A Query Expansion Framework in Image Retrieval Domain Based on Local and Global Analysis

We present an image retrieval framework based on automatic query expansion in a concept feature space by generalizing the vector space model of information retrieval. In this framework, images are represented by vectors of weighted concepts similar to the keyword-based representation used in text retrieval. To generate the concept vocabularies, a statistical model is built by utilizing Support Vector Machine (SVM)-based classification techniques. The images are represented as "bag of concepts" that comprise perceptually and/or semantically distinguishable color and texture patches from local image regions in a multi-dimensional feature space. To explore the correlation between the concepts and overcome the assumption of feature independence in this model, we propose query expansion techniques in the image domain from a new perspective based on both local and global analysis. For the local analysis, the correlations between the concepts based on the co-occurrence pattern, and the metrical constraints based on the neighborhood proximity between the concepts in encoded images, are analyzed by considering local feedback information. We also analyze the concept similarities in the collection as a whole in the form of a similarity thesaurus and propose an efficient query expansion based on the global analysis. The experimental results on a photographic collection of natural scenes and a biomedical database of different imaging modalities demonstrate the effectiveness of the proposed framework in terms of precision and recall.     

Developing and testing a scale of moral thinking and communication (MTC) functioning: a preliminary study and its implications for moral development and education

The purpose of this study was to develop and test a scale assessing students’ moral thinking and communication (MTC) functioning as well as to explore the implications for moral development and education. The rationale of MTC functioning, including interaction of four independent competencies: moral awareness, moral judgement, moral discourse, and moral decision-making, is primarily adapted from L. Kohlberg’s theory, Neo-Kohlbergian theory, J. Habermas’s and K.-O. Apel’s discourse ethics, and L. Hinman’s ethical pluralism. There were two studies in the development of the measure. The resulting instrument contained four moral dilemmas differing by a focus on micro-moral and macro-moral levels. Findings from the studies indicated the MTC scale has acceptable psychometric properties and describe Taiwanese students as attending to the difficult problems of integrating local and international cultural norms. Additionally, the measure provides a detailed picture of students’ moral thinking and communication functioning. These results are discussed in terms of implications for moral theory and assessment of moral education.     

Does Moral Judgment Development Reduce to Political Attitudes or Verbal Ability? Evidence Using the Defining Issues Test

Recent critics of the Defining Issues Test (DIT) suggest that moral judgment development as currently measured is neither developmental nor moral. Instead, scores on the DIT are claimed to be the result of political attitudes or verbal ability. In making such claims, these critics raise the possibility that the validity of the DIT is suspect as well as the construct it purports to measure. We begin our response with an overview of the various claims that DIT scores reduce to political attitudes or verbal ability. Then, a relevant sample of the DIT literature is summarized in order to assess the degree to which relationships between DIT scores and criterion variables typically used to support the validity of the DIT can be explained by political attitudes or verbal ability. This summary suggests that moral judgment development as measured by the DIT provides a unique source of information that cannot be explained by general/verbal ability or political attitudes.