Engineering courses often make use of term projects to tie together course concepts and enable open-ended learning. Projects can also be used to teach entrepreneurial-minded learning (EML). At Rose-Hulman we offer mobile/web app development in 4 different courses. In each of these courses, we have two goals for our students: (1) to master fundamental technical skills for that platform and (2) to create an app of their choosing to add real value for users of the app. To meet the first goal, we use a traditional approach with a series of hands-on lectures and labs. To meet the second goal, students complete a 10-week term project in which they work with a partner to identify a real world need and create a high quality app to meet that need. We surveyed students about their motivation and learning experience in the project. Students reported that self-selected projects that add value for others helped motivate them to work harder in the course which improves student learning. Students leave our app development courses with both an understanding of the technical material and a hands-on learning opportunity where they solve real problems for users.

The face-to-face interaction in a traditional classroom on campus provides many benefits to students: the ability to ask questions and get immediate feedback, external motivation from the instructor and peers to succeed, the joy of interaction, and the ability to work face-to-face with classmates on projects. Meanwhile, video-based, online instruction offers several different benefits: convenience for students due to flexibility in time and place of learning, ease of reviewing materials for mastery, and the ability to work at one's own pace. When given the choice between these two formats, which do students choose? Students enrolled in an upper-level mobile app development course could opt to attend class with face-to-face instruction, to watch videos of the instructor, or to switch between the two formats as they saw fit. Students were given pre- and post-surveys asking them which format they preferred and why. Results indicate that slightly more than half of the students chose the video-based option and that students chose as they did for expected reasons, such as wanting to ask questions in class or wanting the flexibility to watch and re-watch video on demand. More interestingly, results also indicated that students who chose video did not suffer from the dropout and failure rates so commonly reported in the literature, that learning was equally effective using both formats, and that students' expectations of which format they would use were quite different from what they ended up using. However, with a small sample size at one institution, local factors, like scheduling the course during lunchtime, also played a role in students' choices.

The Fulbright Scholar Program is the flagship academic exchange program of the U.S. Department of State; approximately 1,100 American scholars travel worldwide annually to lecture and conduct research. The program is open to all U.S. citizens with university teaching experience and a Ph.D. or equivalent professional/terminal degree. Opportunities for Computer Science educators to win Fulbright scholarships are many. The goal of this panel is to inform the community of computer science educators about the Fulbright program, including the application process, and to answer questions about the program. After an introduction to the program at large, the panelists will each give a 10-15 minute overview of their personal experience as a Fulbright scholar in 2011-2012, leaving ample time for questions from educators considering applying for a Fulbright scholarship. The panelists will offer diverse perspectives based on their experiences in India, Zambia, and Siberia.

Semantic scene classification, the process of categorizing photographs into a discrete set of classes using pattern recognition techniques, is a useful ability for image annotation, organization and retrieval. The literature has focused on classifying outdoor scenes such as beaches and sunsets. Here, we focus on a much more difficult problem, that of differentiating between typical rooms in home interiors, such as bedrooms or kitchens. This requires robust image feature extraction and classification techniques, such as SIFT (scale-invariant feature transform) features and Adaboost classifiers. To this end, we derived SIFT keypoint histograms, an efficient image representation that utilizes variance information from linear discriminant analysis. We compare SIFT keypoint histograms with other features such as spatial color moments and compare Adaboost with support vector machine classifiers. We outline the various techniques used, show their advantages, disadvantages, and actual performance, and determine the most effective algorithm of those tested for home interior classification. Furthermore, we present results of pairwise classification of 7 rooms typically found in homes.

The decline in computing enrollments is a global concern that necessitates that every potentially successful computing student be targeted for support and development. The needs of technically experienced, highly capable first-term college students are unique, and no less challenging than the needs of their lesser-prepared peers. In order to attract advanced first-year students to further computing studies, we need to understand better how instruction can meet their needs. This paper reports the results of a study in which advanced first-term computing students were challenged to become in-depth researcher-learners and to teach the content they acquired to their peers. The results demonstrate that students and instructors alike perceive that the students made significant improvements in communication, presentation, and teaming skills and acquired deep content knowledge from their experience in the course. The data also show that students were extremely uncomfortable with the paradigm shift in their learning environment. These results suggest that anxiety-reducing changes are needed for the course, but that overall, the teacher-researcherlearner concept is very beneficial for increasing the understanding and learning of advanced first year computing students.

Semantic scene classification is a challenging problem in computer vision. In contrast to the common approach of using low-level features computed from the whole scene, we propose "scene parsing" utilizing semantic object detectors (e.g., sky, foliage, and pavement) and region-based scene-configuration models. Because semantic detectors are faulty in practice, it is critical to develop a region-based generative model of outdoor scenes based on characteristic objects in the scene and spatial relationships between them. Since a fully connected scene configuration model is intractable, we chose to model pairwise relationships between regions and estimate scene probabilities using loopy belief propagation on a factor graph. We demonstrate the promise of this approach on a set of over 2000 outdoor photographs, comparing it with existing discriminative approaches and those using low-level features

Semantic scene classification is a useful, yet challenging problem in image understanding. Most existing systems are based on low-level features, such as color or texture, and succeed to some extent. Intuitively, semantic features, such as sky, water, or foliage, which can be detected automatically, should help close the so-called semantic gap and lead to higher scene classification accuracy. To answer the question of how accurate the detectors themselves need to be, we adopt a generally applicable scene classification scheme that combines semantic features and their spatial layout as encoded implicitly using a block-based method. Our scene classification results show that although our current detectors collectively are still inadequate to outperform low-level features under the same scheme, semantic features hold promise as simulated detectors can achieve superior classification accuracy once their own accuracies reach above a nontrivial 90%

Principal Component Analysis (PCA) has been widely used to extract features for pattern recognition problems such as object recognition. Oliva and Torralba used “spatial envelope” properties derived from PCA to classify images as manmade or natural. While our implementation closely matched theirs in accuracy on a similar (Corel) dataset, we found that consumer photos, which are far less constrained in content and imaging conditions, present a greater challenge for the algorithm (as is typical in image understanding). We present an alternative approach to more robust naturalness classification, using overcomplete Independent Components Analysis (ICA) directly on the Fourier-transformed image to derive sparse representations as more effective features for classification. We demonstrated that our ICA-based features are superior to the PCA-based features on a large set of consumer photographs.

Semantic region labeling in outdoor scenes, e.g., identifying sky, grass, foliage, water, and snow, facilitates content-based image retrieval, organization, and enhancement. A major limitation of current object detectors is the significant number of misclassifications due to the similarities in color and texture characteristics of various object types and lack of context information. Building on previous work of spatial context-aware object detection, we have developed a further improved system by modeling and enforcing spatial context constraints specific to individual scene type. In particular, the scene context, in the form of factor graphs, is obtained by learning and subsequently used via MAP estimation to reduce misclassification by constraining the object detection beliefs to conform to the spatial context models. Experimental results show that the richer spatial context models improve the accuracy of object detection over the individual object detectors and the general outdoor scene model.

Automatic image orientation detection for natural images is a useful, yet challenging research topic. Humans use scene context and semantic object recognition to identify the correct image orientation. However, it is difficult for a computer to perform the task in the same way because current object recognition algorithms are extremely limited in their scope and robustness. As a result, existing orientation detection methods were built upon low-level vision features such as spatial distributions of color and texture. Discrepant detection rates have been reported for these methods in the literature. We have developed a probabilistic approach to image orientation detection via confidence-based integration of low-level and semantic cues within a Bayesian framework. Our current accuracy is 90 percent for unconstrained consumer photos, impressive given the findings of a psychophysical study conducted recently. The proposed framework is an attempt to bridge the gap between computer and human vision systems and is applicable to other problems involving semantic scene content understanding.

The performance of an exemplar-based scene classification system depends largely on the size and quality of its set of training exemplars, which can be limited in practice. In addition, in nontrivial data sets, variations in scene content as well as distracting regions may exist in many testing images to prohibit good matches with the exemplars. Various boosting schemes have been proposed in machine learning, focusing on the feature space. We introduce the novel concept of image-transform bootstrapping using transforms in the image space to address such issues. In particular, three major schemes are described for exploiting this concept to augment training, testing, and both. We have successfully applied it to three applications of increasing difficulty: sunset detection, outdoor scene classification, and automatic image orientation detection. It is shown that appropriate transforms and meta-classification methods can be selected to boost performance according to the domain of the problem and the features/classifier used.

Knowledge of the semantic classification of an image can be used to improve the accuracy of queries in content-based image organization and retrieval and to provide customized image enhancement. We developed an exemplar-based system for classifying sunset scenes. However, the performance of such a system depends largely on the size and quality of the set of training exemplars, which can be limited in practice. In addition, variations in scene content, as well as distracting regions, may exist in many testing images to prohibit good matches with the exemplars. We propose using simulated spatial and temporal image recomposition to address such issues. The recomposition schemes boost the recall of sunset images from a reasonably large data set by 10%, while holding the false positive rate constant.