Value Of Original Image Research Articles

Lightweight Image Encryption Based on A Hybrid Approach

A secure image could be achieved by encryption, a technique for securing images over different media transmission lines with privacy and keeping them safe for the receiver. This paper proposes an image encryption approach to achieve excellent security by combining a lightweight encryption algorithm with the chaotic Peter De Jong map. The Lilliput algorithm, lightweight encryption, uses the Peter De-Jones map to produce keys. The suggested approach achieved a suitable level of complexity that matched the historical demands for transmission images. Two methods were used to conduct the tests on a standard image collection: an encrypted image and a generated key. Standard metrics find the similarity between the input and output images to achieve an accurate proposal performance. The encrypted image's entropy was assessed and discovered that it matched the original image values exactly. The results were satisfactory regarding obtaining a precise correlation rate between the original and encrypted photos. The decryption and reconstruction of the image were completed quickly and steadily, with a high success rate and excellent outcomes. The proposed approach was evaluated on a dataset of well-known test photos with unique features, including varying degrees of lightness and shade to create the perfect test.

An efficient dual-layer cross-coupled chaotic map security-based multi-image encryption system

This paper proposes an effective image encryption method to encrypt several images in one encryption process. The proposed encryption scheme differs from the current multiple image encryption schemes because of their two-layer cross-coupled chaotic map-based permutation-diffusion operation. Block-shuffling, left–right (L–R) flipping and then bit-XOR diffusion operations are carried out in the first layer using one set of cross-coupled chaotic map. Block-shuffling, up–down (U–D) flipping and then bit-XOR diffusion operations are performed with another set of cross-coupled chaotic maps in the second layer. The two different layers of permutation-diffusion make the proposed algorithm more efficient than the existing multi-image encryption algorithms. Moreover, the combination of block-based shuffling and flip operation decreases the algorithm’s computational complexity, which means enhancing the time efficiency of the algorithm. In cross-coupling operation, the use of a single fixed-type one-dimensional chaotic map-piece-wise linear chaotic map (PWLCM) makes the algorithm efficient both in hardware and in software. PWLCM’s initial values and system parameters (keys) are generated by means of the hash values of original images that resist the algorithm against the attacks of chosen-plaintext and known-plaintext. Results of simulation and comparative security analysis reveal that the suggested scheme is more effective in encryption and resists better against all widely used attacks.

A Deep Learning Interpretable Model for Novel Coronavirus Disease (COVID-19) Screening with Chest CT Images

In this article, we propose a convolutional neural network (CNN)-based model, a ResNet-50 based model, for discriminating coronavirus disease 2019 (COVID-19) from Non-COVID-19 using chest CT. We adopted the use of wavelet coefficients of the entire image without cropping any parts of the image as input to the CNN model. One of the main contributions of this study is to implement an algorithm called gradient-weighted class activation mapping to produce a heat map for visually verifying where the CNN model is looking at the image, thereby, ensuring the model is performing correctly. In order to verify the effectiveness and usefulness of the proposed method, we compare the obtained results with that obtained by using pixel values of original images as input to the CNN model. The measures used for performance evaluation include accuracy, sensitivity, specificity, positive predictive value, negative predictive value, F1 score, and Matthews correlation coefficient (MCC). The overall classification accuracy, F1 score, and MCC for the proposed method (using wavelet coefficients as input) were 92.2%, 0.915%, and 0.839%, and those for the compared method (using pixel values of the original image as input) were 88.3%, 0.876%, and 0.766%, respectively. The experiment results demonstrate the superiority of the proposed method. Moreover, as a comprehensible classification model, the interpretability of classification results was introduced. The region of interest extracted by the proposed model was visualized using heat maps and the probability score was also shown. We believe that our proposed method could provide a promising computerized toolkit to help radiologists and serve as a second eye for them to classify COVID-19 in CT scan screening examination.

Noise Removal of MRI Images with Different Similarities using Advance NLM Filtering

In modern world, medical imaging has versatile application worldwide. It is very popular in the field of research and innovation. Medical image processing include the study of internal body structure like organs, tissues, etc., which provides much clear information of inner body structure using the digitalized data of human organs and help doctors to detect disease. Magnetic Resonance Imaging (MRI) is most effective and safe method for internal structure diagnosis. MRI images are generally magnitude images and they are follows by Rician distribution. In last few decades, many denoising techniques have been proposed like wavelet based techniques, Maximum likelihood (ML), bilateral filtering etc. But all those algorithms have some shortcomings and limitations. The purpose of our study is to propose a simple but effective advance Non-Local Means filtering approach for MRI denoising. Different distance matrix calculations have been introduced like Euclidean distance, Minkowski distance, Manhattan distance etc. These all are tested and identified best similarity measurement which preserves the image edges information and other information more effectively. The analysis is done on both the quality and quantity basis such as Peak Signal to Noise Ratio (PSNR) which shows the efficiency of noise removal technique and Mean Square Error (MSE) which represents the average of difference between pixels value of original image and denoised images.

Occlusion Images Generation from Occlusion-Free Images for Criminals Identification based on Artificial Intelligence Using Image

In this paper, we propose the method to generate occlusion images which include sunglass and scarf from occlusion-free images for criminals identification. First, we construct an auxiliary set that has occlusion-free face image and its occluded face images from AR database. Secondly, pixel weights are determined by the statistical analysis of the degree depending on whether occlusion-free or occlusion. As the weight is closer to 1, the pixel value of original image is maintained as much as possible. Therefore, pixel values of occlusion-free region are preserved when the weights are closed to 1. Third, pixel values of the occlusion region of original image are replaced to pixel values which are the mean of occlusion images by multiplying the composited weights. As a result of generate face images with various occlusions using the proposed method, the images were able to preserve the person-specific characteristic, and criminals identification has become easier.

A Verifiable Secret Image Sharing Scheme Based on Compressive Sensing

This paper proposes a verifiable secret image sharing scheme based on compressive sensing, secret sharing, and image hashing. In this scheme, Toeplitz matrix generated by two chaotic maps is employed as measurement matrix. With the help of Shamir threshold scheme and image hashing, the receivers can obtain the stored values and the hash value of image. In the verifying stage and restoring stage, there must be at least t legal receivers to get the effective information. By comparing the hash value of the restored image with the hash value of original image, the scheme can effectively prevent the attacker from tampering or forging the shared images. Experimental results show that the proposed scheme has good recovery performance, can effectively reduce space, and is suitable for real-time transmission, storage, and verification.

Artificial Neural Network for TIFF Image Compression

The main aim of image compression is to reduce the its size to be able for transforming and storage, therefore many methods appeared to compress the image, one of these methods is "Multilayer Perceptron ". Multilayer Perceptron (MLP) method which is artificial neural network based on the Back-Propagation algorithm for compressing the image. In case this algorithm depends upon the number of neurons in the hidden layer only the above mentioned will not be quite enough to reach the desired results, then we have to take into consideration the standards which the compression process depend on to get the best results. We have trained a group of TIFF images with the size of (256*256) in our research, compressed them by using MLP for each compression process the number of neurons in the hidden layer was changing and calculating the compression ratio, mean square error and peak signal-to-noise ratio to compare the results to get the value of original image. The findings of the research was the desired results as the compression ratio was less than five and a few mean square error thus a large value of peak signal-to-noise ratio had been recorded.

Klasifikasi Bit-Plane Noise untuk Penyisipan Pesan pada Teknik Steganography BPCS Menggunakan Fuzzy Inference Sistem Mamdani

Bit-Plane Complexity Segmentation (BPCS) is a fairly new steganography technique. The most important process in BPCS is the calculation of complexity value of a bit-plane. The bit-plane complexity is calculated by looking at the amount of bit changes contained in a bit-plane. If a bit-plane has a high complexity, the bi-plane is categorized as a noise bit-plane that does not contain valuable information on the image. Classification of the bit-plane using the set cripst set (noise/not) is not fair, where a little difference of the value will significantly change the status of the bit-plane. The purpose of this study is to apply the principles of fuzzy sets to classify the bit-plane into three sets that are informative, partly informative, and the noise region. Classification of the bit-plane into a fuzzy set is expected to classify the bit-plane in a more objective approach and ultimately message capacity of the images can be improved by using the Mamdani fuzzy inference to take decisions which bit-plane will be replaced with a message based on the classification of bit-plane and the size of the message that will be inserted. This research is able to increase the capability of BPCS steganography techniques to insert a message in bit-pane with more precise so that the container image quality would be better. It can be seen that the PSNR value of original image and stego-image is only slightly different.

Features Extraction and Classification of Rice Paper Images Based on Wavelet Transform

Based on wavelet transform for the classiflcation of image features, a new method for the classiflcation of image texture features is put forward. In our study, the images of rice paper have been acquired using a digital image system. The images of rice paper were decomposed respectively using Debaucheries and Gabor wavelet transforms. The subband of low frequency was selected to extract 11 kinds of classic characteristic value of Gray-level Co-occurrence Matrix (GLCM). Then the texture feature values were classifled by the Support Vector Machine (SVM). In order to evaluate the classiflcation accuracy, feature values of the original images and images processed by wavelet decomposition were sent into SVM individually. The classiflcation rate of rice paper texture images was only 84.1% using characteristic values of original images, but reached 93.0% by using Gabor wavelet. The overall results show that wavelet transform is a highly e‐cient method for paper classiflcation. In summary, the method of using wavelet decomposition for the recognition of rice image provides a new nondestructive and fast method for rice paper classiflcation.

Number Plate Extraction using Template Matching Technique

As an application of CCTV Traffic surveillance, retrieval of the number plate from the vehicles is an important dimension, which demands intelligent solution. In this document, template matching block of computer vision toolbox has been used to extract the vehicle number plate. It is assumed that images of the vehicle have been captured at a particular resolution and orientation. It is also assumed that alphanumeric characters on the plate have been written with a particular font style, type and size. This paper presents a new SIMULINK model in MATLAB which has been developed to extract the number plate from the vehicle. Each alphanumeric character on a plate is extracted and matched with template image with the help of template matching block. This block matches the pixel by pixel value of original image with one of the template images and gives the template metric value. To develop this SIMULINK model, Digital Signal Processing Toolbox and Computer Vision System Toolbox is used in MATLAB. The approach used for this model is template matching, which has been used for the recognition of letters and digits. This technique can be used for security purpose e.g. finding stolen cars, and for parking area management etc. General Terms Digital Signal Processing toolbox, Computer vision System toolbox, Simulink Blockset.

An Algorithm for Amplified Image Enhancement based on Image Interpolation

An magnified image enhancement algorithm is presented in this study. Image interpolation is an important image magnification tool, but the magnified image has not been changed by the traditional image interpolation methods even if the magnified image is not satisfaction. Basically, the interpolating surface is determined uniquely for the given interpolating data. Namely the interpolating surface (magnified image) is fixed when the interpolating data (gray value of original image) is given. If the magnified image needs to be enhanced, another enhancement method must be chosen after image magnifying. The image magnification and enhancement are separated. The image natural attribute will be effected. To overcome the disadvantages of the traditional methods, a new method which combined the image magnification and enhancement is proposed. A bivariate rational interpolation with parameters is used in the algorithm. The value of the interpolating function at any point in the interpolating region can be modified under the condition that the interpolating data are not changed by selecting the suitable parameters. Using the surface control, the enlarged image enhancement is implemented. The experiment shows that the algorithm is efficient.

A novel image encryption scheme based on a linear hyperbolic chaotic system of partial differential equations

Compared with general chaotic systems, a linear hyperbolic chaotic system of partial differential equations with nonlinear boundary conditions has larger parameter space, stronger sensitivity to initial condition and control parameter, better random-like behavior and so on, but it has not been employed in cryptography so far. Then using its significant properties, we present a new cryptosystem with coupled map lattices and time-varying delay. The proposed image encryption algorithm with permutation–diffusion architecture can overcome some drawbacks in the existing methods, because the sum of pixel value of original image is used for determining the permutation parameters and the previous cipher image information is utilized in the next diffusion. Theoretical analysis and computer experiments confirm that the new algorithm is efficient, practicable, and reliable, with high potential to be adopted for network security and secure communications.

Image Quality Assessment Based on Invariant Moments Similarity

To resolve the problems of the image quality assessment issue and the algorithm adaptability for different image size and deformation, this paper proposes a image quality assessment algorithm based on Invariant Moments Similarity. Firstly, Hu invariant moments values of original image and evaluated image are computed. Secondly the invariant moments distance is completed between original image and evaluated image. At last, the method assess the restoration image quality depend on the invariant moment distance. The experimental result shows that the algorithm result is better than MSE, PSNR, SSIM for the same-size images. And the algorithm based on invariant moment similarity can evaluate different image-size and deformation images with low computing-complexity. The assessment experimental result for difference actual images certifies the algorithm effectiveness.

Lifting Wavelet Transform with Singular Value Decomposition for Robust Digital Image Watermarking

Digital image watermarking is proposed using lifting wavelet transform and singular value decomposition for copyright protection and authentication. In this paper, lifting wavelet transform (LWT) transforms the image into subbands. The subband having energy greater than computed „Q‟ value is selected for watermark embedding. Singular value decomposition (SVD) matrix is derived for this subband and used to embed the gray level digital signature as a watermark. This watermarking is useful for real time application since split and merge process in LWT reduces computational complexity by 50%. Loss in information is less as compared to discrete wavelet transform (DWT) algorithm, because in LWT based algorithm down and up sampling is not using. Also, use of SVD lends noninvertible property to the watermarking so that fake watermarked image cannot be generated. This algorithm is spread spectrum thus robust and semi blind needs singular values of original image for retrieval of watermark. The proposed algorithm is tested for robustness against eighteen attacks on each of the five different images. Experimental results and analysis show that proposed algorithm is trustworthy in establishing the ownership and, is robust against different attacks. Correlation coefficient (CRC) values obtained from proposed LWT-SVD algorithm are compared with DWT-SVD method.

Reversible data hiding with histogram-based difference expansion for QR code applications

In this paper, we propose a new algorithm in reversible data hiding, with the application associated with the quick response (QR) codes. QR codes are random patterns, which can be commonly observed on the corner of posters or webpages. The goal of QR codes aims at convenienceoriented applications for mobile phone users. People can use the mobile phone cameras to capture QR code at the corner of web page, and then the hyperlink corresponding to the QR code can be accessed instantly. Since QR code looks like random noise and it occupies a corner of the original image, its existence can greatly reduce the value of the original content. Thus, how to retain the value of original image, while keeping the capability for the instant access for webpages, would be the major concern of this paper. With the aid of our reversible data hiding technique, the QR codes can be hidden into the original image, and considerable increase in embedding capacity can be expected. Next, we propose a scheme such that when the image containing the QR code is browsed, the hyperlink corresponding to the QR code is accessed first. Then, the QR code could get vanished and the original image would be recovered to retain the information conveyed therein. Simulation results demonstrate the applicability of the proposed algorithm.

Kernel regression based feature extraction for 3D MR image denoising

Kernel regression is a non-parametric estimation technique which has been successfully applied to image denoising and enhancement in recent times. Magnetic resonance 3D image denoising has two features that distinguish it from other typical image denoising applications, namely the tridimensional structure of the images and the nature of the noise, which is Rician rather than Gaussian or impulsive. Here we propose a principled way to adapt the general kernel regression framework to this particular problem. Our noise removal system is rooted on a zeroth order 3D kernel regression, which computes a weighted average of the pixels over a regression window. We propose to obtain the weights from the similarities among small sized feature vectors associated to each pixel. In turn, these features come from a second order 3D kernel regression estimation of the original image values and gradient vectors. By considering directional information in the weight computation, this approach substantially enhances the performance of the filter. Moreover, Rician noise level is automatically estimated without any need of human intervention, i.e. our method is fully automated. Experimental results over synthetic and real images demonstrate that our proposal achieves good performance with respect to the other MRI denoising filters being compared.

A Novel algorithm for image encryption by integrated pixel scrambling plus diffusion [IISPD] utilizing duo chaos mapping applicability in wireless systems

Abstract This paper presents a new method for image encryption by integrated pixel scrambling plus diffusion technique [IISPD]. The algorithm makes use of full chaotic property of logistic map and reduces time complexity. The algorithm calculates the permuting address for row by bit xor’ing the adjacent pixel values of original image. Similarly, the algorithm calculates the permuting address for column by bit xor’ing the adjacent pixel values of original image. Therefore, the new technique does not require the knowledge of probability density function of the chaotic orbits a priory, thus it reduces the complexity of the proposed technique. The diffusion is performed after scrambling and is based on two chaotic maps. Therefore, the key space and security of the algorithm is increased. The security analysis and its experimental analysis show that the proposed technique is highly sensitive to initial conditions. It also has higher key space, and higher degree of scrambling.

Study of Image Frequency Spectrum under the Different Settings of USM Parameters

To study the mechanism and functions of USM (Unsharp Masking) sharpening and to investigate its influence on image frequency component, 12 sine-wave images of different spatial frequencies are generated via a program. Then they are composed into a complete gray level image, which serves as original image for sharpening. The original image is sharpened with different parameters of USM. The original image and the sharpened images are processed using Fast Fourier Transformation (FFT) method with MATLAB software. After that, the corresponding Fourier spectral values of the 12 frequencies are extracted, the corresponding spectral value of original image is subtracted from the value of the sharpened images. The data results are finally analyzed and studied. Through the analysis of the spectrum, it indicates that the USM sharpening effect is stronger, while the USM amount and radius increase. But the effects to the spectral components are not balanced. If the USM radius is smaller but the amount is bigger, the effect to the medium and high frequency is stronger. The larger the amount of the USM sharpening and the USM radius are, the stronger the emphasis on the low and medium frequency components grows. The middle and higher frequency components are reduced, if the amount and the radius are all smaller.

기울기 벡터장과 조건부 엔트로피 결합에 의한 의료영상 정합

본 논문에서는 기울기 벡터장과 조건부 엔트로피를 결합한 의료영상 정합 방법을 제안한다. 정합 방법은 조건부 확률의 엔트로피에 기반한 측도를 수행한다. 먼저 공간적 정보를 얻기 위해 윤곽선 정보의 방향을 제공하는 기울기 정보인 기울기 벡터장을 계산한다. 다음으로 주어진 두 영상에서 픽셀의 밝기정보와 에지정보를 결합하여 조인트 히스토그램을 계산하여 조건부 엔트로피를 구하고, 이것을 두 영상의 정합측도로 사용한다. 제안된 방법의 성능평가를 위해 자기공명 영상과 변환된 컴퓨터단층촬영 영상에 기존 방법인 상호정보기반의 측도, 조건부 엔트로피만을 사용한 측도와 비교 실험을 수행한다. 실험결과로부터 제안한 방법이 기존의 최적화 방법들 보다 더 빠르고 정확한 정합임을 알 수 있다. In this paper, we propose a medical image registration technique combining the gradient vector flow and modified conditional entropy. The registration is conducted by the use of a measure based on the entropy of conditional probabilities. To achieve the registration, we first define a modified conditional entropy (MCE) computed from the joint histograms for the area intensities of two given images. In order to combine the spatial information into a traditional registration measure, we use the gradient vector flow field. Then the MCE is computed from the gradient vector flow intensity (GVFI) combining the gradient information and their intensity values of original images. To evaluate the performance of the proposed registration method, we conduct experiments with our method as well as existing method based on the mutual information (MI) criteria. We evaluate the precision of MI- and MCE-based measurements by comparing the registration obtained from MR images and transformed CT images. The experimental results show that the proposed method is faster and more accurate than other optimization methods.

Image bandwidth compression by pre‐compensative interpolation

AbstractIn the interpolative coding method, the pixels constituting the image are divided into “transmitted points” and “interpolated points,” and the former only are transmitted to the receiving end from the sending end. The latter are reconstructed by interpolation at the receiving end. Commonly, the original image values have been used for the transmitted point values as they are, or, the original image values have been properly lowpass filtered for the transmitted point values. However, judging from the entire image transmission system, the problem of how to determine the transmission point values at the sending end is closely related to the interpolation method at the receiving end.In this paper, we propose a pre‐compensative interpolation coding method such that given the interpolation method at the receiving end, the transmission point values at the sending end are determined so that the sum of the squared error between the transmitted points and interpolated points is minimized. We introduce two kinds of pre‐compensative interpolation coding methods for the case where the interpolation at the receiving end is linear, that is, a locally pre‐compensative interpolation coding method and a globally pre‐compensative interpolation coding method. According to a simulation using a standard image, the following effects have been recognized: the improvement of the SN ratio in comparison with existing simple linear interpolation which uses the original image values as the transmitted point values, and the decrease of the image quality degradation which seems to be caused by noise.