Algoritmos de casamento de imagens com filtragem adaptativa de outliers

Abstract

Image matching plays a major role in many applications, such as pattern recognition and microscopic imaging. It encompasses three steps: 1) interest point selection; 2) feature extraction from each point; 3) feature point matching. For steps 1 and 2, traditional interest point detectors/extractors have worked well. However, for step 3 even a few points incorrectly matched (outliers), might lead to an undesirable result. State-of-the-art consensus algorithms present a high time cost as the number of outlier increases. Aiming at overcoming this problem, we present FOMP, a preprocessing approach, that reduces the number of outliers in the initial set of matched points. FOMP filters out the vertices that present a higher difference among their edges in a complete graph representation of the points. To validate the proposed method, experiments were performed with four image database: (a) variations of rotation or camera zoom; (b) repetitive patterns, which leads to duplicity of features vectors; (c) deformable objects, such as plastics, clothes or papers; (d) affine transformations (different viewpoint). The experimental results showed that FOMP removes more than 65% of the outliers, while keeping over 98% of the inliers. Moreover, the precision of traditional methods is kept, while reducing the processing time of graph based approaches by half. K ey-wor ds: Image matching, Feature point matching; Outlier removal, Outlier filtering.

Métodos de mosaico em imagens microscópicas

“…O primeiro método de consenso desenvolvido chama-se RANSAC (do inglês, Randon Sample Consensus) proposto por (FISCHLER;BOLLES, 1981). O trabalho de Ramos (2016) apresenta alguns dos algoritmos de consenso propostos na literatura.…”

“…Em seguida, uma janela quadrada é construída de acordo com a orientação. Assim, o extrator de características do SURF pode ser aplicado sobre esta janela quadrada (RAMOS, 2016).…”

“…A orientação dominante é presumida pelo cálculo da soma de todas as respostas dentro de uma janela de ângulo π 3 , que é movida incrementalmente até cobrir todos os ângulos. Logo, a soma das duas respostas gera um novo vetor, e este é somado dentro do intervalo da janela que apresentar maior valor, sendo escolhido como orientação dominante (RAMOS, 2016).…”