Writer identification approach based on bag of words with OBI features

Handwriter identification aims to simplify the task of forensic experts by providing them with semi-automated tools in order to enable them to narrow down the search to determine the final identification of an unknown handwritten sample. An identification algorithm aims to produce a list of predicted writers of the unknown handwritten sample ranked in terms of confidence measure metrics for use by the forensic expert will make the final decision.Most existing handwriter identification systems use either statistical or model-based approaches. To further improve the performances this paper proposes to deploy a combination of both approaches using Oriented Basic Image features and the concept of graphemes codebook. To reduce the resulting high dimensionality of the feature vector a Kernel Principal Component Analysis has been used. To gauge the effectiveness of the proposed method a performance analysis, using IAM dataset for English handwriting and ICFHR 2012 dataset for Arabic handwriting, has been carried out. The results obtained achieved an accuracy of 96% thus demonstrating its superiority when compared against similar techniques.     

Effects of Multimedia versus Live Professional Development on Teachers’ and Students’ Performance Related to the Question Exploration Routine

In each of two studies, teachers were randomly assigned to either a Virtual Workshop (VW) group that used a computerized professional development program or an Actual Workshop (AW) group that participated in face-to-face professional development, including discussion, feedback, and collaboration. In both studies, teachers’ posttest scores related to their knowledge of the Question Exploration Routine and their plans for using it were significantly higher than their pretest scores. In Study 2, both groups’ posttest scores with regard to implementation and planning of the routine were significantly greater than their pretest scores. There were no significant differences between the groups at posttesting on any measure. The posttest knowledge scores of the whole groups of students and the subgroups of students with LD being taught by both groups of teachers were significantly higher than their pretest scores. All teachers indicated that they were satisfied with the training and the routine. VW teachers in both studies indicated that they were satisfied with the software program.     

The ethics of polyvocal ethnography: empowering vs. textualizing children and teachers

Polyvocal approaches allow researchers and informants to interact on a more equal footing and informants’ voices to be heard in the final text. But research methods intended to empower informants also can be a source of unanticipated authorial power ‐ the power to confront informants with unsolicited self‐reflections and to textualize people's lives and words. The authors reflect on those ethical dilemmas in this article.