Oblique Support Vector Machines

Abstract

In this paper we propose a modified framework of support vector machines, called Oblique Support Vector Machines(OSVMs), to improve the capability of classification. The principle of OSVMs is joining an orthogonal vector into weight vector in order to rotate the support hyperplanes. By this way, not only the regularized risk function is revised, but the constrained functions are also modified. Under this modification, the separating hyperplane and the margin of separation are constructed more precise. Moreover, in order to apply to large-scale data problem, an iterative learning algorithm is proposed. In this iterative learning algorithm, three different schemes for training can be found in this literature, including pattern-mode learning, semi-batch mode learning and batch mode learning. Besides, smooth technique is adopted in order to convert the constrained nonlinear programming problem into unconstrained optimum problem. Consequently, experimental results and comparisons are given to demonstrate that the performance of OSVMs is better than that of SVMs and SSVMs.

Visual security index of selective encrypted images based on multi-directional structure and content-aware features

“…Mao and Wu presented the ESS and LSS 16 methods for computing the edge and LSS between plaintext and ciphertext images. Yao et al 17 introduced the neighborhood similarity degree (NSD) index, which calculates the dissimilarity between the center pixel and its surrounding pixels in each window of plaintext and ciphertext images. Tong et al 18 proposed a local feature-based visual security (LFBVS) index using color and local edge information and assigning weights to these features.…”

“…Numerous researchers have currently put forth visual security indices (VSI), 16 – 24 specifically tailored for selectively encrypted images, to assess the extent of information leakage in an image by quantifying the similarity of features between the plaintext and ciphertext images. The extent of visual information leakage in selectively encrypted images is inversely proportional to the degree of feature similarity between the plaintext and ciphertext images.…”