Robust image hashing with multidimensional scaling

In this paper, a novel perceptual image hashing scheme based on convolutional neural network (CNN) with multiple constraints is proposed, in which our deep hashing network learns the process of features extraction automatically according to the training target and then generates the final hash sequence. The combination of convolutional and pooling layers is to reduce the size of input image while deepening the channels. Then, we construct two pairs of constraints and integrate them into an overall constraint function through a strategy of weight allocation. In order to guarantee the robustness and discrimination of deep hashing network simultaneously, a new training method is developed to adjust the training set structure dynamically according to the changes of constraint values. Experimental results show that the proposed deep hashing network can achieve a satisfactory balance between perceptual robustnzess and discrimination while maintaining security. Based on the large-scale test set, receiver operating characteristic (ROC) curves, ${F}_{1}$ scores and equal error rate (EER) demonstrate the superiority of our scheme in terms of content authentication compared with some state-of-the-art schemes.

Perceptual Image Hashing for Content Authentication Based on Convolutional Neural Network With Multiple Constraints

Robustness and discriminability are the two most important features of perceptual image hashing (PIH) schemes. In order to achieve a good balance between perceptual robustness and discriminability, a novel PIH algorithm is proposed by combining latent low-rank representation (LLRR) and rotation invariant uniform local binary patterns (RiuLBP). LLRR is first applied on resized original images to the principal feature matrix and to the salient feature matrix, since it can automatically extract salient features from corrupted images. Following this, Riulocal bin features are extracted from each non-overlapping block of the principal feature matrix and of the salient feature matrix, respectively. All features are concatenated and scrambled to generate final binary hash code. Experimental results show that the proposed hashing algorithm is robust against many types of distortions and attacks, such as noise addition, low-pass filtering, rotation, scaling, and JPEG compression. It outperforms other local binary patterns (LBP) based image hashing schemes in terms of perceptual robustness and discriminability.

Perceptual Image Hashing Using Latent Low-Rank Representation and Uniform LBP

A wide range of medical devices have significant electronic components. Compared to open-source medical software, open (and open-source) electronic hardware has been less published in peer-reviewed literature. In this review, we explore the developments, significance, and advantages of using open platform electronic hardware for medical devices. Open hardware electronics platforms offer not just shorter development times, reduced costs, and customization; they also offer a key potential advantage which current commercial medical devices lack—seamless data sharing for machine learning and artificial intelligence. We explore how various electronic platforms such as microcontrollers, single board computers, field programmable gate arrays, development boards, and integrated circuits have been used by researchers to design medical devices. Researchers interested in designing low cost, customizable, and innovative medical devices can find references to various easily available electronic components as well as design methodologies to integrate those components for a successful design.

/pdf/open-electronics-for-medical-devices-state-of-art-and-unique-4qec6ve2pl.pdf

Open electronics for medical devices: State-of-art and unique advantages

A digitally altered photograph, often leaving no visual clues of having been tampered with, can be indistinguishable from an authentic photograph. As a result, photographs no longer hold the unique stature as a definitive recording of events. We describe several statistical techniques for detecting traces of digital tampering in the absence of any digital watermark or signature. In particular, we quantify statistical correlations that result from specific forms of digital tampering, and devise detection schemes to reveal these correlations.

Statistical tools for digital forensics

in today's world, face recognition is an important part for the purpose of security and surveillance. Hence there is a need for an efficient and cost effective system. Our goal is to explore the feasibility of implementing Raspberry Pi based face recognition system using conventional face detection and recognition techniques such as Haar detection and PCA. This paper aims at taking face recognition to a level in which the system can replace the use of passwords and RF I-Cards for access to high security systems and buildings. With the use of the Raspberry Pi kit, we aim at making the system cost effective and easy to use, with high performance.

Face detection and recognition using Raspberry Pi

This paper presents a novel image hashing method for authentication and tampering detection. Creation, modification and transfer of multimedia data becomes an easy task due to digitization. Integrity is very important for crucial and sensitive matters like medical records, legal matters, scientific research, forensic investigations and government documents. Image hashing is one of the popular method to maintain integrity of image. We proposed AQ-CSLBP (Average Compressed Center Symmetric Local Binary Pattern) as a feature descriptor for image hashing. First, image is divided into sub blocks, AQ-CSLBP is applied on each sub block to generate 8 bin histogram as a feature. Then, we used double bit quantization to generate hash code for the image. The proposed method is compared with the existing methods by way of quantitative analysis, it has been proved that the proposed method works well in authentication scenario with less hash length and more discrimination power.

Image hashing using AQ-CSLBP with double bit quantization

Center Symmetric Local Binary Pattern (CSLBP) is widely used in texture and object detection, but its utilization in image hashing is still limited. Image hashing is a powerful technique to identify whether image content is changed or preserved. Two main issues in image hashing are its compact length and its robust discrimination power. To deal with these issues, a robust image hashing method is proposed by combining features of CSLBP and Discrete Wavelet Transform(DWT). CSLBP is applied on LL band of DWT for compact length hash. Discrimination power of hashing is enhanced by weigh factor which comprises information from all sub bands of 1-Level DWT. All sub-band images of 1-Level DWT is combined to form secondary image. Local statistical features like Standard Deviation and Magnitude Average are calculated to obtain local weight factor MASD (Magnitude Average and Standard Deviation). Weighted LL-CSLBP histogram is constructed using this weight factor. Experimental results are demonstrated with Receiver Operating Characteristics (ROC) and Normalized Hamming Distance (NHD). The results shows that, the proposed scheme is robust against content preserving operations and sensitive to malicious operations.

/pdf/image-hashing-using-dwt-cslbp-24jgnkssgi.pdf

Image Hashing Using DWT-CSLBP

Approach for image hashing is to use powerful feature descriptor which captures essence of an image. Applications of image hashing lies in the area of content authentication, structural tampering detection, retrieval and recognition. Hashing is a compact summarized information of an image. Center Symmetric Local Binary Pattern (CSLBP) is one of the powerful texture feature descriptor which captures the smallest amount of change. Using CSLBP, appressed hash code can be obtained for an image. If CSLBP feature is weighted by a boost factor, it will enhance success rate of an image hashing. The proposed method of SDQ-CSLBP extract texture feature using CSLBP with standard deviation as weight factor. Standard deviation which represents local contrast is also a powerful descriptor. Resultant histogram of CSLBP is of 16 bin for each block of an image. Further it can be compressed to 8 bin by using the flipped difference concept. Without a weight factor, compressed CSLBP has low discrimination power. Experimental results show that the proposed method is robust against content preserving manipulation and sensitive to content changing and structural tampering.

Image hashing by SDQ-CSLBP

Recent trends and also statistics show that the hashing concept has been gaining importance because its application lies in the area of authentication, retrieval and recognition. The proposed hashing method CCQ-CSLBP (Compressed CSLBP with Correlation Coefficient) for authentication utilized correlation coefficient as a weight factor in CSLBP. CSLBP is a texture operator, whose performance is better than LBP, in terms of rotation invariance, differentiation power and less number of histogram bin. In CSLBP, histogram of each sub block is represented by 16 bin. Reduction in number of histogram bin is achieved by the flipped difference concept. Proposed method takes the advantage of correlation coefficient as a boosting factor during histogram construction, to increase the discrimination power of compressed CSLBP. With the use of correlation coefficient, results of CSLBP improved, in terms TPR and FPR. CCQ-CSLBP is evaluated, based on normalized hamming distance and ROC characteristics.

Varsha Patil

Papers

Face detection and recognition using Raspberry Pi

Image hashing using AQ-CSLBP with double bit quantization

Image Hashing Using DWT-CSLBP

Image hashing by SDQ-CSLBP

Image hashing by CCQ-CSLBP