Thesis (Ed.D.)--Teachers College, Columbia University. / Typescript; issued also on microfilm. Sponsor: Justin Schorr. Dissertation Committee: William J. Mahoney. Includes bibliographical references.

Thesis (Ph. D.)--Michigan State University. Media and Information Studies, 2008. / Title from PDF t.p. (viewed on July 23, 2009) Includes bibliographical references (p. 218-234). Also issued in print.

Thesis (Ph. D.)--University of California, San Diego, 2004. / Vita. Includes bibliographical references.

Thesis (M.S.)--University of Michigan, 1997. / Includes bibliographical references.

Thesis (M.S.)--Rochester Institute of Technology, 1994. / Typescript. Includes bibliographical references (leaves 134-138).

Thesis (M.S.)--Rochester Institute of Technology, 1995. / Typescript. Includes bibliographical references (leaves 53-56).

Typescript. Includes bibliographical references (p. 321-325).

Thesis (Ph. D.)--University of California, San Diego, 2010. / Title from 1st page of PDF file (viewed July 8, 2010). Available via ProQuest Digital Dissertations. Vita. Includes bibliographical references: Leaves 147-154.

Banana has become the most commonly consumed fresh fruit among US population. It is a challenge to use computer vision to divide touching bananas, for this purpose a novel image segmentation algorithm is proposed, combining k-means and the watershed transformation. The first part is to extract the background, achieved using a K-means based in the HS space, the second part is individual banana segmentation where a smarter selection of the initial markers from where the watershed transformation grows is attained fusing two morphological filters with different structural elements. The validation of the proposed algorithm has been conducted using 124 experimentally capture banana pictures manually segmented. For background extraction K-means in HS space produced the best performance over the other two tested (Otsu, K-means(L*a*b*), getting average a F1 Score average of 96.99%, Otsu and K-means(L*a*b*) scored 82.58% and 88.06% respectively. The result of the watershed segmentation was also compared with the manual segmentation; The overall performance using the F1 Score in average is 92.28%. The performance would improve with modifications to the system, including a more homogenous illumination, only allowing certain positions to be possible for the bananas cluster, and a more adequate background selection.

Este estudo comparou a percepção da diferença de cor entre profissionais da Odontologia e a influência de cada coordenada na percepção da diferença de cor. O critério de exclusão dos participantes foi a deficiência na visão cromática que foi avaliada através da versão simplificada do teste de Ishihara. Dois homens identificaram incorretamente 1 ou mais pranchas e foram excluídos do estudo. Participaram desta pesquisa 51 pessoas: 20 alunos do último ano de graduação, 20 clínicos gerais e 11 professores. Todas avaliações foram realizadas sob iluminante D65 e em cabine de luz. Neste experimento foram utilizados 1 cartão padrão e 3 conjuntos de cartões. Cada conjunto de cartões foi composto por 1 cartão que apresenta os mesmos valores de L*, a* e b* que o cartão padrão e 6 cartões que apresentavam variações em apenas uma das coordenadas. Solicitamos aos participantes que selecionassem: 1 cartão que não apresentasse diferença de cor em relação ao cartão padrão, 1 cartão cuja diferença de cor em relação ao cartão padrão seria aceitável e 1 cartão cuja diferença de cor seria inaceitável. A análise dos resultados sugere que não houve diferença na percepção da diferença de cor entre homens e mulheres e entre alunos de graduação, clínicos gerais e professores em qualquer dos grupos. / This study investigated the perception of color difference among distinct group of dental personnel and the influence of each color coordinate on the perception of color difference. The color vision deficiency was the only exclusion criteria used. Screening for color defective vision was conducted using the simplified version of Ishihara test. Two men who missed 1 or more plates did not take part in this study. Fifty one subjects took part in this experiment: 20 final year dental students, 20 dental practitioners and 11 teachers. All visual assessments were conducted with D65 illumination of visual observation booth. Test was composed of 1 standard card and 3 sets of cards. Each set consisted of 1 card that did not differ from standard card and 6 cards that differed from the standard card in only one coordinate L*, a* or b*. The subjects were asked to select: 1 card that matched to the standard card; 1 card that color difference from the standard card would be acceptable; and 1 card that color difference from the standard card would be unacceptable. The analysis of percentis suggests that within the limitations of this study: there were no significant difference in color difference perception between men and women or between dental students, dental practitioners and teachers.