Features Of Original Image Research Articles

A Novel Security based Image Watermarking using NBP-IWT-DCT-NSVD-GA-PSO Algorithm

In this novel technique, a modified singular value decomposition named normalized singular value decomposition (NSVD) used for select the original image features to embedding the watermark image into these features. So, the quality of the original image won’t be affected. To select the Normalization Constant of NSVD, the optimization technique used is Genetic Algorithm (GA). In embedding stage, Particle Swarm Optimization (PSO) is used to optimize watermarking constant. Instead of these preliminaries the novel approach also used normalized block processing (NBP) to make the watermarked image more robust to rotation and flipping attacks. The various experiments are conducted on the novel approach to estimate the performance. The experimental results achieved good Robustness for most of the attacks compared to conventional approaches.

Noise detection and image denoising based on fractional calculus

Abstract Fractional-order integral can weaken high-frequency signal and greatly preserve low-frequency signal nonlinearly, that is, the high-frequency noise can be removed while retaining the information of low-frequency image itself, thus the fractional calculus can achieve good a denoising effect and the application of fractional calculus theory in the digital image processing field has also been favored by more and more scholars. On the basis of summarizing and analyzing previous research works, this paper proposes a new method for detecting noise points in images using fractional differential gradient and an improved image denoising algorithm based on fractional integration. The noise detection method determines the noise position by the fractional differential gradient, and achieves to detect the noise, snowflake and stripe anomaly though utilizing the neighborhood information feature of the image and the contour and direction distribution of various noise anomalies in spatial domain; the image denoising algorithm firstly regards the appearance of noise points in image as a small probability event and divides it, then applies the fractional calculus to subtly transform and adjust signal filter and meanwhile utilizes iterative idea to control image denoising effect for accurately distinguishing between noise and high-frequency signals, so that the original image feature information is more preserved while the image is denoised. The simulation results show that this algorithm model can effectively remove the noise while maintaining the details of image edge and texture, and have the characteristics of simple algorithm and good stability. The model can effectively remove the noise and meanwhile preserve the details of image edges and textures, and has the characteristics of simple algorithm and high stability. The study results of this paper provide a reference for further research on the noise detection and image denoising based on fractional calculus.

Developing an Image Manipulation Detection Algorithm Based on Edge Detection and Faster R-CNN

Due to the wide availability of the tools used to produce manipulated images, a large number of digital images have been tampered with in various media, such as newspapers and social networks, which makes the detection of tampered images particularly important. Therefore, an image manipulation detection algorithm leveraged by the Faster Region-based Convolutional Neural Network (Faster R-CNN) model combined with edge detection was proposed in this paper. In our algorithm, first, original tampered images and their detected edges were sent into symmetrical ResNet101 networks to extract tampering features. Then, these features were put into the Region of Interest (RoI) pooling layer. Instead of the RoI max pooling approach, the bilinear interpolation method was adopted to obtain the RoI region. After the RoI features of original input images and edge feature images were sent into bilinear pooling layer for feature fusion, tampering classification was performed in fully connection layer. Finally, Region Proposal Network (RPN) was used to locate forgery regions. Experimental results on three different image manipulation datasets show that our proposed algorithm can detect tampered images more effectively than other existing image manipulation detection algorithms.

Using chaos world cup optimization algorithm for medical images contrast enhancement

SummaryIn this paper, a chaos‐based optimization algorithm is employed for medical images contrast enhancement. Here, a weighted combined framework is suggested as the cost function for the contrast enhancement. The method utilizes the advantages of Gamma correction, histogram equalization, and edge information for decreasing the original image features losses. For more enhancements, a piecewise version of Gamma correction is also utilized to decrease the unnatural artifacts in the output image. A combined cost function is employed based on the three aforementioned features and the proposed chaos world cup optimization algorithm is used for maximizing the fitness function. The simulation results have been compared with five state‐of‐the‐art methods for presenting the method efficiency. To do this, contrast, homogeneity, weighted average peak SNR, a measure of enhancement, and contrast noise ratio are employed. The results also applied to two standard medical imaging datasets and compared with the other methods. Final results denoted that the presented multiobjective optimization algorithm improves the quality of the image contrast and can illustrate more details and information toward the other compared methods.

An Energy-Based SAR Image Segmentation Method with Weighted Feature

To extract more structural features, which can contribute to segment a synthetic aperture radar (SAR) image accurately, and explore their roles in the segmentation procedure, this paper presents an energy-based SAR image segmentation method with weighted features. To precisely segment a SAR image, multiple structural features are incorporated into a block- and energy-based segmentation model in weighted way. In this paper, the multiple features of a pixel, involving spectral feature obtained from original SAR image, texture and boundary features extracted by a curvelet transform, form a feature vector. All the pixels’ feature vectors form a feature set of a SAR image. To automatically determine the roles of the multiple features in the segmentation procedure, weight variables are assigned to them. All the weight variables form a weight set. Then the image domain is partitioned into a set of blocks by regular tessellation. Afterwards, an energy function and a non-constrained Gibbs probability distribution are used to combine the feature and weight sets to build a block-based energy segmentation model with feature weighted on the partitioned image domain. Further, a reversible jump Markov Chain Monte Carlo (RJMCMC) algorithm is designed to simulate from the segmentation model. In the RJMCMC algorithm, three move types were designed according to the segmentation model. Finally, the proposed method was tested on the SAR images, and the quantitative and qualitative results demonstrated its effectiveness.

Pathology-preserving intensity standardization framework for multi-institutional FLAIR MRI datasets

Fluid-Attenuated Inversion Recovery (FLAIR) MRI are used by physicians to analyze white matter lesions (WML) of the brain, which are related to neurodegenerative diseases such as dementia and vascular disease. To study the causes and progression of these diseases, multi-centre (MC) studies are conducted, with images acquired and analyzed from multiple institutions. Due to differences in acquisition software and hardware, there is variability in image properties, which creates challenges for automated algorithms. This work explores this variability, known as the MC effect, by analyzing nearly 5000 MC FLAIR volumes and proposes an intensity standardization framework to normalize intensity non-standardness in FLAIR MRI, while ensuring the appearance of WML. Results show that original image characteristics varied significantly between scanner vendors and centres, and that this variability was reduced with standardization. To further highlight the utility of intensity standardization, a threshold-based brain extraction algorithm is implemented and compared with a classifier-based approach. A competitive Dice Similarity Coefficient of 81% was achieved on 183 volumes, demonstrating that optimized pre-processing can effectively reduce the variability in MC studies, allowing for simplified algorithms to be applied on large datasets robustly.

A Novel Multispace Image Reconstruction Method for Pathological Image Classification Based on Structural Information.

Pathological image classification is of great importance in various biomedical applications, such as for lesion detection, cancer subtype identification, and pathological grading. To this end, this paper proposed a novel classification framework using the multispace image reconstruction inputs and the transfer learning technology. Specifically, a multispace image reconstruction method was first developed to generate a new image containing three channels composed of gradient, gray level cooccurrence matrix (GLCM) and local binary pattern (LBP) spaces, respectively. Then, the pretrained VGG-16 net was utilized to extract the high-level semantic features of original images (RGB) and reconstructed images. Subsequently, the long short-term memory (LSTM) layer was used for feature selection and refinement while increasing its discrimination capability. Finally, the classification task was performed via the softmax classifier. Our framework was evaluated on a publicly available microscopy image dataset of IICBU malignant lymphoma. Experimental results demonstrated the performance advantages of our proposed classification framework by comparing with the related works.

Bilinear Supervised Hashing Based on 2D Image Features

Hashing has been recognized as an efficient representation learning method to effectively handle big data due to its low computational complexity and memory cost. Most of the existing hashing methods focus on learning the low-dimensional vectorized binary features based on the high-dimensional raw vectorized features. However, the studies on how to obtain preferable binary codes from the original 2D image features for retrieval is very limited. This paper proposes a bilinear supervised discrete hashing (BSDH) method based on 2D image features which utilizes bilinear projections to binarize the image matrix features such that the intrinsic characteristics in the 2D image space are preserved in the learned binary codes. Meanwhile, the bilinear projection approximation and vectorization binary codes regression are seamlessly integrated together to formulate the final robust learning framework. Furthermore, a discrete optimization strategy is developed to alternatively update each variable for obtaining the high-quality binary codes. In addition, two 2D image features, traditional SURF-based FVLAD feature, and CNN-based AlexConv5 feature are designed for further improving the performance of the proposed BSDH method. The results of extensive experiments conducted on four benchmark datasets show that the proposed BSDH method almost outperforms all competing hashing methods with different input features by different evaluation protocols.

Joint Image Deblurring and Matching with Blurred Invariant‐Based Sparse Representation Prior

Image matching is important for vision‐based navigation. However, most image matching approaches do not consider the degradation of the real world, such as image blur; thus, the performance of image matching often decreases greatly. Recent methods try to deal with this problem by utilizing a two‐stage framework—first resorting to image deblurring and then performing image matching, which is effective but depends heavily on the quality of image deblurring. An emerging way to resolve this dilemma is to perform image deblurring and matching jointly, which utilize sparse representation prior to explore the correlation between deblurring and matching. However, these approaches obtain the sparse representation prior in the original pixel space, which do not adequately consider the influence of image blurring and thus may lead to an inaccurate estimation of sparse representation prior. Fortunately, we can extract the pseudo‐Zernike moment with blurred invariant from images and obtain a reliable sparse representation prior in the blurred invariant space. Motivated by the observation, we propose a joint image deblurring and matching method with blurred invariant‐based sparse representation prior (JDM‐BISR), which obtains the sparse representation prior in the robust blurred invariant space rather than the original pixel space and thus can effectively improve the quality of image deblurring and the accuracy of image matching. Moreover, since the dimension of the pseudo‐Zernike moment is much lower than the original image feature, our model can also increase the computational efficiency. Extensive experimental results demonstrate that the proposed method performs favorably against the state‐of‐the‐art blurred image matching approach.

Initial Matting-Guided Visual Tracking With Siamese Network

Fully-convolutional Siamese networks for visual tracking have drawn great attention in balancing tracking accuracy and speed. However, there is still some inherent inaccuracy with advanced trackers, since they only learn a general matching model from large scale datasets by off-line training. This generates the target template without sufficient discriminant information and does not adapt well to the current tracking sequence. In this paper, we introduce the channel attention mechanism into the network to better learn the matching model and, during the online tracking phase, we design an initial matting guidance strategy in which: 1) the superpixel matting algorithm is applied to extract the target foreground in the initial frame, and 2) the matted image with foreground only is fed into the network and fused with the original image feature. Under matting guidance, the fused target template has more details for representation of target appearance and more structural information from superpixels for robust tracking. The experimental results on object tracking benchmark (OTB) show that our approach achieves excellent performance while it also provides real-time tracking speed.

Visible Infrared Cross-Modality Person Re-Identification Network Based on Adaptive Pedestrian Alignment

Cross-modality person re-identification between the visible domain and infrared domain is important but extremely challenging for night-time surveillance. Besides the cross-modality discrepancies caused by different camera spectrums, visible infrared person re-identification (VI-REID) still suffers from much pedestrian misalignment as well as the variations caused by different camera viewpoints and various pedestrian pose deformations like traditional person re-identification. In this paper, we propose a multi-path adaptive pedestrian alignment network (MAPAN) to learn discriminative feature representations. The multi-path network learns features directly from the data in an end-to-end manner and aligns the pedestrians adaptively without any additional manual annotations. To alleviate the intra-modality discrepancies caused by image misalignment, we combine the aligned visible image features with the original visible image features and enhance the attention of the network towards pedestrians, resulting in significant improvements in distinguishability of the learning features. To mitigate the cross-modality discrepancies between the visible domain and the infrared domain, the discriminative features of the two modalities are mapped to the same feature embedding space, and the identity loss as well as triplet loss is incorporated as the overall loss. Extensive experiments demonstrate the superior performance of proposed method compared to the state-of-the-arts.

Pixel-Based Image Encryption Without Key Management for Privacy-Preserving Deep Neural Networks

We present a novel privacy-preserving scheme for deep neural networks (DNNs) that enables us not to only apply images without visual information to DNNs but to also consider the use of independent encryption keys for both training and testing images for the first time. In this paper, a novel pixel-based image encryption method that maintains important features of original images is proposed for privacy-preserving DNNs. For training, a DNN model is trained with images encrypted by using the proposed method with independent encryption keys. For testing, the model enables us to apply both encrypted images and plain images for image classification. Therefore, there is no need to manage keys. In addition, the proposed method allows us to perform data augmentation in the encrypted domain. In an experiment, the proposed method is applied to well-known networks, that is, deep residual networks and densely connected convolutional networks, for image classification. The experimental results demonstrate that the proposed method, under the use of independent encryption keys, can maintain a high classification performance, and it is robust against ciphertext-only attacks (COAs). Moreover, the results confirm that the proposed scheme is able to classify plain images as well as encrypted images, even when data augmentation is carried out in the encrypted domain.

Prominent edge detection with deep metric expression and multi-scale features

Edge detection is one of today’s hottest computer vision issues with widely applications. It is beneficial for improving the capability of many vision systems, such as semantic segmentation, salient object detection and object recognition. Deep convolution neural networks (CNNs) recently have been employed to extract robust features, and have achieved a definite improvement. However, there is still a long run to study this hotspot with the main reason that CNNs-based approaches may cause the edges thicker. To address this problem, a novel semantic edge detection algorithm using multi-scale features is proposed. Our model is deep symmetrical metric learning network, which includes 3 key parts. Firstly, the deep detail layer, as a preprocessing layer and a guide module, is employed to remove some low-frequency information and still maintain the edge. Secondly, the deep encoder-decoder networks extract multi-scale features of original image, integrated for complementing information among each level feature. Finally, metric learning is introduced to generate a metric space used to predict edge result. It is easy to distinguish different categories, such as edge space and object space. Simulations and comparisons on benchmark datasets demonstrate the proposed algorithm is superior to the others through visual and quantitative evaluation, and specifically, the score of ODS reachs 0.788.

Bi-dimensional empirical mode decomposition (BEMD) and the stopping criterion based on the number and change of extreme points

In the bi-dimensional empirical mode decomposition, the determination of the stopping criterion is an important reason for obtaining a complete bi-dimensional intrinsic mode function. An excellent stopping criterion can adapt the image characteristics to stop the decomposition. This paper first analyzes the number and distribution of extreme points reflecting the physical state of the mean surface during the sieving process. Then, bi-dimensional empirical mode decomposition and the stopping criterion based on the number and change of extreme points is proposed. In order to verify the adaptability, effectiveness and reliability of the criterion, the relevant examples were subjected to bi-dimensional empirical mode decomposition experiments under the conditions of the traditional stopping criterion, the GRILL stopping criterion and the stopping criterion proposed in this paper. The results show that the intrinsic mode function obtained by the stop criterion proposed in this paper is more in line with the physical characteristics, more reflective of the original image feature information and with higher accuracy.

Weight strategy aided infrared and visible image fusion utilizing the center operator from opening and closing based toggle operator

Fusion of infrared and visible images is an effective way for image analysis. The crucial factor of the fusion is extracting and combing the image features of original images. In this paper, an effective algorithm for infrared and visible image fusion utilizing a center operator is proposed. The center operator constructed from opening and closing based toggle operator is used to extract the multi-scale features of original images. After that, the final fusion features are calculated from these extracted multi-scale features through a weight strategy. The weight strategy is based on the entropy and gradient information of the extracted features, which is an effective way for integrating the information of the original images. Finally, the fusion image is produced by adding the final fusion features with the average image of original images. Experimental results of different types of infrared and visible images indicate that, the proposed algorithm performs effectively for infrared and visible image fusion.

An adaptive deep Q-learning strategy for handwritten digit recognition

Handwritten digits recognition is a challenging problem in recent years. Although many deep learning-based classification algorithms are studied for handwritten digits recognition, the recognition accuracy and running time still need to be further improved. In this paper, an adaptive deep Q-learning strategy is proposed to improve accuracy and shorten running time for handwritten digit recognition. The adaptive deep Q-learning strategy combines the feature-extracting capability of deep learning and the decision-making of reinforcement learning to form an adaptive Q-learning deep belief network (Q-ADBN). First, Q-ADBN extracts the features of original images using an adaptive deep auto-encoder (ADAE), and the extracted features are considered as the current states of Q-learning algorithm. Second, Q-ADBN receives Q-function (reward signal) during recognition of the current states, and the final handwritten digits recognition is implemented by maximizing the Q-function using Q-learning algorithm. Finally, experimental results from the well-known MNIST dataset show that the proposed Q-ADBN has a superiority to other similar methods in terms of accuracy and running time.

Contrast enhancement using feature-preserving bi-histogram equalization

A new contrast enhancement algorithm is proposed, which is based on the fact that, for conventional histogram equalization, a uniform input histogram produces an equalized output histogram. Hence before applying histogram equalization, we modify the input histogram in such a way that it is close to a uniform histogram as well as the original one. Thus, the proposed method can improve the contrast while preserving original image features. The main steps of the new algorithm are adaptive gamma transform, exposure-based histogram splitting, and histogram addition. The object of gamma transform is to restrain histogram spikes to avoid over-enhancement and noise artifacts effect. Histogram splitting is for preserving mean brightness, and histogram addition is used to control histogram pits. Extensive experiments are conducted on 300 test images. The results are evaluated subjectively as well as by DE, PSNR EBCM, GMSD, and MCSD metrics, on which, except for the PSNR, the proposed algorithm has some improvements of 2.89, 9.83, 28.32, and 26.38% over the second best ESIHE algorithm, respectively. That is to say, the overall image quality is better.

FFT Consolidated Sparse and Collaborative Representation for Image Classification

Spectrum analysis can quickly extract and analyze frequency domain features of signal, and it has been widely applied in fields of image processing, noise processing and signal processing. Fast Fourier transform (FFT) is fast and efficient, because it can efficiently decrease complexity of discrete Fourier transform. As a consequence, FFT is a very good method for image frequency spectrum analysis. In this paper, we propose to consolidate frequency domain representation by sparse representation (SR) and collaborative representation classification (CRC) which has excellent performance in comparison with general sparse representation-associated classification algorithms. Our proposed novel method has three main phases. The first phase utilizes FFT to extract frequency domain features of original images, which are complementary with representations of the original images. The second phase of our proposed novel method exploits CRC or SR to obtain scores of original images and obtained features, respectively. The third phase integrates the scores of original images and obtained features and uses them to classify images. The major contribution of the proposed method is that it is usually more robust than methods using only FFT, CRC or state-of-art method CIRLRC for image classification. The experiments of image classification demonstrate that the simultaneous use of FFT and CRC or sparse representation classification has high accuracy on image recognition.

Swarm intelligence optimized piecewise gamma corrected histogram equalization for dark image enhancement

In this paper, a highly adaptive swarm intelligence optimized dark image enhancement approach is proposed for remotely sensed satellite images. Here, a weighted summation framework is suggested for imparting “on-demand entropy restoration and contrast enhancement”. This approach utilizes the benefits of both gamma correction and histogram equalization; and hence, overall image enhancement can be appropriately imposed without losing original image features, especially for dark satellite images. For further improvement, gamma correction is also employed in a piecewise manner, separately for dark as well as light pixel values, so that over-saturation and other related unnatural artifacts can be avoided. A suitable entropy and contrast based cost function is utilized, and its maximization is done by employing particle swarm optimization over a three-dimensional search space. The proposed approach is found to be highly appreciable for overall enhancement, preserving all the intrinsic visual details for a wide range of dark image database covering satellite as well as general images.

Local gray level S-curve transformation – A generalized contrast enhancement technique for medical images

Most medical images suffer from inadequate contrast and brightness, which leads to blurred or weak edges (low contrast) between adjacent tissues resulting in poor segmentation and errors in classification of tissues. Thus, contrast enhancement to improve visual information is extremely important in the development of computational approaches for obtaining quantitative measurements from medical images. In this research, a contrast enhancement algorithm that applies gray-level S-curve transformation technique locally in medical images obtained from various modalities is investigated. The S-curve transformation is an extended gray level transformation technique that results into a curve similar to a sigmoid function through a pixel to pixel transformation. This curve essentially increases the difference between minimum and maximum gray values and the image gradient, locally thereby, strengthening edges between adjacent tissues. The performance of the proposed technique is determined by measuring several parameters namely, edge content (improvement in image gradient), enhancement measure (degree of contrast enhancement), absolute mean brightness error (luminance distortion caused by the enhancement), and feature similarity index measure (preservation of the original image features). Based on medical image datasets comprising 1937 images from various modalities such as ultrasound, mammograms, fluorescent images, fundus, X-ray radiographs and MR images, it is found that the local gray-level S-curve transformation outperforms existing techniques in terms of improved contrast and brightness, resulting in clear and strong edges between adjacent tissues. The proposed technique can be used as a preprocessing tool for effective segmentation and classification of tissue structures in medical images.