Shape description based on bag of salience points

Abstract

Salient points are very important for image description because they are related to the visually most important parts of the image, leading to a compact and more discriminative representation close to human perception. Based on these promising features, in this paper we propose a new shape descriptor, namely Bag-ofSalience-Points (BoSP), using the shape salience points combined with the Bag-of-Visual-Words modeling approach. Each salience point, after extracted from the shape contour, is represented by its curvature value using a multi-scale procedure proposed in this work. Taking advantage of this representation, each salience is assigned to a visual word according to a Dictionary of Curvatures. The final shape representation is given by computing a histogram of visual words detected in the shape, combined with a spatial pooling approach that encodes the distance distribution of the visual words in relation the shape centroid. This proposed new shape description allows to analyze the dissimilarity between shapes using fast distance functions, such as the City-block distance, even if two shapes have different number of salience points. This is a powerful asset to reduce the computational complexity when retrieving images. Compared to other shape descriptors, the BoSP descriptor has the advantage of proving a powerful shape description with high recognition accuracy, a compact representation invariant to geometric transformations while demanding a low computational cost to measure the dissimilarity of shapes.

Caracterização e recuperação de imagens usando dicionários visuais semanticamente enriquecidos

“…Os melhores resultados foram obtidos usando os detectores Harris e Dense. Esseúltimo, por sua vez, obteve os melhores resultados em três bases (1,3,4). O detector DoG por sua vez, queé a técnica utilizada pelo descritor SIFT, gerou resultados semelhantes ao detector baseado em pontos-aleatórios (Random).…”

“…5.5a. Para os pontos de saliências côncavas (1,4,5,8) a curvaturaé positiva, enquanto os pontos de saliências convexas (2,3,6,7) tem curvaturas negativas. Quando o valor de t aumenta, obtém-se uma representação mais global da forma.…”