, we focused on how visual media serve to improve engagement in non-expert Outsmart users by building confidence and expertise. Our work can provide guidance to other citizen science projects in how to best use visual media to empower citizens and improve scientific outcomes.

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 with 56% accuracy. I classify the same dataset with 52% accuracy, but identify factors that have the greatest effect on the accuracy. The ability for computers to identify human sketches would be useful particularly in pictionary-like games and other kinds of human-computer interaction; the concepts from sketch recognition could be extended to other kinds of object recognition.

A company, Unanimous AI, has created a software platform that allows individuals to come together as a group or a human swarm to make decisions. These human swarms amplify the decision-making capabilities of both the individuals and the group. One way Unanimous AI increases the swarm’s collective decision-making capabilities is by limiting the swarm to more informed individuals on the given topic. The previous way Unanimous AI selected users to enter the swarm was improved upon by a new methodology that is detailed in this study. This new methodology implements a new type of survey that collects data that is more indicative of a user’s knowledge on the subject than the previous survey. This study also identifies better metrics for predicting each user’s performance when predicting Major League Baseball game outcomes throughout a given week. This study demonstrates that the new machine learning models and data extraction schemes are approximately 12% more accurate than the currently implemented methods at predicting user performance. Finally, this study shows how predicting a user’s performance based purely on their inputs can increase the average performance of a group by limiting the group to the top predicted performers. This study shows that by limiting the group to the top predicted performers across five different weeks of MLB predictions, the average group performance was increased up to 5.5%, making this a superior method.

Diminished reality, as a sub-topic of augmented reality where digital information is overlaid on an environment, is the perceived removal of an object from an environment. Previous approaches to diminished reality used digital replacement techniques, inpainting, and multi-view homographies. However, few used a virtual representation of the real environment, limiting their domains to planar environments. This thesis provides a framework to achieve real-time diminished reality on an augmented reality headset. Using state-of-the-art hardware, we combine a virtual representation of the real environment with inpainting to remove existing objects from complex environments. Our work is found to be competitive with previous results, with a similar qualitative outcome under the limitations of available technology. Additionally, by implementing new texturing algorithms, a more detailed representation of the real environment is achieved.

There’s no denying the ever increasing presence of social networking in our daily lives. Every day, people share what they are thinking, doing, and experiencing. But even more so, they check their favorite networks to see what the people in their lives are sharing. Social networking has become so prevalent that most applications incorporate it since it keeps users engaged and beckons them back to the application again and again. PolyXpress is an interactive, location-based storytelling mobile application that functions as a platform for creating and experiencing stories. Written as a research project at California Polytechnic State University, it allows users to play through stories in real-world locations by using their smart phones. However, in an age of social networking, PolyXpress falls behind the curve, as it does not contain any social features. The work in this thesis aims to test if adding social networking features to PolyX- press will increase user engagement by performing a usability study. The new social features allow users to participate in public forums about stories, message friends while playing stories, and view their friends’ experiences within the app. The results of the study indicate that the overall user experience of PolyXpress was not increased by the social networking features; however, these features are desired and liked by the users. 70% of the experimental group enjoyed using the social features, while 30% remained indifferent. The problem is that the new features disrupted app satisfac- tion, as UI satisfaction decreased from 100% with the control group to 40% with the experimental group.

Studies of how users experience Virtual Reality (VR) have thus far failed to address the extent to which rendering resolution and rendering frame rate affect users’ sense of immersion in VR, including applications of VR involving simulators, treatments for psychological and mental disorders, explorations of new and nonexistent structures, and ways to better understand the human body in medical applications. This study investigated if rendering resolution affected users’ sense of immersion in VR. This was conducted by comparing the responses of two groups, relative to two measures of participant immersion: (a) participant’s sense of presence and (b) participant’s sense of embodiment. The treatment levels were (a) low 512 pixels per inch (ppi) and (b) high 2048 ppi rendering resolution. One potential moderating variable, game type, varied over three levels: narrative, objective, and situational. The participants were randomly assigned to a treatment level account for previous VR experience, neither participants nor the research observer knew the treatment level. Measurements were collected after each game via an Immersion tendency Questionnaire after each game. For each dependent measure, sample descriptive statistics—mean (M) and inter-quartile range (IQR) with a conventional significance level of 0.05—were evaluated to conclude the results. Data indicated that the rendering resolution did not affect user immersion, but the game type did affect immersion and the situational game type was determined to be significantly more immersive than the other game types.

Computer-generated imagery is ubiquitous in today's society, appearing in advertisements, video games, and computer-animated movies among other places. Much of this imagery needs to be as realistic as possible, and animators have turned to techniques such as fluid simulation to create scenes involving substances like smoke, fire, and water. The Lattice-Boltzmann Method (LBM) is one fluid simulation technique that has gained recent popularity due to its relatively simple basic algorithm and the ease with which it can be distributed across multiple processors. Unfortunately, current LBM simulations also suffer from high memory usage and restrict free surface fluids to domains of fixed size. This thesis modifies the LBM to utilize a recursive run-length-encoded (RLE) grid data structure instead of the standard fixed array of grid cells, which reduces the amount of memory required for LBM simulations as well as allowing the domain to grow and shrink as necessary to accomodate a liquid surface. The modified LBM is implemented within the open-source 3D animation package Blender and compared to Blender's current LBM simulator using the metrics of memory usage and time required to complete a given simulation. Results show that, although the RLE-based simulator can take several times longer than the current simulator to complete a given simulation, the memory usage is significantly reduced, making an RLE-based simulation preferable in a few specific circumstances.