The prediction of salient areas in images has been traditionally addressed with hand-crafted features based on neuroscience principles. This paper, however, addresses the problem with a completely data-driven approach by training a convolutional neural network (convnet). The learning process is formulated as a minimization of a loss function that measures the Euclidean distance of the predicted saliency map with the provided ground truth. The recent publication of large datasets of saliency prediction has provided enough data to train end-to-end architectures that are both fast and accurate. Two designs are proposed: a shallow convnet trained from scratch, and a another deeper solution whose first three layers are adapted from another network trained for classification. To the authors knowledge, these are the first end-to-end CNNs trained and tested for the purpose of saliency prediction.

No abstract

Leishmaniasis is considered a neglected disease that causes thousands of deaths annually in some tropical and subtropical countries. There are various techniques to diagnose leishmaniasis of which manual microscopy is considered to be the gold standard. There is a need for the development of automatic techniques that are able to detect parasites in a robust and unsupervised manner. In this paper we present a procedure for automatizing the detection process based on a deep learning approach. We train a U-net model that successfully segments leismania parasites and classifies them into promastigotes, amastigotes and adhered parasites.

The signal flow graph for the fast recursive implementation method of OC with the GSE of size two is presented in Fig. 4. The comparison of Fig. 3 with Fig. 4 shows that the fast recursive structure in Fig. 4 requires significantly fewer computations for an V. CONCLUSION Efficient real-time implementation methods for the FP nnorphological operators were presented by extending our previous work 151, [6].It was shown that the proposed recursive algorithms can improve the computational efficiency of the basis matrix implementation method by avoiding the redundant steps in computing overlapping min/max operations. It was also shown that, with the proposed recursive algorithms, both opening and closing can be determined in real time by 2N -2 additions and 2N -2 comparisons, and bolh OC and CO by 4 N -4 additions and 41V -4 comparisons when the size of the GSE is equal to N . Moreover Motion Estimation Using Higher Order StatisticsElisa Sayrol, Antoni Gasull, and Javier R. Fonollosa Abstract-The objective of this paper is to introduce a fourth-order cost function of the displaced frame difference (DFD) capable of estimating motion even for small regions or blocks. Using higher than second-order statistics is appropriate in case the image sequence is severely corrupted by additive Gaussian noise. Some results are presented and compared to those obtained from the mean kurtosis and the mean square error of the DFD.

This work concentrutes on the problem of wutermurking embedding und optimum detection in color imuges through the use of spread spectrum techniques, both in spuce (Direct Sequence Spread Spectrum or DSSS) and fiequency (Frequency Hopping). It is applied to RGB und opponent color component representutions. Perceptive information is considered in both color systems. Some tests are performed in order to ensure imperceptibility und to ussess detection quality of the optimum color detectors