Search

Several salient object detection approaches have been published which have been assessed using different evaluation scores and datasets resulting in discrepancy in model comparison. This calls for a methodological framework to compare existing models and evaluate their pros and cons. We analyze benchmark datasets and scoring techniques and, for the first time, provide a quantitative comparison of 35 state-of-the-art saliency detection models. We find that some models perform consistently better than the others. Saliency models that intend to predict eye fixations perform lower on segmentation datasets compared to salient object detection algorithms. Further, we propose combined models which show that integration of the few best models outperforms all models over other datasets. By analyzing the consistency among the best models and among humans for each scene, we identify the scenes where models or humans fail to detect the most salient object. We highlight the current issues and propose future research directions.

A new method for query expansion using genetic programming (GP) is proposed in this paper to enhance the retrieval performance of text information retrieval systems. Using a set of queries and retrieved relevant and nonrelevant documents corresponding to each query, GP tries to evolve a criteria for selecting terms which when added to the original query improve the next retrieved set of documents. Two experiments are conducted to evaluate the proposed method over three standard datasets: Cranfield, Lisa and Medline. In first experiment a formula is evolved using GP over a training set and is then evaluated over a test query set of the same dataset. In the second experiment, evolved expansion formula over a dataset is evaluated over a different dataset. We compared our method against the base probabilistic method in literature. Results show a higher performance in comparison with original and probabilistically expanded method.

Faces are complex and important visual stimuli for humans and are subject to many psychophysical and computational studies. A new parametric method for generating synthetic faces is proposed in this study. Two separate programs, one in Delphi 2005 programming environment and another in MATLAB is developed to sample real faces and generating synthetic faces respectively. The user can choose to utilize default configurations or to customize specific configurations to generate a set of synthetic faces. Head-shape and inner-hairline is sampled in a polar coordinate frame, located at the center of line connecting two eyes at 16 and 9 equ-angular positions. Three separate frames are placed at the left eyes center, nose tip and lips to sample them with 20, 30 and 44 angular points respectively. Eyebrows are sampled with 8 points in eye coordinate systems. Augmenting vectors representing these features and their distance from the origin generates a vector of size 95. For synthesized face, intermediate points are generated using spline curves and the whole image is then band pass filtered. Two experiments are designed to show that the set of generated synthetic faces match very well with their equivalent real faces.

Extensive use of computer networks and online electronic data and high demand for security has called for reliable intrusion detection systems. A repertoire of different classifiers has been proposed for this problem over last decade. In this paper we propose a combining classification approach for intrusion detection. Outputs of four base classifiers ANN, SVM, kNN and decision trees are fused using three combination strategies: majority voting, Bayesian averaging and a belief measure. Our results support the superiority of the proposed approach compared with single classifiers for the problem of intrusion detection.

A new numerical optimization algorithm inspired by political competitions during parliamentary head elections is proposed in this paper. Competitive behaviors could be observed in many aspects of human social life. Our proposed algorithm is a stochastic, iterative and population-based global optimization technique like genetic algorithms and particle swarm optimizations. Particularly, our method tries to simulate the intra and inter group competitions in trying to take the control of the parliament. Performance of this method for function optimization over some benchmark multidimensional functions, of which global and local minimums are known, is compared with traditional genetic algorithms.