A multimedia indexing and retrieval framework for multimedia database systems

The main challenges of multimedia data retrieval lie in the effective mapping between low-level features and high-level concepts, and in the individual users' subjective perceptions of multimedia content. ^ The objectives of this dissertation are to develop an integrated multimedia indexing and retrieval framework with the aim to bridge the gap between semantic concepts and low-level features. To achieve this goal, a set of core techniques have been developed, including image segmentation, content-based image retrieval, object tracking, video indexing, and video event detection. These core techniques are integrated in a systematic way to enable the semantic search for images/videos, and can be tailored to solve the problems in other multimedia related domains. In image retrieval, two new methods of bridging the semantic gap are proposed: (1) for general content-based image retrieval, a stochastic mechanism is utilized to enable the long-term learning of high-level concepts from a set of training data, such as user access frequencies and access patterns of images. (2) In addition to whole-image retrieval, a novel multiple instance learning framework is proposed for object-based image retrieval, by which a user is allowed to more effectively search for images that contain multiple objects of interest. An enhanced image segmentation algorithm is developed to extract the object information from images. This segmentation algorithm is further used in video indexing and retrieval, by which a robust video shot/scene segmentation method is developed based on low-level visual feature comparison, object tracking, and audio analysis. Based on shot boundaries, a novel data mining framework is further proposed to detect events in soccer videos, while fully utilizing the multi-modality features and object information obtained through video shot/scene detection. ^ Another contribution of this dissertation is the potential of the above techniques to be tailored and applied to other multimedia applications. This is demonstrated by their utilization in traffic video surveillance applications. The enhanced image segmentation algorithm, coupled with an adaptive background learning algorithm, improves the performance of vehicle identification. A sophisticated object tracking algorithm is proposed to track individual vehicles, while the spatial and temporal relationships of vehicle objects are modeled by an abstract semantic model. ^

Menu Analysis: Review and Evaluation

In the article - Menu Analysis: Review and Evaluation - by Lendal H. Kotschevar, Distinguished Professor School of Hospitality Management, Florida International University, Kotschevar’s initial statement reads: “Various methods are used to evaluate menus. Some have quite different approaches and give different information. Even those using quite similar methods vary in the information they give. The author attempts to describe the most frequently used methods and to indicate their value. A correlation calculation is made to see how well certain of these methods agree in the information they give.” There is more than one way to look at the word menu. The culinary selections decided upon by the head chef or owner of a restaurant, which ultimately define the type of restaurant is one way. The physical outline of the food, which a patron actually holds in his or her hand, is another. These descriptions are most common to the word, menu. The author primarily concentrates on the latter description, and uses the act of counting the number of items sold on a menu to measure the popularity of any particular item. This, along with a formula, allows Kotschevar to arrive at a specific value per item. Menu analysis would appear a difficult subject to broach. How does a person approach a menu analysis, how do you qualify and quantify a menu; it seems such a subjective exercise. The author offers methods and outlines on approaching menu analysis from empirical perspectives. “Menus are often examined visually through the evaluation of various factors. It is a subjective method but has the advantage of allowing scrutiny of a wide range of factors which other methods do not,” says Distinguished Professor, Kotschevar. “The method is also highly flexible. Factors can be given a score value and scores summed to give a total for a menu. This allows comparison between menus. If the one making the evaluations knows menu values, it is a good method of judgment,” he further offers. The author wants you to know that assigning values is fundamental to a pragmatic menu analysis; it is how the reviewer keeps score, so to speak. Value merit provides reliable criteria from which to gauge a particular menu item. In the final analysis, menu evaluation provides the mechanism for either keeping or rejecting selected items on a menu. Kotschevar provides at least three different matrix evaluation methods; they are defined as the Miller method, the Smith and Kasavana method, and the Pavesic method. He offers illustrated examples of each via a table format. These are helpful tools since trying to explain the theories behind the tables would be difficult at best. Kotschevar also references examples of analysis methods which aren’t matrix based. The Hayes and Huffman - Goal Value Analysis - is one such method. The author sees no one method better than another, and suggests that combining two or more of the methods to be a benefit.

A study of the implementation of junior college *evaluation system in Taiwan

Since the establishment of the evaluation system in 1975, the junior colleges in the Republic of China (Taiwan), have gone through six formal evaluations. We know that evaluation in schooling, like quality control in businesses, should be a systematic, formal, and a continual process. It can doubtless serve as a strategy to refine the quality of education. The purpose of this research is to explore the current practice of junior college evaluation in Taiwan. This provides insight into the development of and quality of the current evaluation system. Moreover, this study also identified the source of problems with the current evaluation system and provided suggestion for improvements.^ In order to attain the above purposes, this research was undertaken in both theoretical and practical ways. First, theoretically, on the basis of a literature review, the theories of educational evaluation and, according to the course and principles of development, a view of the current practice in Taiwan. Secondly, in practice, by means of questionnaires, an analysis of the views of evaluation committeemen, junior college presidents, and administrators were obtained on evaluation models, methods, contents, organization, functions, criteria, grades reports, and others with suggestions for improvement. The summary of findings concludes that most evaluators and evaluatees think the purpose of evaluation can help the colleges explore their difficulties and problems. In addition, it was found that there is significant difference between the two groups regarding the evaluation methods, contents, organization, functions, criteria, grades reports and others, while analyzing these objective data forms the basis for an improved method of evaluation for Junior Colleges in Taiwan. ^

Dynamic image precompensation for improving visual performance of computer users with ocular aberrations

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.

Dynamic Image Precompensation for Improving Visual Performance of Computer Users with Ocular Aberrations

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.

Mathematics: Going Beyond the Academic Discipline

Mathematics is rigidly classified as an academic discipline. This determines curriculum content and teaching and evaluation methods. These methods can give rise to negative views of mathematics, resulting in increased math anxiety. Educators, therefore, need to look beyond the discipline to provide a classroom environment that meets students’ needs.

Monitoring the Accuracy of Multiple Occupancy Forecasts

Corporate executives closely monitor the accuracy of their hotels' occupancy fore- casts since important decisions are based upon these predictions. This study lists the criteria for selecting an appropriate error measure. It discusses several evaluation methods focusing on statistical significance tests and demonstrates the use of two adequate evaluation methods: Mincer- Zamowitz's efficiency test and Wilcoxon's Non-Parametric Matched-Pairs Signed- Ranks test.

Rigid and non-rigid point-based medical image registration

The primary goal of this dissertation is to develop point-based rigid and non-rigid image registration methods that have better accuracy than existing methods. We first present point-based PoIRe, which provides the framework for point-based global rigid registrations. It allows a choice of different search strategies including (a) branch-and-bound, (b) probabilistic hill-climbing, and (c) a novel hybrid method that takes advantage of the best characteristics of the other two methods. We use a robust similarity measure that is insensitive to noise, which is often introduced during feature extraction. We show the robustness of PoIRe using it to register images obtained with an electronic portal imaging device (EPID), which have large amounts of scatter and low contrast. To evaluate PoIRe we used (a) simulated images and (b) images with fiducial markers; PoIRe was extensively tested with 2D EPID images and images generated by 3D Computer Tomography (CT) and Magnetic Resonance (MR) images. PoIRe was also evaluated using benchmark data sets from the blind retrospective evaluation project (RIRE). We show that PoIRe is better than existing methods such as Iterative Closest Point (ICP) and methods based on mutual information. We also present a novel point-based local non-rigid shape registration algorithm. We extend the robust similarity measure used in PoIRe to non-rigid registrations adapting it to a free form deformation (FFD) model and making it robust to local minima, which is a drawback common to existing non-rigid point-based methods. For non-rigid registrations we show that it performs better than existing methods and that is less sensitive to starting conditions. We test our non-rigid registration method using available benchmark data sets for shape registration. Finally, we also explore the extraction of features invariant to changes in perspective and illumination, and explore how they can help improve the accuracy of multi-modal registration. For multimodal registration of EPID-DRR images we present a method based on a local descriptor defined by a vector of complex responses to a circular Gabor filter.

A high efficient biometrics approach for unconstrained iris segmentation and recognition

This dissertation develops an innovative approach towards less-constrained iris biometrics. Two major contributions are made in this research endeavor: (1) Designed an award-winning segmentation algorithm in the less-constrained environment where image acquisition is made of subjects on the move and taken under visible lighting conditions, and (2) Developed a pioneering iris biometrics method coupling segmentation and recognition of the iris based on video of moving persons under different acquisitions scenarios. The first part of the dissertation introduces a robust and fast segmentation approach using still images contained in the UBIRIS (version 2) noisy iris database. The results show accuracy estimated at 98% when using 500 randomly selected images from the UBIRIS.v2 partial database, and estimated at 97% in a Noisy Iris Challenge Evaluation (NICE.I) in an international competition that involved 97 participants worldwide involving 35 countries, ranking this research group in sixth position. This accuracy is achieved with a processing speed nearing real time. The second part of this dissertation presents an innovative segmentation and recognition approach using video-based iris images. Following the segmentation stage which delineates the iris region through a novel segmentation strategy, some pioneering experiments on the recognition stage of the less-constrained video iris biometrics have been accomplished. In the video-based and less-constrained iris recognition, the test or subject iris videos/images and the enrolled iris images are acquired with different acquisition systems. In the matching step, the verification/identification result was accomplished by comparing the similarity distance of encoded signature from test images with each of the signature dataset from the enrolled iris images. With the improvements gained, the results proved to be highly accurate under the unconstrained environment which is more challenging. This has led to a false acceptance rate (FAR) of 0% and a false rejection rate (FRR) of 17.64% for 85 tested users with 305 test images from the video, which shows great promise and high practical implications for iris biometrics research and system design.

Color-based surface reflectance separation for scene illumination estimation and rendering

Given the importance of color processing in computer vision and computer graphics, estimating and rendering illumination spectral reflectance of image scenes is important to advance the capability of a large class of applications such as scene reconstruction, rendering, surface segmentation, object recognition, and reflectance estimation. Consequently, this dissertation proposes effective methods for reflection components separation and rendering in single scene images. Based on the dichromatic reflectance model, a novel decomposition technique, named the Mean-Shift Decomposition (MSD) method, is introduced to separate the specular from diffuse reflectance components. This technique provides a direct access to surface shape information through diffuse shading pixel isolation. More importantly, this process does not require any local color segmentation process, which differs from the traditional methods that operate by aggregating color information along each image plane. ^ Exploiting the merits of the MSD method, a scene illumination rendering technique is designed to estimate the relative contributing specular reflectance attributes of a scene image. The image feature subset targeted provides a direct access to the surface illumination information, while a newly introduced efficient rendering method reshapes the dynamic range distribution of the specular reflectance components over each image color channel. This image enhancement technique renders the scene illumination reflection effectively without altering the scene’s surface diffuse attributes contributing to realistic rendering effects. ^ As an ancillary contribution, an effective color constancy algorithm based on the dichromatic reflectance model was also developed. This algorithm selects image highlights in order to extract the prominent surface reflectance that reproduces the exact illumination chromaticity. This evaluation is presented using a novel voting scheme technique based on histogram analysis. ^ In each of the three main contributions, empirical evaluations were performed on synthetic and real-world image scenes taken from three different color image datasets. The experimental results show over 90% accuracy in illumination estimation contributing to near real world illumination rendering effects. ^

Evaluation of the evidential value of the elemental composition of glass, ink and paper by laser-based microspectrochemical methods

Elemental analysis can become an important piece of evidence to assist the solution of a case. The work presented in this dissertation aims to evaluate the evidential value of the elemental composition of three particular matrices: ink, paper and glass. In the first part of this study, the analytical performance of LIBS and LA-ICP-MS methods was evaluated for paper, writing inks and printing inks. A total of 350 ink specimens were examined including black and blue gel inks, ballpoint inks, inkjets and toners originating from several manufacturing sources and/or batches. The paper collection set consisted of over 200 paper specimens originating from 20 different paper sources produced by 10 different plants. Micro-homogeneity studies show smaller variation of elemental compositions within a single source (i.e., sheet, pen or cartridge) than the observed variation between different sources (i.e., brands, types, batches). Significant and detectable differences in the elemental profile of the inks and paper were observed between samples originating from different sources (discrimination of 87–100% of samples, depending on the sample set under investigation and the method applied). These results support the use of elemental analysis, using LA-ICP-MS and LIBS, for the examination of documents and provide additional discrimination to the currently used techniques in document examination. In the second part of this study, a direct comparison between four analytical methods (µ-XRF, solution-ICP-MS, LA-ICP-MS and LIBS) was conducted for glass analyses using interlaboratory studies. The data provided by 21 participants were used to assess the performance of the analytical methods in associating glass samples from the same source and differentiating different sources, as well as the use of different match criteria (confidence interval (±6s, ±5s, ±4s, ±3s, ±2s), modified confidence interval, t-test (sequential univariate, p=0.05 and p=0.01), t-test with Bonferroni correction (for multivariate comparisons), range overlap, and Hotelling's T2 tests. Error rates (Type 1 and Type 2) are reported for the use of each of these match criteria and depend on the heterogeneity of the glass sources, the repeatability between analytical measurements, and the number of elements that were measured. The study provided recommendations for analytical performance-based parameters for µ-XRF and LA-ICP-MS as well as the best performing match criteria for both analytical techniques, which can be applied now by forensic glass examiners.

Evaluation of Some Statistical Methods for the Identification of Differentially Expressed Genes

Microarray platforms have been around for many years and while there is a rise of new technologies in laboratories, microarrays are still prevalent. When it comes to the analysis of microarray data to identify differentially expressed (DE) genes, many methods have been proposed and modified for improvement. However, the most popular methods such as Significance Analysis of Microarrays (SAM), samroc, fold change, and rank product are far from perfect. When it comes down to choosing which method is most powerful, it comes down to the characteristics of the sample and distribution of the gene expressions. The most practiced method is usually SAM or samroc but when the data tends to be skewed, the power of these methods decrease. With the concept that the median becomes a better measure of central tendency than the mean when the data is skewed, the tests statistics of the SAM and fold change methods are modified in this thesis. This study shows that the median modified fold change method improves the power for many cases when identifying DE genes if the data follows a lognormal distribution.

Rigid and Non-rigid Point-based Medical Image Registration

The primary goal of this dissertation is to develop point-based rigid and non-rigid image registration methods that have better accuracy than existing methods. We first present point-based PoIRe, which provides the framework for point-based global rigid registrations. It allows a choice of different search strategies including (a) branch-and-bound, (b) probabilistic hill-climbing, and (c) a novel hybrid method that takes advantage of the best characteristics of the other two methods. We use a robust similarity measure that is insensitive to noise, which is often introduced during feature extraction. We show the robustness of PoIRe using it to register images obtained with an electronic portal imaging device (EPID), which have large amounts of scatter and low contrast. To evaluate PoIRe we used (a) simulated images and (b) images with fiducial markers; PoIRe was extensively tested with 2D EPID images and images generated by 3D Computer Tomography (CT) and Magnetic Resonance (MR) images. PoIRe was also evaluated using benchmark data sets from the blind retrospective evaluation project (RIRE). We show that PoIRe is better than existing methods such as Iterative Closest Point (ICP) and methods based on mutual information. We also present a novel point-based local non-rigid shape registration algorithm. We extend the robust similarity measure used in PoIRe to non-rigid registrations adapting it to a free form deformation (FFD) model and making it robust to local minima, which is a drawback common to existing non-rigid point-based methods. For non-rigid registrations we show that it performs better than existing methods and that is less sensitive to starting conditions. We test our non-rigid registration method using available benchmark data sets for shape registration. Finally, we also explore the extraction of features invariant to changes in perspective and illumination, and explore how they can help improve the accuracy of multi-modal registration. For multimodal registration of EPID-DRR images we present a method based on a local descriptor defined by a vector of complex responses to a circular Gabor filter.