Search

Convolutional neural networks (CNNs) have recently made impressive results for image super-resolution (SR). Our goal is to introduce a new image SR framework rely on a CNN. In this paper, the input image is decomposed into luminance channel and chromatic channels. A designed network based on a residual dense network is introduced to extract the hierarchical features from luminance part. The bicubic interpolation is simply used to upscale low resolution (LR) chromatic channels. However, this step degrades the chromatic channels. To tackle this issue, the SR reconstructed luminance channel is applied as the reference image in guided filters to promote the interpolated chromatic channels. Guided filters technique has ability to retain sharp edges and fine details from the reference image and carry them to the target images. Extensive experiments on several commonly used image SR testing datasets demonstrate that our framework has the ability to extract features and outperforms existing well-known techniques for image SR by LR image into the high resolution (HR) image efficiently. [ABSTRACT FROM AUTHOR]

We propose a method of reversible data hiding in encrypted image. Proposed method achieves reserving room before encryption, and separates data extraction from image decryption. Our method is an improvement of Ma's method [IEEE Trans Inf Forensic Secur 8(3):554-558, 2013]. Our improvements mainly focus on two aspects. (1) We improved the interpolation error estimate method via using Bicubic interpolation instead of pixel estimation that calculates the weighted sum of four surrounding pixels. Thus more sharp interpolation error histogram is obtained to increase the hidden information capacity. (2) We use partitioned local histogram shift instead of traditional histogram shift to reduce the amount of shifted pixels. This directly results in a higher quality of stego image in the same embedding capacity. The experimental results indicate that the improved method offers better performance. It is superior to Ma's work in both embedding rate and the PSNR values of stego images. [ABSTRACT FROM AUTHOR]

This paper proposes an effective method for visual saliency detection based on multi-scale and multi-channel mean. 2-D wavelet transform is used to decompose and reconstruct image. Bicubic interpolation algorithm is applied to narrow the filtered image in multi-scale. We take the distances between the narrowed images and the means of their channels as saliency values, and we only reserve part values which are not less than the mean saliency of the given image. Bicubic interpolation algorithm is applied again to amplify the images in multi-scale, and then the saliency map is calculated by adding the amplified images. Finally, linear normalization is employed to obtain the final saliency map. Experimental results show that the proposed method outperforms 9 state-of-the-art methods both on the definition and accuracy of salient detection. [ABSTRACT FROM AUTHOR]