Submitted by Automa??o e Estat?stica (sst@bczm.ufrn.br) on 2016-01-20T20:57:18Z No. of bitstreams: 1 AlessandraMendesPachecoGuerraVale_TESE.pdf: 6083940 bytes, checksum: 50490507cf0394240eea06786d58ff08 (MD5) / Approved for entry into archive by Arlan Eloi Leite Silva (eloihistoriador@yahoo.com.br) on 2016-01-21T19:07:52Z (GMT) No. of bitstreams: 1 AlessandraMendesPachecoGuerraVale_TESE.pdf: 6083940 bytes, checksum: 50490507cf0394240eea06786d58ff08 (MD5) / Made available in DSpace on 2016-01-21T19:07:52Z (GMT). No. of bitstreams: 1 AlessandraMendesPachecoGuerraVale_TESE.pdf: 6083940 bytes, checksum: 50490507cf0394240eea06786d58ff08 (MD5) Previous issue date: 2014-12-26 / A detec??o autom?tica de componentes sangu?neos em imagens microsc?picas ? um importante t?pico da ?rea hematol?gica. A segmenta??o permite que os componentes sangu?neos sejam agrupados em ?reas comuns e a classifica??o diferencial dos leuc?citos possibilita que os mesmos sejam analisados separadamente. Com a segmenta??o autom?tica e classifica??o diferencial, contribui-se no processo de an?lise dos componentes sangu?neos, fornecendo ferramentas que propiciem a diminui??o do trabalho manual e o aumento da sua precis?o e efici?ncia. Utilizando t?cnicas de processamento digital de imagens associadas a uma abordagem fuzzy gen?rica e autom?tica, este trabalho apresenta dois Sistemas de Infer?ncia Fuzzy, definidos como I e II, para a segmenta??o autom?tica de componentes sangu?neos e classifica??o diferencial de leuc?citos, respectivamente, em imagens microsc?picas de esfrega?os. Utilizando o Sistema de Infer?ncia Fuzzy I, a t?cnica desenvolvida realiza a segmenta??o da imagem em quatro regi?es: n?cleo e citoplasma leucocit?rios, eritr?citos e ?rea de plasma e utilizando o Sistema de Infer?ncia Fuzzy II e os leuc?citos segmentados (n?cleo e citoplasma leucocit?rios), os classifica diferencialmente em cinco tipos: bas?filos, eosin?filos, linf?citos, mon?citos e neutr?filos. Foram utilizadas para testes 530 imagens contendo amostras microsc?picas de esfrega?os sangu?neos corados com m?todos variados. As imagens foram processadas e seus ?ndices de Acur?cia e Gold Standards foram calculados e comparados com os resultados manuais e com outros resultados encontrados na literatura para os mesmos problemas. Quanto ? segmenta??o, a t?cnica desenvolvida demonstrou percentuais de acur?cia de 97,31% para leuc?citos, 95,39% para eritr?citos e 95,06% para plasma sangu?neo. Quanto ? classifica??o diferencial, os percentuais variaram entre 92,98% e 98,39% para os diferentes tipos leucocit?rios. Al?m de promover a segmenta??o autom?tica e classifica??o diferencial, a t?cnica desenvolvida contribui ainda com defini??o de novos descritores e a constru??o de um banco de imagens utilizando diversos processos de colora??o hematol?gicos / Automatic detection of blood components is an important topic in the field of hematology. The segmentation is an important stage because it allows components to be grouped into common areas and processed separately and leukocyte differential classification enables them to be analyzed separately. With the auto-segmentation and differential classification, this work is contributing to the analysis process of blood components by providing tools that reduce the manual labor and increasing its accuracy and efficiency. Using techniques of digital image processing associated with a generic and automatic fuzzy approach, this work proposes two Fuzzy Inference Systems, defined as I and II, for autosegmentation of blood components and leukocyte differential classification, respectively, in microscopic images smears. Using the Fuzzy Inference System I, the proposed technique performs the segmentation of the image in four regions: the leukocyte?s nucleus and cytoplasm, erythrocyte and plasma area and using the Fuzzy Inference System II and the segmented leukocyte (nucleus and cytoplasm) classify them differentially in five types: basophils, eosinophils, lymphocytes, monocytes and neutrophils. Were used for testing 530 images containing microscopic samples of blood smears with different methods. The images were processed and its accuracy indices and Gold Standards were calculated and compared with the manual results and other results found at literature for the same problems. Regarding segmentation, a technique developed showed percentages of accuracy of 97.31% for leukocytes, 95.39% to erythrocytes and 95.06% for blood plasma. As for the differential classification, the percentage varied between 92.98% and 98.39% for the different leukocyte types. In addition to promoting auto-segmentation and differential classification, the proposed technique also contributes to the definition of new descriptors and the construction of an image database using various processes hematological staining