Erchan Aptoula

Learn More
The successful application of univariate morphological operators on several domains, along with the increasing need for processing the plethora of available multivalued images, have been the main motives behind the efforts concentrated on extending the mathematical morphology framework to multivariate data. The few theoretical requirements of this(More)
Since mathematical morphology is based on complete lattice theory, a vector ordering method becomes indispensable for its extension to multivariate images. Among the several approaches developed with this purpose, lexicographical orderings are by far the most frequent, as they possess certain desirable theoretical properties. However, their main drawback(More)
The extension of mathematical morphology to colour, and more generally to multivariate image data, continues to be an open problem. As its underlying theory is defined in terms of complete lattices, the main challenge lies in introducing a complete lattice structure on the image intensity range, hence vectorial extrema computation methods are necessary. In(More)
Although polar colour spaces are being increasingly used in the context of colour mathematical morphology, mainly due to their intuitiveness, the processing of the circular hue band continues to be their main drawback. In this paper, we discuss the two principal problems concerning the morphological processing of hue, first its lack of a lattice structure,(More)
Placed within the context of content-based image retrieval, we study in this paper the potential of morphological operators as far as color description is concerned, a booming field to which the morphological framework, however, has only recently started to be applied. More precisely, we present three morphology-based approaches, one making use of(More)
Open-set recognition, a challenging problem in computer vision, is concerned with identification or verification tasks where queries may belong to unknown classes. This work describes a fine-grained plant identification system consisting of an ensemble of deep convolutional neural networks within an open-set identification framework. Two wellknown deep(More)
We use deep convolutional neural networks to identify the plant species captured in a photograph and evaluate different factors affecting the performance of these networks. Three powerful and popular deep learning architectures, namely GoogLeNet, AlexNet, and VGGNet, are used for this purpose. Transfer learning is used to fine-tune the pre-trained models,(More)
We describe our system in 2014 LifeCLEF [1] Plant Identification Competition. The sub-system for isolated leaf category (LeafScans) was basically the same as last year [2], while plant photographs in all the remaining categories were classified using either local descriptors or deep learning techniques. However, due to large amount of data, large number of(More)