Amalia I. Rusu

Handwritten CAPTCHA: using the difference in the abilities of humans and machines in reading handwritten words

Handwritten text offers challenges that are rarely encountered in machine-printed text. In addition, most problems faced in reading machine-printed text (e.g., character recognition, word segmentation, letter segmentation, etc.) are more severe, in handwritten text. In this paper we present the application of human interactive proofs (HIP), which is a relatively new research area with the primary focus of defending online services against abusive attacks. It uses a set of security protocols based on automatic tests that humans can pass but the state-of-the-art computer programs cannot. This is accomplished by exploiting the differential in the proficiency between humans and computers in reading handwritten word images.

Synthetic handwritten CAPTCHAs

CAPTCHAs (completely automated public Turing test to tell computers and humans apart) are in common use today as a method for performing automated human verification online. The most popular type of CAPTCHA is the text recognition variety. However, many of the existing printed text CAPTCHAs have been broken by web-bots and are hence vulnerable to attack. We present an approach to use human-like handwriting for designing CAPTCHAs. A synthetic handwriting generation method is presented, where the generated textlines need to be as close as possible to human handwriting without being writer-specific. Such handwritten CAPTCHAs exploit the differential in handwriting reading proficiency between humans and machines. Test results show that when the generated textlines are further obfuscated with a set of deformations, machine recognition rates decrease considerably, compared to prior work, while human recognition rates remain the same.

Academia-academia-industry collaborations on software engineering projects using local-remote teams

It is widely recommended by both academia and industry that todays technology and software engineering students be well prepared for industry before graduation, especially given global outsourcing and other trends. Various methods have been developed to ensure student readiness, including co-ops and capstone courses. These approaches increasingly use real-world projects for their benefits to industry and often to the community at large. In this paper, we argue that students can be prepared to effectively join industry and keep the US technology workforce competitive through a curriculum that includes a theoretical software engineering course with real-world projects and the collaboration of paired teams across two or more universities. We present a case study of a successful teaching experience that features these aspects, and describe the outcome along with the unique perspective of a participating student.

Using the Gestalt Principle of Closure to Alleviate the Edge Crossing Problem in Graph Drawings

Graphs, generally used as data structures in computer science applications, have steadily shown a growth in mapping various types of relationships, from maps to computer networks to social networks. As graph layouts and visualizations have been at the forefront of graph drawing research for decades, it consequently led to aesthetic heuristics that not only generated better visualizations and aesthetically appealing graphs but also improved readability and understanding of the graphs. A variety of approaches examines aesthetics of nodes, edges, or graph layout, and related readability metrics. In this paper we focus on the edge crossing problem and propose a solution that incorporates Gestalt principles to improve graph aesthetics and readability. We introduce the concept of breaks in edges at edge crossings. A break is a gap in an edge drawing occurring in the vicinity of an edge crossing. At every edge crossing, one of the incident edges is broken, which will prevent any unintentional gestalts that occur at edge crossings that reduce the readability of a graph drawing. We present our preliminary results and user studies that show that this technique could play a role in improving graph readability.

A human interactive proof algorithm using handwriting recognition

The recognition of unconstrained handwriting continues to be a difficult task for computers despite active research for several decades. This is because handwritten text offers great challenges such as: character and word segmentation, character recognition, variation between handwriting styles, different character size and orientation, no font constraints, the type of printing surface, as well as the background clarity. In this paper, we explore the gap in the ability in reading handwritten text between humans and computers to propose solutions for security problems in Web services. We present a new HIP algorithm that uses handwriting recognition task to distinguish between humans and computers. We propose methods to deform handwritten text images to make them indecipherable by computers and explore the cognitive factors that assist humans in reading and understanding. Experimental results on both humans and computers are presented and compared.

Visual CAPTCHA with handwritten image analysis

By convention, CAPTCHA is an automated test that humans can pass but current computer programs can′t. In general, the research on CAPTCHA and Human Interactive Proofs is focusing on those recognition tasks that are harder for machines than for humans. The recognition of unconstrained handwriting continues to be a difficult task for computers and handwritten image analysis is still an unsolved problem. Therefore, handwriting recognition provides a reasonable gap between humans and machines that could be exploited and used for new CAPTCHA challenges. In this paper we use handwritten word images and explore Gestalt psychology to motivate our image transformations. The deformation methods are individually described and results are presented and compared to other traditional handwritten image transformations. Several applications for Web services would find our handwritten CAPTCHA an excellent biometric for online security and a way of defending online services against abusive attacks.

Learning software engineering basic concepts using a five-phase game

Unfortunately, the stereotype of a software engineer or computer scientist is one who spends his whole day in a cubicle programming. Other aspects of software engineering, such as holding meetings with the customer and users to gather requirements, documenting requirements, design, and testing are not talked about. Many middle and high school students believe this stereotype and become disinterested in a prospective career in software engineering. As a result, we developed a game prototype to teach software engineering basic concepts to middle and high school students. Our game allows a student to explore the various phases of the software life cycle, which are requirements, design, implementation, testing, and maintenance. The waterfall software life cycle was practiced while developing this game, and every student in the Information Visualization course participated equally in the development of the game. In addition, visualization techniques were used to develop this game.

Securing the Web Using Human Perception and Visual Object Interpretation

Being motivated by the need for usable Web security systems, we present in this paper new image-based CAPTCHA systems that overcome the weaknesses of commercial CAPTCHAs. We describe Tree and Shape CAPTCHAs in addition to handwritten CAPTCHAs that feature visual objects transformed according to specific principles of cognitive psychology. These transformations, in addition to other security measures we describe, ensure that our CAPTCHAs are easily interpretable by humans but not by machines. We seek not only to provide useful CAPTCHAs, but to offer important insights into such fields as Information Visualization, Human-Computer Interaction, etc. Early testing results indicate that users find our CAPTCHAs an attractive alternative to text-based CAPTCHAs and are readily able to solve them based on cognitive abilities. Conversely, machine recognition is low due to the current inability to make use of these cognitive aids, thus making our CAPTCHAs a viable solution for cyber security.

An industry-academia team-teaching case study for software engineering capstone courses

Exposing software engineering students to newest industry practices and latest research and theories allows them to acquire and maintain the technical skills necessary to continually adjust to the rapid changes that occur in technology. Close interaction with industry members help the university and engineering programs identify real-world problems and their solutions and incorporate them into the curriculum. Software engineering capstone projects require the development of major software products and are usually either industry-generated or research-based. They are either assigned for the overall supervision of one instructor or each project is supervised by different instructors independently. In this paper, the authors present a case study in which the software engineering capstone projects have been team-coordinated by two instructors: one full-time faculty and one part-time faculty (full-time industry practitioner), thus combining two complementary sets of skills towards the mentoring of the software engineering students. Two capstone projects (one industry-generated and the other research-based) are also presented with the contribution of each instructor described.

Connecting campus and community through web development service-learning projects

In this paper we present a service learning course offered in Software Engineering Department at Fairfield University, which links two opposite cities together for good reasons. Web Development is a one-semester course required for undergraduate students and part of the Web Applications track for the graduate program. Currently, it operates with the service learning designation in the undergraduate catalog and annually being revised by universitys Office of Service Learning. The course stresses web site design, current web technologies, and client-side scripting languages, including a class project. The paper discusses the service learning framework of the course, with the major role played by the project. The root of our approach is the belief that the best way of learning in engineering is by doing and the best way of doing is by actively participating in the community. Two case studies in which the web development projects have been paired with local community partners are first presented and the outcomes and success of them are later discussed.