We consider image intrinsic structure in two aspects: foreground saliency computation and background saliency calculation. On the one hand, a segmented image is represented as a weighted undirected graph, and we calculate the foreground saliency by choosing some superpixels as ranking queries, where we apply a robust background measure to select those for accuracy. On the other hand, we compute the posterior probabilities to measure the background saliency and in terms of the probability, we construct a probability tree via multimerging on superpixels, and then apply the optimization strategy to the background saliency. We evaluate our proposed algorithm on two benchmark datasets and our algorithm yields the competitive results when compared with nine state-of-the-art algorithms in terms of five evaluation metrics.
The extraction of effective features is extremely important for understanding the intrinsic structure hidden in high-dimensional data. In recent years, sparse representation models have been widely used in feature extraction. A supervised learning method, called sparsity preserving discriminative learning (SPDL), is proposed. SPDL, which attempts to preserve the sparse representation structure of the data and simultaneously maximize the between-class separability, can be regarded as a combiner of manifold learning and sparse representation. More specifically, SPDL first creates a concatenated dictionary by class-wise principal component analysis decompositions and learns the sparse representation structure of each sample under the constructed dictionary using the least squares method. Second, a local between-class separability function is defined to characterize the scatter of the samples in the different submanifolds. Then, SPDL integrates the learned sparse representation information with the local between-class relationship to construct a discriminant function. Finally, the proposed method is transformed into a generalized eigenvalue problem. Extensive experimental results on several popular face databases demonstrate the effectiveness of the proposed approach.
Segmentation of medical image is an indispensable process in image analysis and recognition, and it provides the basis
of quantitative analysis of images about human organs and functions. The Mumford-Shah model using level set method
is more robust than other curve evolution models to detect discontinuities under noisy environment, which has been
widely used in the field of medical image segmentation. Consequently, serial computed tomography (CT) image
segmentation algorithm based on an improved Mumford-Shah model is presented. First of all, the window
transformation technique of medical images is introduced, which is able to display the digital imaging and
communications in medicine (DICOM) images directly and distinctly with a little information loss. Secondly, the
characteristics of serial CT images as well as the topological structure relation between them are analyzed, followed by
the processing method of CT image sequence, which can make the serial CT image segmentation much more
automatically and swiftly. Thirdly, in the light of the problems of segmentation speed and termination in traditional
Mumford-Shah model, a novel segmentation algorithm based on image entropy and simulated annealing is presented.
The algorithm alleviates these two problems by using the image entropy to displace the energy coefficients in the
original energy function, and also combining the simulated annealing to terminate the contours evolution automatically.
Finally, the algorithm is applied in some experiments to deal with serial CT images, and the results of the experiments
show that the proposed algorithm can provide a fast and reliable segmentation.