Learn More
Image classification is an important task in computer vision. In this paper, we propose a new image representation based on local feature vectors approximation by the wavelet networks. To extract an approximation of the feature vectors space, a Wavelet Network algorithm based on fast Wavelet is suggested. Then, the K-nearest neighbor (K-NN) classification(More)
Automatic photo annotation task aims to describe the semantic content by detecting high level concepts in order to further facilitate concept based video retrieval. Most of existing approaches are based on independent semantic concept detectors without considering the contextual correlation between concepts. This drawback has its impact over the efficiency(More)
The semantic gap is a crucial issue in the enhancement of computer vision. The user longs for retrieving images on a semantic level, but the image characterizations can only give a low-level similarity. As a result, recording a stage medium between high-level semantic concepts and low-level visual features is a stimulating task. A recent work, called Bag of(More)
The increasing demand for microalgae lipids as an alternative to fish has encouraged researchers to explore oleaginous microalgae for food uses. In this context, optimization of growth and lipid production by the marine oleaginous V2-strain-microalgae is of great interest as it contains large amounts of mono-unsaturated (MUFAs) and poly-unsaturated fatty(More)
An amylase and lipase producing bacterium (strain C2) was enriched and isolated from soil regularly contaminated with olive washing wastewater in Sfax, Tunisia. Cell was aerobic, mesophilic, Gram-negative, motile, non-sporulating bacterium, capable of growing optimally at pH 7 and 30°C and tolerated maximally 10% (W/V) NaCl. The predominant fatty acids were(More)
To generate the visual codebook, a step of quantization process is obligatory. Several works have proved the efficiency of sparse coding in feature quantization process of BoW based image representation. Furthermore, it is an important method which encodes the original signal in a sparse signal space. Yet, this method neglects the relationships among(More)
BACKGROUND This study aimed to maximize biomass concentration, biomass productivity and biochemical composition of the marine microalga Tetraselmis sp. METHODS In the current study, Box-Behnken Design was used to model the effect of NaNO3, NaH2PO4, metals and vitamins in the F/2 medium on the growth, total chlorophylls, carotenoids and starch contents.(More)