Blind watermarking targets the challenging recovery of the watermark when the host is not available during the detection stage. This paper proposes Discrete Shearlet Transform (DST) as a new embedding domain for blind image watermarking. Our novel DST blind watermark detection system uses a nonadditive scheme based on the statistical decision theory. It first computes the Probability Density Function (PDF) of the DST coefficients modeled as a Laplacian distribution. The resulting likelihood ratio is compared with a decision threshold calculated using Neyman–Pearson criterion to minimize the missed detection subject to a fixed false alarm probability. Our method is evaluated in terms of imperceptibility, robustness, and payload against different attacks (Gaussian noise, blurring, cropping, compression, and rotation) using 30 standard grayscale images covering different characteristics (smooth, more complex with a lot of edges, and high detail textured regions). The proposed method shows greater windowing flexibility with more sensitive to directional and anisotropic features when compared against discrete wavelet and contourlets.

/pdf/blind-image-watermark-detection-algorithm-based-on-discrete-h0k29mwacz.pdf

Blind Image Watermark Detection Algorithm Based on Discrete Shearlet Transform Using Statistical Decision Theory

Human action recognition is an active research area in computer vision. Although great progress has been made, previous methods mostly recognize actions from depth video sequences at only one scale, and thus they often neglect multi-scale spatial changes that provide additional information in practical applications. In this paper, we present a novel framework with a multi-scale mechanism to improve scale diversity of motion features. We propose a multi-scale feature map called Laplacian pyramid depth motion images(LP-DMI). First, We employ depth motion images (DMI) as the templates to generate the multi-scale static representation of actions. Then, we caculate LP-DMI to enhance multi-scale dynamic information of motions and reduce redundant static information in human bodies. We further extract the multi-granularity descriptor called LP-DMI-HOG to provide more discriminative features. Finally, we utilize extreme learning machine (ELM) for action classification. The proposed method yeilds the recognition accuracy of 93.41%, 85.12%, 91.94% on the public MSRAction3D, UTD-MHAD and DHA dataset. Through extensive experiments, we prove that our method outperforms the state-of-the-art benchmarks.

Human action recognition based on multi-scale feature maps from depth video sequences

Pore is widely used because of its strong security and usefulness for live fingerprint detection and recognition. There are considerable pores in a high-resolution fingerprint image that can be used for fingerprint recognition. However, the quality of fingerprint has become one of the bottlenecks in the method of pore detection and matching currently. In order to improve the accuracy and stability of the existing pore detection and matching methods, this paper proposes a fingerprint enhancement technique based on neural network. The residual structure is used to learn the local features of the fingerprint to reconstruct the original image. Experimental results indicate the approach can improve the precision of the existing pore extraction and matching methods significantly.

CNN-based High-Resolution Fingerprint Image Enhancement for Pore Detection and Matching

Image enhancement is a very important process used for enhancing the quality of an image, and for this purpose, numerous techniques have been used and applied. This paper describes how to enhance an image using different techniques. Various techniques have been studied for image enhancement used in different research papers. Understanding and reviewing the techniques used for image enhancement are the main goal of this paper. Our review work leaves a lot of future scopes which can be extended further by researchers.

A Systematic Review on Image Enhancement Techniques

In the development of computer aided diagnosis (CAD), there are many instruments for pulse signal acquisition. Traditional contact pulse wave collector is inconvenient and depends on complex electronic equipment. Based on Euler video magnification algorithm (EVM), a non-contact pulse wave lifting method based on video action amplification is proposed. The method uses only one digital camera to photograph the pulse in the neck position for pulse wave acquisition. Compared with the method the acquisition rate is higher in other non-contact ways.

Cervical Pulse Wave Extraction Based On Video Motion Amplification

Image enhancement is a low-level image processing and have many methods of image enhancement processing. Which based on Laplacian pyramid of the image processing algorithm for image enhancement is an essential field of image processing and crucial technologies. The Laplacian pyramid is ubiquitous for decomposing images into multiple scales and is widely used for image analysis. In this paper, we describes the basic tenets of the Laplacian pyramid decomposition, and analysis using user-defined threshold values to distinguish between the image detail and edges of the disadvantages, and propose to use the global information directly to obtain the threshold value method. In the basis of the obtained good results, the limit remapping layers that not only able to reduce time and cost, and can reduce the cost of unnecessary calculations. As we demonstrate, our method produces consistently high-quality results in the process of image detail enhancement.

Fuyan Liu

Papers

The Research of Image Detail Enhancement Algorithm with Laplacian Pyramid