No abstract

Abstract:In order to lower the dependence on textual annotations for image searches, the content based image retrieval (CBIR) has become a popular topic in computer vision. A wide range of CBIR applications consider classification techniques, such as artificial neural networks (ANN), support vector machines (SVM), etc. to understand the query image content to retrieve relevant output. However, in multi-class search environments, the retrieval results are far from optimal due to overlapping semantics amongst subjects of various classes. The classification through multiple classifiers generate better results, but as the number of negative examples increases due to highly correlated semantic classes, classification bias occurs towards the negative class, hence, the combination of the classifiers become even more unstable particularly in one-against-all classification scenarios. In order to resolve this issue, a genetic algorithm (GA) based classifier comity learning (GCCL) method is presented in this paper to generate stable classifiers by combining ANN with SVMs through asymmetric and symmetric bagging. The proposed approach resolves the classification disagreement amongst different classifiers and also resolves the class imbalance problem in CBIR. Once the stable classifiers are generated, the query image is presented to the trained model to understand the underlying semantic content of the query image for association with the precise semantic class. Afterwards, the feature similarity is computed within the obtained class to generate the semantic response of the system. The experiments reveal that the proposed method outperforms various state-of-the-art methods and significantly improves the image retrieval performance.

No abstract

Image watermarking is a robust solution for solving key issues like copyright protection and proof of ownership of digital data. Existing schemes of image watermarking mostly used grayscale or binary images as embedded watermarks, while only a few watermarking schemes are developed for color images. In this paper, we propose a novel robust semi-blind image watermarking scheme based on finite ridgelet transform (FRT), discrete wavelet transform (DWT), singular value decomposition (SVD), particle swarm optimization (PSO), and Arnold transform to protect copyright and verify the authenticity of color images. Firstly, the color image is converted from RGB to YCbCr color space, and the luminance component (Y) is taken into account to insert the watermark data. In this study, the principal component (PC) of the watermark image is directly inserted into the corresponding singular value of the cover image by the scaling factor to avoid the false positive problem (FPP). To further improve security, Arnold transform is applied to process the Y channel of the watermark image before inserting it in the cover image. Besides, PSO optimizes the embedding factor matrices. The qualitative evaluation factors like peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) are used to assess the visual quality, while normalized correlation coefficient (NCC) is used to assess the resemblance between the watermarked and the restored watermarked images. The performance of the proposed scheme is evaluated using geometric, non-geometric, and combinational attacks, and its comparison is performed with different image watermarking schemes to prove its robustness.

The aim of this study is to describe the characteristics and outcome of thyroid storm patients presenting at two tertiary care centres of Karachi, i.e.