In present digital era, multimedia like images, text, documents and videos plays a vital role, therefore due to increase in usage of digital data; there comes high demand of security. Encryption is a technique used to secure and protect the images from unfair means. In cryptography, chaotic maps play an important role in forming strong and effective encryption algorithm. In this paper 3D chaotic logistic map with DNA encoding is used for confusion and diffusion of image pixels. Additionally, three symmetric keys are used to initialize 3D chaos logistic map, which makes the encryption algorithm strong. The symmetric keys used are 32 bit ASCII key, Chebyshev chaotic key and prime key. The algorithm first applies 3D non-linear logistic chaotic map with three symmetric keys in order to generate initial conditions. These conditions are then used in image row and column permutation to create randomness in pixels. The third chaotic sequence generated by 3D map is used to generate key image. Diffusion of these random pixels are done using DNA encoding; further XOR logical operation is applied between DNA encoded input image and key image. Analysis parameters like NPCR, UACI, entropy, histogram, chi-square test and correlation are calculated for proposed algorithm and also compared with different existing encryption methods.
相似文献The competitive layer model (CLM) implemented by the Lotka–Volterra recurrent neural networks (LV RNNs) is prominently characterized by its capability of binding neurons with similar feature into the same layer by competing among neurons at different layers in a column. This paper proposes to use the CLM of the LV RNN for detecting brain activated regions from the fMRI data. The correlated voxels from brain fMRI data can be obtained, and the clusters from fMRI time series can be uncovered. Experiments on synthetic and real fMRI data demonstrate the effectiveness of binding activated voxels into the ‘active’ layers of the CLM. The activated voxels can be detected more accurately than some existing methods by the proposed method.
相似文献The target of this article is to study almost periodic dynamical behaviors for complex-valued recurrent neural networks with discontinuous activation functions and time-varying delays. We construct an equivalent discontinuous right-hand equation by decomposing real and imaginary parts of complex-valued neural networks. Based on differential inclusions theory, diagonal dominant principle and nonsmooth analysis theory of generalized Lyapunov function method, we achieve the existence, uniqueness and global stability of almost periodic solution for the equivalent delayed differential network. In particular, we derive a series of results on the equivalent neural networks with discontinuous activation functions, constant coefficients as well as periodic coefficients, respectively. Finally, we give a numerical example to demonstrate the effectiveness and feasibility of the derived theoretical results.
相似文献An imperceptible digital watermarking algorithm based on 4-level discrete wavelet transform, discrete cosine transform and singular value decomposition is designed. In this method, the 4-level diagonal sub-band image is obtained by performing the 4-level two-dimensional wavelet transform on the original image, and then a coefficient matrix is produced by applying the discrete cosine transform on the 4-level diagonal sub-band image. A diagonal matrix is constructed by performing the singular value decomposition on the coefficient matrix. The watermark is scrambled by Arnold transform and Logistic map, then the scrambled watermark is processed by the singular value decomposition. Later, the encryption process is completed by embedding the scrambled watermark singular value into the singular value of the coefficient matrix. Simulation results demonstrate that the proposed digital watermarking algorithm could resist JPEG compression attack, Salt and Pepper noise attack, Gaussian noise attack, filter attack, brightness change attack, geometric attack, cut attack, etc.
相似文献A visually secure multiple image encryption using chaotic map and compressive sensing is proposed. The existing image encryption algorithms transform a secret image into a random noise like cipher image which can lead to cryptanalysis by an intruder. In the proposed method, compressive sampling is done using a chaos based, key controlled measurement matrix. An image dependent key generation scheme is used to generate the parameters of the chaotic map. The secret images are transformed into wavelet coefficients, and scrambled along a zigzag path, so that the high correlation among them can be reduced and thereby provide increased security level. The sparse coefficients are measured using the chaotic map-based measurement matrix, whose initial parameters are obtained from the keys generated. Then the reduced measurements are embedded into the sub-bands of the wavelet transformed cover image. Therefore, the proposed algorithm is highly sensitive to the secret images and can effectively withstand known-plaintext and chosen-plaintext attacks. Additionally, the cipher image and the secret images are of same size and do not require additional transmission bandwidth and storage space.
相似文献Computer vision techniques enhanced by the advent of deep learning has become a quintessential part of our day-to-day life. The application of such computer vision techniques in image retrieval can be termed as query based image retrieval process. Conventional methods have limitations such as increased dimensionality, reduced accuracy, high time consumption, and dependence on indexing for retrieval. In order to overcome these limitations, this research work aims to develop a new image retrieval system by developing an image preprocessing mechanism via target prediction technique, which isolates object from the background. Further, a Micro-structure based Pattern Extraction (MPE) technique is implemented to extract the patterns from the preprocessed image, where the diagonal patterns are generated for increasing the accuracy of the retrieval process. Consequently, the Convolutional Neural Network (CNN) is utilized to reduce the dimensionality of the features, and the similarity learning approach is utilized to map the selected features with trained features based on the distance metric. The performance of the proposed system is evaluated by using various measures. Thereby, the efficiency of the proposed technique is ascertained by comparing it with the existing techniques.
相似文献A novel image encryption framework is proposed in this article. A new chaotic map and a pseudorandom bit generator are proposed. Apart from this, a novel image encryption system is designed based on the proposed map and the proposed pseudorandom bit generator. These three are the major contributions of this work that makes a complete cryptosystem. The proposed new chaotic map is proposed which will be known as the ‘RCM map’ and its chaotic property is studied based on Devaney’s theory. The proposed pseudorandom bit generator is tested using the NIST test suite. The proposed method is simple to implement and does not involve any highly complex operations. Moreover, the proposed method is completely lossless, and therefore cent percent of data can be recovered from the encrypted image. The decryption process is also simple to implement i.e. just reverse of the encryption procedure. A scrambling algorithm is also proposed to further enhance the security of the overall system. The simulation, detailed analysis, and comparative studies of the proposed overall image encryption framework will help to understand the strengths and weaknesses of it. The experimental results are very promising and show the prospects of chaos theory and its usage in the field of data security.
相似文献This paper is concerned with a class of neutral type recurrent neural networks with time-varying delays, distributed delay and D operator on time–space scales which unify the continuous-time and the discrete-time recurrent neural networks under the same framework. Some sufficient conditions are given for the existence and the global exponential stability of the pseudo almost periodic solution by using inequality analysis techniques on time scales, fixed point theorem and the theory of calculus on time scales. An example is given to show the effectiveness of the derived results via computer simulations.
相似文献Image segmentation is a process of segregating foreground object from background object in an image. This paper proposes a method to perform image segmentation for the color and textured images with a two-step approach. In the first step, self-organizing neurons based on neural networks are used for clustering the input image, and in the second step, multiphase active contour model is used to get various segments of an image. The contours are initialized in the active contour model with the help of the self-organizing maps obtained as a result of first step. From the results, it is inferred that the proposed method provides better segmentation result for all types of images.
相似文献Because Unmanned Aerial Vehicle (UAV) image exhibits low positioning accuracy, the accurate registration of the image is required. Since the viewpoint direction, capturing time and shoot height are considerably different between the UAV image and google satellite map, the existing methods cannot match two images accurately. For the registration between the UAV image and google satellite map, a full-automated image registration method was proposed based on deep convolution feature. Such method consists of five steps: automatically reference images downloading, uniform key point extraction, deep convolution features computation, accurately feature matching and image registration. The reference image was downloaded from google map service according to the approximate location and region of the UAV image. The deep convolution feature was extracted using the pre-trained VGG16 model. Finally, many experiments were performed to verify the efficiency of the proposed method, and the results demonstrate that the proposed method is more effective and robust than the existing method.
相似文献In the era of big data, many fields produce massive images every day. To improve the security of image transmission, a multiple-image encryption algorithm based on bit planes and chaos is proposed. Firstly, k images are decomposed into 8k bit planes; secondly, the Chen chaotic system and two-dimensional Logistic map are used to scramble pixel positions of the 5th-8th bit planes of each image; thirdly, the scrambled bit planes and all the 1st-4th bit planes are randomly combined into k scrambled images; finally, to obtain k encrypted images, the exclusive OR operation is performed on the chaotic image and k scrambled images. Experimental results and algorithm analyses show that the proposed algorithm has the advantages of the excellent encryption effect, high encryption efficiency, large key space, key sensitivity, strong ability to resist the statistical attack, the brute-force attack, etc.
相似文献