Pixel-level Image Research Articles

Feature-Level Fusion between Gaofen-5 and Sentinel-1A Data for Tea Plantation Mapping

The accurate mapping of tea plantations is significant for government decision-making and environmental protection of tea-producing regions. Hyperspectral and Synthetic Aperture Radar (SAR) data have recently been widely used in land cover classification, but effective integration of these data for tea plantation mapping requires further study. This study developed a new feature-level image fusion method called LPPSubFus that combines locality preserving projection and subspace fusion (SubFus) to map tea plantations. Based on hyperspectral and SAR data, we first extracted spectral indexes, textures, and backscattering information. Second, this study applied LPPSubFus to tea plantation mapping with different classification algorithms. Finally, we compared the performance of LPPSubFus, SubFus, and pixel-level image fusion in tea plantation mapping. Feature-level image fusion performed better than pixel-level image fusion. An improvement of about 3% was achieved using feature-level image fusion compared to hyperspectral data alone. Regarding feature-level image fusion, LPPSubFus improved the overall accuracy by more than 3% compared to SubFus. In particular, LPPSubFus using neural network algorithms achieved the highest overall accuracy (95%) and over 90% producer and user accuracy for tea plantations and forests. In addition, LPPSubFus was more compatible with different classification algorithms than SubFus. Based on these findings, it is concluded that LPPSubFus has better and more stable performance in tea plantation mapping than pixel-level image fusion and SubFus. This study demonstrates the potential of integrating hyperspectral and SAR data via LPPSubFus for mapping tea plantations. Our work offers a promising tea plantation mapping method and contributes to the understanding of hyperspectral and SAR data fusion.

Incoherent digital holographic spectral imaging with high accuracy of image pixel registration* *Project supported by the National Natural Science Foundation of China (Grant Nos. 61505178, 61307019, and 11504333) and the Natural Science Foundation of Henan Province, China (Grant Nos. 18A140032, 15A140038, and 16A140035).

Fresnel incoherent correlation holography (FINCH) is a unique three-dimensional (3D) imaging technique which has the advantages of scanning-free, high resolution, and easy matching with existing mature optical systems. In this article, an incoherent digital holographic spectral imaging method with high accuracy of spectral reconstruction based on liquid crystal tunable filter (LCTF) and FINCH is proposed. Using the programmable characteristics of spatial light modulator (SLM), a series of phase masks, none of whose focal lengths changes with wavelength, is designed and made. For each wavelength of LCTF output, SLM calls three phase masks with different phase constants at the corresponding wavelength, and CCD records three holograms. The spectral images obtained by this method have a constant magnification, which can achieve pixel-level image registration, restrain image registration errors, and improve spectral reconstruction accuracy. The results show that this method can not only obtain the 3D spatial information and spectral information of the object simultaneously, but also have high accuracy of spectral reconstruction and excellent color reproducibility.

3-Image Bit-Level Encryption Algorithm Based on 3D Nonequilateral Arnold Transformation and Hyperchaotic System

In this paper, we propose a novel 3-image bit-level encryption algorithm based on 3D nonequilateral Arnold transformation and hyperchaotic system. Firstly, the three plain images with N × M are decomposed into 8-bit planes and then they overlap into a 3D bit matrix with size N × M × 24 . Then, the 3D bit matrix is scrambled by 3D nonequilateral Arnold transformation and the scrambled 3D bit matrix is integrated and transformed into three 2D pixel-level images. Finally, the hyperchaotic system is used to diffuse the three 2D pixel-level images; then three diffused images are rearranged to be one color image, resulting in the encrypted image. Numerical simulations and analyses of the proposed encryption scheme are given to validate the feasibility and safety of the method. The statistical analyses like histogram, correlation, and entropy confirm that the proposed method can effectively resist statistical attacks and security key analysis shows that the key space is large enough to render the brute-force attack ineffective in proposed method. The differential analysis confirms that the proposed method is effective against differential attacks and the results of the experiment confirmed that the method can resist occlusion attack.

Application of 3D laser scanning technology for image data processing in the protection of ancient building sites through deep learning

To study the conservation of architectural heritage, computer algorithms are used to process the artificial field measurements and reference data maps. A 3D virtual model of traditional architecture is constructed for the direct learning and feature extraction from image data through deep learning. A set of tools and processes for pixel-level image processing labeling are proposed, and a label quality checking tool is written specially. Through the training method of transfer learning, the convergence speed and accuracy of the network are accelerated and improved. Based on the field data collection of the architectural heritage by a 3D laser scanner, the impacts of the number of stations, the number of targets, and the distance on the data scanning results are analyzed, thereby drawing the rules and principles of setting up the survey stations. While processing the point cloud data, for the redundant data and the rough difference points found in the original point cloud data, the program is written by the gross error elimination algorithm, which realizes the automatic elimination of the point cloud gross error data and provides a convenient method for data processing. The data collection, data processing, and model construction of architectural heritage are performed by the 3D laser scanner. The 3D models of traditional architecture with texture photos are obtained. The results show that through correlation error analysis and model evaluation, the requirements for the measurement of traditional architecture can be achieved. Therefore, the technology has a guiding significance for the conservation of traditional architecture, which proves that the 3D laser scanner has broad application prospects in the surveying and mapping of architectural heritage.

Branch-structured detector for fast face detection using asymmetric LBP features

Face detection has been widely used to solve many important problems. In this paper, we present a fast face detector that is more suitable to be used by a low-cost embedded system. It can obtain high performance but use less CPU and memory resources. We first present a kind of pixel-level image feature named asymmetric LBP feature (ALBP). Furthermore, we find four kinds of four-bit ALBP features that are suitable to be used to construct cascade classifiers, since the four-bit ALBP features are discriminative features and large feature pools can be generated even if a small image patch is given. Second, we propose a branch-structured face detector that is composed of three ALBP-based cascade classifiers, i.e., one deep ALBP cascade and two shallow ALBP cascades. The detection speed and performance on FDDB dataset of the branch-structured face detector have both been evaluated. Experimental results show that it runs much faster than existing face detectors run on similar platforms, and its performance is close to that of well-known non-CNN face detectors which can achieve high performance.

Evaluation of Pan-Sharpening Techniques Using Lagrange Optimization

Earth’s observation satellites, such as IKONOS, provide simultaneously multispectral and panchromatic images. A multispectral image comes with a lower spatial and higher spectral resolution in contrast to a panchromatic image which usually has a high spatial and a low spectral resolution. Pan-sharpening represents a fusion of these two complementary images to provide an output image that has both spatial and spectral high resolutions. The objective of this paper is to propose a new method of pan-sharpening based on pixel-level image manipulation and to compare it with several state-of-art pansharpening methods using different evaluation criteria. The paper presents an image fusion method based on pixel-level optimization using the Lagrange multiplier. Two cases are discussed: (a) the maximization of spectral consistency and (b) the minimization of the variance difference between the original data and the computed data. The paper compares the results of the proposed method with several state-of-the-art pan-sharpening methods. The performance of the pan-sharpening methods is evaluated qualitatively and quantitatively using evaluation criteria, such as the Chi-square test, RMSE, SNR, SD, ERGAS, and RASE. Overall, the proposed method is shown to outperform all the existing methods.

TEXT RECOGNITION FROM IMAGES USING IMAGE PROCESSING TECHNIQUE

— Image Processing is a next level character and object recognizer. At present image processing is a major technology that evolved in order to identify things as same as human eyes. It is developed by using a trained model in order to capture objects optically, it has greater error rate in order to capture the character and objects. Nowadays it is popularly used everywhere in various businesses and software tools. A paper document is best source of raw data but filtering required information from it is difficult. In order to gather in such a way, we need information into textual document which easily underpass into filters and produces required output from it. Image processing algorithms are not accurate enough to give efficient output of the text document. It can be improved by using trained model which frequently updates the algorithm efficiency and in order to decrease the word error rate. In this way text can be recognized efficiently from the image. The major distractors in this are image quality, image contrast, pixel level impurities and image backgrounds acts a lot in text recognition. Various improvements are brought in order to get the best out of the image content.

A novel synthetic aperture radar image change detection system using radial basis function-based deep convolutional neural network

Today, the automatic change detection and also classification as of the Synthetic Aperture Radar (SAR) images remain a hard process. In the existing research, the availability of Speckle Noise (SN), high time-consumption, and low accuracy are the chief issues. To resolve such issues, this paper proposed a novel SAR image change detection system utilizing a Radial Basis Function-based Deep Convolutional Neural Network (RBF-DCNN). The proposed methodology comprises six phases, namely, pre-processing, obtaining difference image, pixel-level image fusion, Feature Extraction (FE), Feature Selection (FS), and also change detection (CD) utilizing the classifier. Initially, the noise is eliminated as of the input, SAR image 1 and SAR image 2, utilizing the NLMSTAF approach. Subsequently, the difference image is attained by utilizing a Log-ratio operator (LRO) and Gauss-LRO, and the attained difference image is then fused. Next, the LTrP, WST, edge, and MSER features are extracted from the fused image. As of those features that were extracted, the necessary features are selected utilizing the Hybrid GWO-GA algorithm. The features (selected) are finally inputted to the RBF-DCNN classifier for detecting the changes in an image. Experimental outcomes established that the proposed work renders better performance on considering the existing system.

Evaluation of automated computed tomography segmentation to assess body composition and mortality associations in cancer patients

BackgroundBody composition from computed tomography (CT) scans is associated with cancer outcomes including surgical complications, chemotoxicity, and survival. Most studies manually segment CT scans, but Automatic Body composition Analyser using Computed tomography image Segmentation (ABACS) software automatically segments muscle and adipose tissues to speed analysis. Here, we externally evaluate ABACS in an independent dataset.MethodsAmong patients with non‐metastatic colorectal (n = 3102) and breast (n = 2888) cancer diagnosed from 2005 to 2013 at Kaiser Permanente, expert raters annotated tissue areas at the third lumbar vertebra (L3). To compare ABACS segmentation results to manual analysis, we quantified the proportion of pixel‐level image overlap using Jaccard scores and agreement between methods using intra‐class correlation coefficients for continuous tissue areas. We examined performance overall and among subgroups defined by patient and imaging characteristics. To compare the strength of the mortality associations obtained from ABACS's segmentations to manual analysis, we computed Cox proportional hazards ratios (HRs) and 95% confidence intervals (95% CI) by tertile of tissue area.ResultsMean ± SD age was 63 ± 11 years for colorectal cancer patients and 56 ± 12 for breast cancer patients. There was strong agreement between manual and automatic segmentations overall and within subgroups of age, sex, body mass index, and cancer stage: average Jaccard scores and intra‐class correlation coefficients exceeded 90% for all tissues. ABACS underestimated muscle and visceral and subcutaneous adipose tissue areas by 1–2% versus manual analysis: mean differences were small at −2.35, −1.97 and −2.38 cm2, respectively. ABACS's performance was lowest for the <2% of patients who were underweight or had anatomic abnormalities. ABACS and manual analysis produced similar associations with mortality; comparing the lowest to highest tertile of skeletal muscle from ABACS versus manual analysis, the HRs were 1.23 (95% CI: 1.00–1.52) versus 1.38 (95% CI: 1.11–1.70) for colorectal cancer patients and 1.30 (95% CI: 1.01–1.66) versus 1.29 (95% CI: 1.00–1.65) for breast cancer patients.ConclusionsIn the first study to externally evaluate a commercially available software to assess body composition, automated segmentation of muscle and adipose tissues using ABACS was similar to manual analysis and associated with mortality after non‐metastatic cancer. Automated methods will accelerate body composition research and, eventually, facilitate integration of body composition measures into clinical care.

Pixel-Level Classification of Pollution Severity on Insulators Using Photothermal Radiometry and Multiclass Semisupervised Support Vector Machine

Pollution flashover is a serious accident with a wide range of impacts in power grid. Accurate and timely classification of pollution severity is both a key to preventing pollution flashovers and a crucial challenge. This article proposes an innovative method based on photothermal radiometry (PTR) and multiclass semisupervised support vector machine for the classification of insulator pollution severity. The introduction of time-dimension information makes it possible to achieve pixel-level image identification instead of image- or region-level image identification. The PTR physical model for pollution severity measurement is established to determine the effect of pollution severity parameters such as the equivalent salt deposit density and the nonsoluble deposit density on the transient and frequency-domain thermal radiation characteristics of contamination layer. The relevant features are extracted by using principal component analysis. A semisupervised classifier is proposed to solve the problem of poor generalization due to insufficient labeled samples in industrial applications. Experimental results verify the satisfactory efficiency and accuracy of the proposed method and an estimation framework for fast, accurate, and nondestructive industrial application without the tedious work of labeling large amounts of data is concluded.

Image understanding via learning weakly-supervised cross-modal semantic translation

Fusing cross-modal features is significant for image understanding, which aims at describing objects inside an image by optimally combining multiple visual channels. In the literature, low-level based multimodal feature fusion have achieved impressive performance. However, the semantic gap is a big limitation, i.e., these methods cannot reflect the how humans perceive image semantic objects. Supervised learning-based methods require intolerably expensive manual labeling, which is not a good choice in practice. To alleviate these limitations, we present an image understanding method by learning weakly-supervised based cross-modal semantic translation. More specifically, we design a manifold embedding algorithm to automatically translate image-level text semantic labels into several pixel-level image regions. Subsequently, we leverage a three-level spatial pyramid model to extract both local and global features of objects from training images. Afterwards, these cross-modal features are seamlessly concatenated to form a multiple feature matrix. Afterwards, these cross-modal features are seamlessly concatenated to form a multiple feature matrix. The feature matrix can be employed to learn a kernel SVM and ranking SVM for image classification and retrieval respectively. Comprehensive experiments on image recognition, classification and retrieval have demonstrated the effectiveness of our method.

Weakly Supervised Conditional Random Fields Model for Semantic Segmentation with Image Patches

Image semantic segmentation (ISS) is used to segment an image into regions with differently labeled semantic category. Most of the existing ISS methods are based on fully supervised learning, which requires pixel-level labeling for training the model. As a result, it is often very time-consuming and labor-intensive, yet still subject to manual errors and subjective inconsistency. To tackle such difficulties, a weakly supervised ISS approach is proposed, in which the challenging problem of label inference from image-level to pixel-level will be particularly addressed, using image patches and conditional random fields (CRF). An improved simple linear iterative cluster (SLIC) algorithm is employed to extract superpixels. for image segmentation. Specifically, it generates various numbers of superpixels according to different images, which can be used to guide the process of image patch extraction based on the image-level labeled information. Based on the extracted image patches, the CRF model is constructed for inferring semantic class labels, which uses the potential energy function to map from the image-level to pixel-level image labels. Finally, patch based CRF (PBCRF) model is used to accomplish the weakly supervised ISS. Experiments conducted on two publicly available benchmark datasets, MSRC and PASCAL VOC 2012, have demonstrated that our proposed algorithm can yield very promising results compared to quite a few state-of-the-art ISS methods, including some deep learning-based models.

A new remote sensing image fusion method combining principal component analysis and curvelet transform

In the framework of multi-scale decomposition, a new multi-source image fusion algorithm based on principal component analysis (PCA) and curvelet transform is proposed for pixel-level image fusion. Firstly the low-resolution multi-spectral image is transformed by PCA and principal components are obtained. Secondly the high-resolution image and the first three principal components of the multi-spectral image are respectively merged with curvelet transform and finally the fused image is obtained by inverse PCA transform. This method gives the results of fusion and is compared with the traditional method of PCA, which proves the effectiveness of the method.

A Survey on Multi-Scale Medical images Fusion Techniques: Brain Diseases

Brain diseases such as degenerative (alzheimer's disease), neoplastic disease (brain tumor like sarcoma, glioma) are considered an interesting topic areas in the medical image fusion diagnosis. Pixel-level image fusion techniques are designed to combine multiple/multi-scale input images into a fused image, which is expected to be more informative for human or machine perception as compared to any of the input images. Since they are difficult to be summarized ; survey paper are characterized by (1) medical image definition , brain diseases challenges , analysis a various techniques for multi-scale image fusion with its own modalities, fusion rule, fusion strategy and dis-advantage ,Whilst used a database of medical images for medical Harvard School (brain diseases) which contains various groups of co-registered multi-modal images including MRI/CT, MRI/PET and PET/SPECT and MRI (T1/T2) images.

Object-Based Classification of PolSAR Images Based on Spatial and Semantic Features

High-resolution polarimatric synthetic aperture radar (PolSAR) images can provide more detail information on land-cover types and increase the image complexity at the same time. Traditionally, pixel-based image classification that takes image pixel as a processing unit cannot make full use of various features contained in high-resolution remote sensing images, and thus may not obtain satisfactory results. Hence, object-based image classification (OBIC) methods using image objects as processing units have been introduced into the PolSAR image classification. However, current researches on OBIC methods for PolSAR images usually could not take advantage of multiscale information of image objects, leading to some results that are not as satisfactory as expected. In this article, a multilevel image description consisting of proposed pixel-level spatial and object-level semantic features is developed for OBIC of PolSAR images. At the image pixel level, based on th combination of polarimetric and morphological image descriptions, polarimetric morphological profiles are developed to describe pixel-level spatial features. At the image object level, based on the construction of object adjacent graph, an object-level semantic indicator is proposed, which takes into account the contextual neighborhood of image objects. Finally, the proposed pixel-level spatial and object-level semantic features are integrated and incorporated in an OBIC scheme for the PolSAR image classification. Two fully polarized datasets acquired by ESAR and uninhabited airborne vehicle synthetic aperture radar (UAVSAR), respectively, are adopted to evaluate the effectiveness of the proposed method. The experimental results validate that the comprehensive utilization of both pixel-level and object-level features can effectively improve the OBIC accuracy of PolSAR images.

Restoration of Lossy JPEG-Compressed Brain MR Images Using Cross-Domain Neural Networks

Lossy image compression allows for efficient storage and transfer of image data with varying degrees of image degradation. However, lossy compression is not commonly used in medical imaging as the process may irreversibly remove information that defines clinically important image features. The lossy component of JPEG compression is represented as lost precision in the discrete cosine transform (DCT) domain after quantization on $8 \times 8$ image blocks and results in degradation of the image. We propose a cross-domain cascade of U-nets called the W-net. This network operates in the DCT domain to restore discarded DCT coefficients that leverages information from adjacent blocks, and the image domain to suppress compression artifacts at the image pixel level. For comparison, we adapted the Automated Transform by Manifold Approximation (AUTOMAP) method for JPEG decompression by learning the dequantization of individual $8 \times 8$ DCT coefficient blocks. These results were then transformed to the image domain and processed by a U-net. The deep learning models were able to suppress common compression artifacts at the expense of high spatial frequency detail. Both the W-net and AUTOMAP network structures were quantitatively superior to standard JPEG decompression, with the W-net outperforming AUTOMAP, suggesting that leveraging DCT coefficients from adjacent blocks improves JPEG decompression performance.

Pixel Level Image Fusion in Moving objection Detection and Tracking with Machine Learning

It is not feasible for a single image sensor to convey all of the information essential to comprehend a circumstance thoroughly. The output of many image sensors combined in one place would supply more accurate or comprehensive information on the topic at hand. In recent years, multi-sensor fusion has emerged in the academic world as an emerging topic that has the potential to produce beneficial results. This is because it can aggregate the data from several different sensors. One of the primary objectives is to devise various methods for combining kinematic and visual data to track a moving object. These methods should allow us to achieve this aim. This article looks into the intricacies of various techniques to evaluate the current condition of a target and explores the outcomes of those approaches. These sorts of methods include, for instance, the Kalman filter and its expanded version, the extended Kalman filter. The study of the proposed work is to demonstrate the specifics of the development of an interacting multiple-model Kalman filter to monitor the performance of the moving target in response to a wide variety of tuning parameters. The proposed technique includes the Principal Component Analysis and spatial frequency to integrate the hazy images that were all shot with the same sensor modalities. This action was taken to achieve the aimed-for outcome. The effectiveness of the fusion is evaluated based on the results of several distinct metrics.

A Fast Chaotic Image Encryption Scheme With Simultaneous Permutation-Diffusion Operation

In this paper, a secure and fast chaotic image encryption scheme with simultaneous permutation-diffusion operation is proposed. We combine permutation and diffusion processes into a whole, namely, simultaneous permutation and diffusion operation (SPDO). This can solve the problem of traditional encryption scheme in which the permutation and diffusion are two independent processes, that leads attackers to crack the two processes separately. In SPDO, the initial value of the current Sine-Sine chaotic map is related to the secret keys and the previous encrypted pixels’ values. In this case, the proposed scheme can generate dynamic key streams and indexes that are related to plaintext, which improves the sensitivity to plaintext for the encryption scheme. In addition, the pixel values are processed by row and column (row-level and column-level) during the encryption procedure. Thus, the proposed scheme presents lower time complexity and faster running speed compared with bit-level or pixel-level image encryption schemes, which makes the proposed scheme be conducive to the batch transmission and real-time transmission of digital images. The simulation results and security analysis show that our scheme can resist common attacks, such as statistical attack, differential attack, chosen plaintext attack and other comprehensive attacks.

Joint image compression and encryption based on sparse Bayesian learning and bit-level 3D Arnold cat maps.

Image compression and image encryption are two essential tasks in image processing. The former aims to reduce the cost for storage or transmission of images while the latter aims to change the positions or values of pixels to protect image content. Nowadays, an increasing number of researchers are focusing on the combination of these two tasks. In this paper, we propose a novel joint image compression and encryption approach that integrates a quantum chaotic system, sparse Bayesian learning (SBL) and a bit-level 3D Arnold cat map, so-called QSBLA, for such a purpose. Specifically, the QSBLA consists of 6 stages. First, a quantum chaotic system is employed to generate chaotic sequences for subsequent compression and encryption. Second, as one method of compressive sensing, SBL is used to compress images. Third, an operation of diffusion is performed on the compressed image. Fourth, the compressed and diffused image is transformed into several bit-level cubes. Fifth, 3D Arnold cat maps are used to permute each bit-level cube. Finally, all the bit-level cubes are integrated and transformed into a 2D pixel-level image, resulting in the compressed and encrypted image. Extensive experiments on 8 publicly-accessed images demonstrate that the proposed QSBLA is superior or comparable to some state-of-the-art approaches in terms of several measurement indices, indicating that the QSBLA is promising for joint image compression and encryption.

A Novel Adaptive PET/CT Image Fusion Algorithm

Background: Lung cancer is one of the common malignant tumors. The successful diagnosis of lung cancer depends on the accuracy of the image obtained from medical imaging modalities. Objective: The fusion of CT and PET is combining the complimentary and redundant information both images and can increase the ease of perception. Since the existing fusion method sare not perfect enough, and the fusion effect remains to be improved, the paper proposes a novel method called adaptive PET/CT fusion for lung cancer in Piella framework. Methods: This algorithm firstly adopted the DTCWT to decompose the PET and CT images into different components, respectively. In accordance with the characteristics of low-frequency and high-frequency components and the features of PET and CT image, 5 membership functions are used as a combination method so as to determine the fusion weight for low-frequency components. In order to fuse different high-frequency components, we select the energy difference of decomposition coefficients as the match measure, and the local energy as the activity measure; in addition, the decision factor is also determined for the high-frequency components. Results: The proposed method is compared with some of the pixel-level spatial domain image fusion algorithms. The experimental results show that our proposed algorithm is feasible and effective. Conclusion: Our proposed algorithm can better retain and protrude the lesions edge information and the texture information of lesions in the image fusion.