This paper proposes a special session on the use of computational methods for analyzing educational data. Computation has permeated all disciplines because it provides unique opportunities to represent knowledge and understand complex phenomena. In education, disciplines such as learning analytics and educational data mining have emerged to better understand educational phenomena. This special session will discuss three different approaches to use computational methods to analyze qualitative educational data. After the discussion, the participants will be able to implement these methods using R programming, while reflecting on how they can use these methods in their own context.

This Full Paper in the Research Category presents a principled approach to integrate machine learning within qualitative education research. More specifically, we show how to build on an existing theory or conceptual framework using machine learning applied to qualitative data in order to make valid conclusions. Our model is guided by the assessment triangle. One case study is presented. The study focuses on habits of mind and their relationship to course outcomes. Patterns among students are identified using the n-TARP clustering method and validated statistically. Students are represented by a profile representing the patterns they follow and their individual course outcomes. We subsequently test for the existence of a relationship between the patterns of habits of mind and the course outcomes using a statistical approach in order to meaningfully interpret the profiles.

Clustering a high-dimensional data set is known to be very difficult. In this paper, we show that this is not the case when the points to cluster correspond to images. More specifically, image data sets are shown to have a lot of structures, so much, so that projecting the set onto a random 1D linear subspace is likely to uncover a binary grouping among the images. Based on this observation, we propose a method to quantify the clusterability of a data set. The method is based on the probability density of a measure (S) of clusterability (in 1D) of the projection of the data onto a random line. After comparing the clusterability of image datasets with that of synthetically generated clusters, we conclude that these intriguing structures we find in image datasets do not fit the notion of clusters in the traditional sense. Further suggested by our observation is a fast method for clustering high-dimensional data in a hierarchical fashion; at each stage, the data is partitioned into two based on the binary clustering found in a 1D random projection of the data. Since most of the computations are performed in 1D, this approach is extremely efficient. But despite its simplicity, it achieves overall a better quality of clustering than existing high-dimensional clustering methods, not only for datasets representing image data, but for other real data sets as well. Our results highlight the need to re-examine our assumptions about high-dimensional clustering and the geometry of real datasets such as sets of images.

This paper proposed a workshop to introduce the use of computational tools and methods to analyze educational data. The workshop will demonstrate three different contexts in which these tools can be used to visualize and characterize patterns within educational data, and validate them using statistical techniques. Participants in this workshop will have the opportunity to learn how to implement these methods using R programming language.

We propose a new active learning activity called “slecture” (a contraction of the words “student” and “lecture”). In this activity, students create online lectures based on the in-class lectures of their course instructor, and post these online lectures on a publicly accessible website. As an experiment, slectures were integrated into the mandatory assignments of a large engineering graduate course with a diverse student population. In our implementation, the students were free to pick the topic (from a list provided by the instructor), medium, and language of instruction. The students' slectures were peer-reviewed at the end of the semester, and full credit was given for timely completion of the assignment. In a semester-end survey, students indicated that they learned more from making a slecture than from the other active learning techniques employed throughout the course. Furthermore, nearly 60% of the students rated the learning value of making a slecture at least as high as that of attending the lectures. The high level of enthusiasm for the slecture creation, especially among students who rated the learning value of the classroom lectures lower than the rest of the class, suggests that this activity may be a good way to engage students and stimulate learning.

We propose the pdf of W, where W is the normalized withinss after a 1D random projection, as a way to visualize the amount of structure contained in a set of images. Using this pdf, we show that real image datasets tend to have a lot of structure and that part of that structure is highly likely to be captured by a 1D random projection. According to our experiments, the structure of image datasets does not appear to be compatible with that of clusters. Nevertheless, the high degree of structure in image sets leads to an efficient and effective way of clustering image datasets using 1D random projections.

In this paper we describe two methods for hazardous material (hazmat) sign recognition. The first method is based on segment detection and grouping using geometric constraints. The second method is based on the use of a saliency map and convex quadrilateral detection. Our experimental results show a detection accuracy of 57.7% on a set of hazmat signs taken in the field under various lightning conditions, distances, and perspectives.

We have developed a system to translate and interpret printed documents (such as periodicals) using a commercially available mobile device (e.g., a mobile telephone) with an embedded camera. The system comprises an automatic layout analysis tool along with an Optical Character Recognition (OCR) engine and a translation engine. The translation engine combines Rule-Based Machine Translation (RBMT) software, a list of context-sensitive words/phrases, and an encyclopedia for a list of words. We implemented the proposed system on a Nokia N900 smartphone for translating newspaper articles from Spanish to English. Our tests show that the accuracy and speed of the system is mostly influenced by the accuracy and speed of the OCR method used. Our application requires 19.43 MB of memory and no more than 28 MB of dynamic memory. We show the ability to complete the process for roughly 410 words in as little as 65 seconds for high accuracy or 17 seconds for high speed, on average. The energy consumption in both cases is minimal.

We propose a system for helping individuals who follow a medical diet maintain this diet while visiting countries where a foreign language is spoken. Our focus is on diets where certain foods must either be restricted (e.g., metabolic diseases), avoided (e.g., food intolerance or allergies), or preferably consumed for medical reasons. However, our framework can be used to manage other diets (e.g., vegan) as well. The system is based on the use of a hand-held multimedia device such as a PDA or mobile telephone to analyze and/or disambiguate the content of foods offered on restaurant menus and interpret them in the context of specific diets. The system also provides the option to communicate diet-related instructions or information to a local person (e.g., a waiter) as well as obtain clarifications through dialogue. All computations are performed within the device and do not require a network connection. Real-time text translation is a challenge. We address this challenge with a light-weight, context-specific machine translation method. This method builds on a modification of existing open source Machine Translation (MT) software to obtain a fast and accurate translation. In particular, we describe a method we call n-gram consolidation that joins words in a language pair and increases the accuracy of the translation. We developed and implemented this system on the iPod Touch for English speakers traveling in Spain. Our tests indicate that our translation method yields the correct translation more often than general purpose translation engines such as Google Translate, and does so almost instantaneously. The memory requirements of the application, including the database of picture, are also well within the limits of the device.

Structure from motion (SFM) is the problem of recovering the geometry of a scene from a stream of images taken from unknown viewpoints. One popular approach to estimate the geometry of a scene is to track scene features on several images and reconstruct their position in 3-D. During this process, the unknown camera pose must also be recovered. Unfortunately, recovering the pose can be an ill-conditioned problem which, in turn, can make the SFM problem difficult to solve accurately. We propose an alternative formulation of the SFM problem with fixed internal camera parameters known a priori. In this formulation, obtained by algebraic variable elimination, the external camera pose parameters do not appear. As a result, the problem is better conditioned in addition to involving much fewer variables. Variable elimination is done in three steps. First, we take the standard SFM equations in projective coordinates and eliminate the camera orientations from the equations. We then further eliminate the camera center positions. Finally, we also eliminate all 3-D point positions coordinates, except for their depths with respect to the camera center, thus obtaining a set of simple polynomial equations of degree two and three. We show that, when there are merely a few points and pictures, these "depth-only equations" can be solved in a global fashion using homotopy methods. We also show that, in general, these same equations can be used to formulate a pose-free cost function to refine SFM solutions in a way that is more accurate than by minimizing the total reprojection error, as done when using the bundle adjustment method. The generalization of our approach to the case of varying internal camera parameters is briefly discussed.

We propose a low complexity method for sign detection and text localization in natural images. This method is designed for mobile applications (e.g., unmanned or handheld devices) in which computational and energy resources are limited. No prior assumption is made regarding the text size, font, language, or character set. However, the text is assumed to be located on a homogeneous background using a contrasting color. We have deployed our method on a Nokia N800 cellular phone as part of a system for automatic detection and translation of outdoor signs. This handheld device is equipped with a 0.3-megapixel camera capable of acquiring images of outdoor signs that typically contain enough details for the sign to be readable by a human viewer. Our experiments show that the text of these images can be accurately localized within the device in a fraction of a second.

We propose a low complexity method for segmentation of text regions in natural images. This algorithm is designed for mobile applications (e.g. unmanned or hand-held devices) in which computational and energy resources are limited. No prior assumption is made regarding the text size, font, language, character set or the camera angle. However, the text is assumed to be located on a piecewise homogeneous background with a contrasting color. We have deployed our method on a Nokia N800 Internet tablet as part of a system for automatic detection and translation of outdoor signs. Our experiments show that the 0.3 megapixel images taken by the phone camera can be accurately segmented within the device in a fraction of a second.

The motivation of this study is to be able to recognize planar objects consisting of “blobs” which can be modeled as Gaussian mixtures densities. Given are a two planar point-sets P̂ and P̃ consisting of point samples drawn from Gaussian mixtures ρ̂(x) and ρ̃(x), respectively. We propose a method to determine whether ρ̂(x) and ρ̃(x) have the same shape using P̂ and P̃. More precisely, we empirically compare the underlying distribution of distances of ρ̂(x) and ρ̃(x) using pairwise distances of the points contained in P̂ and P̃, respectively. The distribution of distances has been shown to be a lossless representation of generic Gaussian mixtures. Since distances are invariant under rotations and translations, this provides a workaround to the problem of aligning the objects before comparing them. We assess the method using synthetic data as well as real data consisting of halftoning patterns. Our results show a robust recognition performance.

Conventional electrophotographic printers tend to produce Moiré artifacts when used for printing images scanned from printed material such as books and magazines. We propose a novel noniterative, nonlinear, and space-variant descreening filter that removes a wide range of Moiré-causing screen frequencies in a scanned document while preserving image sharpness and edge detail. This filter is inspired by Perona-Malik's anisotropic diffusion equation. The amount of diffusion of the image intensity resulting from applying the filter is governed by an edge intensity estimate that is robust under halftone noise. More precisely, the filter extracts a spatial feature vector comprising local intensity gradients estimated from a local window in a presmoothed version of the noisy input image. Tunable nonlinear polynomial functions of this feature vector are then used to perform one iteration of a discrete diffusion controlled by the intensity gradient. The polynomial functions and feature extraction kernels are selected empirically in order to minimize computation while ensuring robust performance across a wide range of test images on a target imaging platform. The algorithm uses integer arithmetic, mostly relying on low-cost bit-wise shift and addition operations, and uses a strictly sequential architecture to provide a cost-effective and robust descreening solution in practical imaging devices including copiers and multifunction printers. We compare the performance of the proposed algorithm to other descreening solutions and demonstrate that the new algorithm improves quality over the existing methods while reducing computation.

We describe an automatic method for beautifying digital portraits by smoothing the skin of the face. The method builds on existing face detection and face feature alignment technology to automatically segment the face and neck areas to be smoothed. A smoothing filter is then applied to these areas. The resulting portraits are enhanced in a subtle and natural fashion.

Many applications in computer graphics require detailed 3D digital models of real-world environments. The automatic and semi-automatic modeling of such spaces presents several fundamental challenges. In this work, we present an easy and robust camera-based acquisition approach for the modeling of 3D scenes which is a significant departure from current methods. Our approach uses a novel pose-free formulation for 3D reconstruction. Unlike self-calibration, omitting pose parameters from the acquisition process implies no external calibration data must be computed or provided. This serves to significantly simplify acquisition, to fundamentally improve the robustness and accuracy of the geometric reconstruction given noise in the measurements or error in the initial estimates, and to allow using uncalibrated active correspondence methods to obtain robust data. Aside from freely taking pictures and moving an uncalibrated digital projector, scene acquisition and scene point reconstruction is automatic and requires pictures from only a few viewpoints. We demonstrate how the combination of these benefits has enabled us to acquire several large and detailed models ranging from 0.28 to 2.5 million texture-mapped triangles.

We present a hierarchical method for segmenting text areas in natural images. The method assumes that the text is written with a contrasting color on a more or less uniform background. No assumption is made regarding the language or character set used to write the text. In particular, the text can contain simple graphics or symbols. The key feature of our approach is that we first concentrate on finding the background of the text, before testing whether there is actually text on the background. Since uniform areas are easy to find in natural images, and since text backgrounds define areas which contain "holes" (where the text is written) we thus look for uniform areas containing "holes" and label them as text backgrounds candidates. Each candidate area is then further tested for the presence of text within its convex hull. We tested our method on a database of 65 images including English and Urdu text. The method correctly segmented all the text areas in 63 of these images, and in only 4 of these were areas that do not contain text also segmented.

Conventional electrophotographic printers tend to produce Moire artifacts when used for printing images scanned from printed material such as books and magazines. Inspired by anisotropic diffusion, we propose a novel non-iterative, non-linear, and space-variant de- screening filter that removes a wide range of Moire-causing screen frequencies in a scanned document while preserving image sharpness and edge detail. The amount of diffusion of the image intensity resulting from applying the filter is governed by an estimate of the gradient that is robust under halftone noise. More precisely, the filter extracts a spatial feature vector comprising local intensity gradients estimated from a local window in a pre-smoothed version of the noisy input image. Tunable non-linear polynomial functions of this feature vector are then used to perform one iteration of a discrete diffusion controlled by the intensity gradient. We compare the performance of the proposed algorithm to other descreening solutions and demonstrate that the new algorithm improves quality over the existing methods while reducing computation.

Reconstructing large models from images is a significant challenge for computer vision, computer graphics, and related fields. In this paper, we present an approach for simplifying the reconstruction process by mathematically eliminating external camera parameters. This results in less parameters to estimate and in an overall significantly more robust and accurate reconstruction. We reformulate the problem in such a manner as to be able to identify invariants, eliminate superfluous parameters, and measure the performance of our formulation under various conditions. We compare a two-step camera orientation-free method, where the majority of the points are reconstructed using a linear equation set, and a camera position-and- orientation free method, using a degree-two equation set. Both approaches use a full perspective camera and are applied to synthetic and real-world datasets.

It has been recently discovered that a faithful representation for the shape of some simple distributions can be constructed using invariant statistics [1,2]. In this paper, we consider the more general case of a Gaussian mixture model. We show that the shape of generic Gaussian mixtures can be represented without any loss by the distribution of the distance between two points independently drawn from this mixture. In other words, we show that if their respective distributions of distances are the same, then there exists a rigid transformation mapping one Gaussian mixture onto the other. Our main motivation is the problem of recognizing the shape of an object represented by points given noisy measurements of these points which can be modeled as a Gaussian mixture.

Accurately reconstructing the 3D geometry of a scene or object observed on 2D images is a difficult problem: there are many unknowns involved (camera pose, scene structure, depth factors) and solving for all these unknowns simultaneously is computationally intensive and suffers from numerical instability. In this paper, we algebraically decouple some of the unknowns so that they can be solved for independently. Decoupling the pose from the other variables has been previously discussed in the literature. Unfortunately, pose estimation is an ill-conditioned problem. In this paper, we algebraically eliminate all the camera pose parameters (i.e., position and orientation) from the structure-from-motion equations for an internally calibrated camera. We then also fully eliminate the structure coordinates from the equations. This yields a very simple set of homogeneous polynomial equations of low degree involving only the depths of the observed points. When considering a small number of tracked points and pictures (e.g., five points on two pictures), these equations can be solved using the sparse resultant method.

Structure from motion (SFM) is the problem of reconstructing the geometry of a scene from a stream of images. In this problem, the geometry of the scene must be inferred from images, along with the camera pose parameters. Bundle adjustment (BA) is a refinement method used to improve SFM solutions. It consists in simultaneously improving a set of initial estimates for all parameters (structure and camera pose) by minimizing a global cost function. It is generally considered to be highly accurate, and so is typically used as a last refinement step in most current SFM methods. Unfortunately, estimating the pose of the camera from a stream of images is an ill-conditioned problem. We thus propose a BA adjustment formulation which does not involve solving for the camera orientations. We tested this approach on several real world models. The numerical results obtained show that this approach is much less affected by noise than traditional BA.