Features Of Original Image Research Articles

Research on Image Texture Feature Extraction Based on Digital Twin

The purpose of image smoothing is to improve the visual effect of the image and improve the clarity of the image, so as to make the image more conducive to computer processing and various feature analysis. Because the current technology fails to smooth the preprocessed image, it leads to the extraction of image texture features. The anti-interference performance is weak. For this reason, an image texture feature extraction technology based on the digital twin is proposed. Similarity analysis is carried out through the internal structure of the image, and the image is smoothed by the semisupervised learning method. On the basis of optimizing the denoised image through digital twinning, detect target feature points in the original image, then remove the abnormal and split feature points, assign the direction of image texture feature points, and build a fuzzy back propagation neural network model. Image texture feature extraction technology is implemented. The experimental results show that, compared with the traditional method, the proposed technique has a strong identification of original image features, and has a strong consistency with original data, and has a strong ability to resist the influence of abnormal data, noise, or redundant feature points.

Convex optimization for additive noise reduction in quantitative complex object wave retrieval using compressive off-axis digital holographic imaging

Abstract Image denoising is one of the important problems in the research field of computer vision, artificial intelligence, 3D vision, and image processing, where the fundamental aim is to recover the original image features from a noisy contaminated image. The camera sensor additive noise present in the holographic recording process reduces the quality of the retrieved image. Even though various techniques have been developed to minimize the noise in digital holography, the noise reduction still remains a challenging task. This article presents a compressive sensing (CS) technique to minimize the additive noise in the digital holographic reconstruction process. We demonstrate the reduction of additive noise using complex wave retrieval method as a sensing matrix in the CS model. The proposed CS method to suppress the noise during the reconstruction process is illustrated using numerical simulations. Only 50% of the pixel measurements are considered in the noisy hologram, which is far less than the original complex object pixels. The impact of additive gaussian noise in the recording plane on the reconstruction accuracy of both intensity and phase distribution is analysed. The CS method denoises and estimates the complex object information accurately. The numerical simulation results have shown that the proposed CS method has effectively minimized the noise in the reconstructed image and has greatly improved the quality of both intensity and phase information.

Extraction of soybean planting area based on feature fusion technology of multi-source low altitude unmanned aerial vehicle images

Soybean is an important food and oil crop in the world. It is of great significance to statics the planting scale accurately for optimizing the crop planting structure and world food security. The technology of accurately extracting the area of soybean planting areas at the field scale using UAV images combined with deep learning algorithms is important for the application. In this study, firstly, RGB images and multispectral images (RGN) were acquired simultaneously by the quad-rotor UAV DJ-Phantom4 Pro at a flying height of 200 m. And the features were extracted from the RGB and RGN images. Further, the fusion image of RGB + VIs and the fusion image of RGN + VIs were obtained by concatenating the band reflectivity of the original image with the calculated Vegetation Index (VI). Then, the soybean planting area was segmented from the feature fusion images by U-Net. And the accuracy of the two sensors was compared. The results showed that the Kappa coefficients obtained based on RGB image, RGN image, CME(the combination of CIVE, MExG, and ExGR), ODR(the combination of OSAVI, DVI, and RDVI), RGB + CME(the combination of RGB and CME), and RGN + ODR(the combination of RGN and ODR) were 0.8806, 0.9327, 0.8437, 0.9330, 0.9420, and 0.9238, respectively. The Kappa coefficient of the combination of the original image and the vegetation index was higher than the original image, indicating that the vegetation index calculation was beneficial to improving the soybean recognition accuracy of the U-Net model. Among them, the precision of the soybean planting area extracted from RGB + CME was the highest, and the Kappa coefficient was 0.9420. Finally, the soybean recognition accuracy of U-Net was compared with the results of DeepLabv3+, Random Forest, and Support Vector Machine. The accuracy of U-Net was the best. It can be concluded that this research proposed the method that was using U-Net trained the fusion image of the original image and vegetation index feature fusion image obtained by the UAV platform, which can effectively segment soybean planting areas. The conclusion of this work provided important technical support for farm level, family cooperatives, and other business entities to manage finely soybean planting and production at low cost.

An Integrated Change Detection Method Based on Spectral Unmixing and the CNN for Hyperspectral Imagery

Hyperspectral remote sensing image (HSI) include rich spectral information that can be very beneficial for change detection (CD) technology. Due to the existence of many mixed pixels, pixel-wise approaches can lead to considerable errors in the resulting CD map. The spectral unmixing (SU) method is a potential solution to this problem, as it decomposes mixed pixels into a set of fractions of land cover. Subsequently, the CD map is created by comparing the abundance images. However, based only on the abundance images created through the SU method, they are unable to effectively provide detailed change information. Meanwhile, the features of change information cannot be sufficiently extracted by the traditional sub-pixel CD framework, which leads to a poor CD result. To address these problems, this paper presents an integrated CD method based on multi-endmember spectral unmixing, joint matrix and CNN (MSUJMC) for HSI. Three main steps are considered to accomplish this task. First, considering the endmember spectral variability, more reliable endmember abundance information is obtained by multi-endmember spectral unmixing (MSU). Second, the original image features are incorporated with the abundance images using a joint matrix (JM) algorithm to provide more temporal and spatial land cover change information characteristics. Third, to efficiently extract the change features and to better handle the fused multi-source information, the convolutional neural network (CNN) is introduced to realize a high-accuracy CD result. The proposed method has been verified on simulated and real multitemporal HSI datasets, which provide multiple changes. Experimental results verify the effectiveness of the proposed approach.

A domain adaptation neural network for change detection with heterogeneous optical and SAR remote sensing images

• A novel pseudo-Siamese network for heterogeneous satellite image change detection is proposed. • A domain adaptation constraint block is proposed to implicitly align the heterogeneous deep features. • Attention-regulated feature refinement improves change map reconstruction. • A large heterogeneous SAR and optical remote sensing change detection dataset is newly created. • Experiments on scenarios of flooding and urban development demonstrate the improved performance of the proposed network. Heterogeneous remote sensing source-based change detection with optical and SAR data and their combined all-time and all-weather observation capability provides a reliable and promising solution for a wide range of applications. State-of-the-art supervised methods typically take a two-stage strategy that suffers from the loss of original image features and the introduction of noise on the transferred images. This paper proposes a domain adaptation-based multi-source change detection network (DA-MSCDNet) suitable to process heterogeneous optical and SAR images. DA-MSCDNet employs feature-level transformation to align inconsistent deep feature spaces in heterogeneous data. Feature space transformation and change detection are bridged within the network to encourage task communication. Experiments are conducted on two public datasets based on Sentinel-1A and Landsat-8 imagery acquired over the Sacramento, Yuba, and Sutter Counties (California, USA), and QuickBird-2 and TerraSAR-X imagery over Gloucester (UK), as well as one new large-scale dataset of Sentinel-2 and COSMO-SkyMed imagery over Wuhan (China). Compared with other six supervised and unsupervised approaches, the proposed method achieves the highest performance with an average precision of 80.81%, recall of 84.39%, mIOU of 73.67% and F1 score of 82.58%, beating the state-of-the-art method with 5.42% improvements on F1 score and 10 times efficiency on training time cost on the large-scale change detection task.

Fusing Multimodal and Anatomical Volumes of Interest Features Using Convolutional Auto-Encoder and Convolutional Neural Networks for Alzheimer's Disease Diagnosis.

Alzheimer’s disease (AD) is an age-related disease that affects a large proportion of the elderly. Currently, the neuroimaging techniques [e.g., magnetic resonance imaging (MRI) and positron emission tomography (PET)] are promising modalities for AD diagnosis. Since not all brain regions are affected by AD, a common technique is to study some region-of-interests (ROIs) that are believed to be closely related to AD. Conventional methods used ROIs, identified by the handcrafted features through Automated Anatomical Labeling (AAL) atlas rather than utilizing the original images which may induce missing informative features. In addition, they learned their framework based on the discriminative patches instead of full images for AD diagnosis in multistage learning scheme. In this paper, we integrate the original image features from MRI and PET with their ROIs features in one learning process. Furthermore, we use the ROIs features for forcing the network to focus on the regions that is highly related to AD and hence, the performance of the AD diagnosis can be improved. Specifically, we first obtain the ROIs features from the AAL, then we register every ROI with its corresponding region of the original image to get a synthetic image for each modality of every subject. Then, we employ the convolutional auto-encoder network for learning the synthetic image features and the convolutional neural network (CNN) for learning the original image features. Meanwhile, we concatenate the features from both networks after each convolution layer. Finally, the highly learned features from the MRI and PET are concatenated for brain disease classification. Experiments are carried out on the ADNI datasets including ADNI-1 and ADNI-2 to evaluate our method performance. Our method demonstrates a higher performance in brain disease classification than the recent studies.

Research on facial expression recognition based on an improved fusion algorithm

Abstract This article puts forward a facial expression recognition (FER) algorithm based on multi-feature fusion and convolutional neural network (CNN) to solve the problem that FER is susceptible to interference factors such as non-uniform illumination, thereby reducing the recognition rate of facial expressions. It starts by extracting the multi-layer representation information (asymmetric region local binary pattern [AR-LBP]) of facial expression images and cascading them to minimize the loss of facial expression texture information. In addition, an improved algorithm called divided local directional pattern (DLDP) is used to extract the original facial expression image features, which not only retains the original texture information but also reduces the time consumption. With a weighted fusion of the features extracted from the above two facial expressions, new AR-LBP-DLDP facial local features are then obtained. Later, CNN is used to extract global features of facial expressions, and the local features of AR-LBP-DLDP obtained by weighted fusion are cascaded and fused with the global features extracted by the CNN, thereby producing the final facial expression features. Ultimately, the final facial expression features are input into Softmax for training and classification. The results show that the proposed algorithm, with good robustness and real-time performance, effectively improves the recognition rate of facial expressions.

Cascaded context enhancement network for automatic skin lesion segmentation

Skin lesion segmentation is an important step for automatic melanoma diagnosis. Due to the non-negligible diversity of lesions from different patients, extracting powerful context for fine-grained semantic segmentation is still challenging today. Although the deep convolutional neural networks (CNNs) have made significant improvements on skin lesion segmentation, they often fail to reserve the spatial details and long-range dependencies context due to consecutive convolution striding and pooling operations inside CNNs. In this paper, we formulate a cascaded context enhancement neural network for automatic skin lesion segmentation. A new cascaded context aggregation (CCA) module with a gate-based information integration approach is proposed to sequentially and selectively aggregate original image and multi-level features from the encoder sub-network. The generated context is further utilized to guide discriminative features extraction by the designed context-guided local affinity (CGL) module. Furthermore, an auxiliary loss is added to the CCA module for refining the prediction. In our work, we evaluate our approach on four public skin dermoscopy image datasets. The proposed method achieves the Jaccard Index (JA) of 87.1%, 80.3%, 84.3%, and 86.6% on ISIC-2016, ISIC-2017, ISIC-2018, and PH2 datasets, which show highly competitive performance with other state-of-the-art models respectively.

A Novel High-Resolution Fingerprint Representation Method

Current high-resolution fingerprints are almost entirely represented by sweat pores, resulting in information loss and weak robustness. This is caused by dividing fingerprint representation into pore detection and pore representation. This paper proposes a novel high-resolution fingerprint representation method for recognition based on only one fully convolutional network. By guiding the network to learn the most discriminative representation (i.e., sweat pores) and to reconstruct the original fingerprint image, pore maps and hidden features are provided simultaneously to represent the high-resolution fingerprint image for the subsequent direct matching process. The experimental results, which are evaluated on the public PolyU pore database, show that the best average <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$R_{T}$ </tex-math></inline-formula> , which is 94.88%, can be obtained using our proposed method. In addition, the recognition results show that our proposed method achieves matching equal error rates (EERs) of 5.55% and 1.27% on the PolyU DBI and DBII databases, respectively, which is better than other pore detection methods when using the same matching method. Compared with the latest DeepPoreID method which split fingerprint representation into pore extraction and pore representation, our approach improves the EER by up to 50.98% when evaluated on an in-house database, further demonstrating the outstanding generalization ability of the proposed method.

MMPCANet: An Improved PCANet for Occluded Face Recognition

Principal Component Analysis Network (PCANet) is a lightweight deep learning network, which is fast and effective in face recognition. However, the accuracy of faces with occlusion does not meet the optimal requirement for two reasons: 1. PCANet needs to stretch the two-dimensional images into column vectors, which causes the loss of essential image spatial information; 2. When the training samples are few, the recognition accuracy of PCANet is low. To solve the above problems, this paper proposes a multi-scale and multi-layer feature fusion-based PCANet (MMPCANet) for occluded face recognition. Firstly, a channel-wise concatenation of the original image features and the output features of the first layer is conducted, and then the concatenated result is used as the input of the second layer; therefore, more image feature information is used. In addition, to avoid the loss of image spatial information, a spatial pyramid is used as the feature pooling layer of the network. Finally, the feature vector is sent to the random forest classifier for classification. The proposed algorithm is tested on several widely used facial image databases and compared with other similar algorithms. Our experimental results show that the proposed algorithm effectively improves the efficiency of the network training and the recognition accuracy of occluded faces under the same training and testing datasets. The average accuracies are 98.78% on CelebA, 97.58% on AR, and 97.15% on FERET.

Effect of Land-Use Change on Runoff in Hyrcania

Population growth and human activities have resulted in drastic changes in land use in many areas of the world, including the Hyrcania region in northern Iran. Land-use changes affect the hydrological processes of water basins. This study evaluated the effect of land-use changes on runoff over 15 years in the Haraz River basin located in Hyrcania using remote sensing data and GIS analyses. The annual precipitation of the region is 66.5 cm. Two Landsat images were used to develop land-use maps for 1996 and 2011. Original image features, their principal components, and vegetation indices were used to classify the two Landsat images into different land-use categories. Runoff was predicted from precipitation, land use, and hydrological soil groups, using the SCS-CN model (the “curve number” approach). During the 15 years, 62.4% of the area remained unchanged and 37.6% had undergone a land-use change. The highest average runoffs were obtained for bare land (14.1–14.5 cm/year) and residential land (10.4–11.4 cm/year), and the lowest for dense forest (2.5–2.6 cm/year) and first-grade rangeland (2.8–3.1 cm/year). The volume of annual runoff increased by 9% during 1996–2011 due to land-use changes. Runoff was estimated at 9.4% of precipitation in 1996, and 9.6% of precipitation in 2011. Most of the increase was related to the increased area of bare land and decreased area of rangeland. The study indicated that combined use of the SCS-CN approach, remote sensing data, and GIS tools allow cost-effective runoff estimation, helping watershed management. The results on the effect of land-use change on runoff can be seen as a warning for land-use managers and policymakers, who should aim at stopping and reversing the current land-use trends of the Haraz River basin.

Citrus Huanglongbing Recognition Algorithm Based on CKMOPSO

In view of the similarity of characteristics between the features of the disease images and the large dimension, and the features correlation of the disease images, this will lead to the generation of feature redundancy, and will introduce a serious impact on the recognition efficiency and accuracy of citrus Huanglongbing. In addition, they have the defects of high cost of detection algorithms and low detection accuracy. This will occur in the image cutting feature extraction stage, so this paper uses the citrus Huanglongbing recognition algorithm based on kriging model simplex crossover local based search Multi-objective particle swarm optimization algorithm(CKMOPSO) selects feature vectors with strong classification capabilities from the original disease image features, experimental results show that this is an effective recognition method.

An Automatic Optic Disk Segmentation Approach from Retina of Neonates via Attention Based Deep Network

Every year, many newborns lose their sight to retinopathy of prematurity (ROP) worldwide. Despite its high prevalence and adverse consequences, periodic examinations can effectively prevent it. The use of an intelligent system enables physicians to avoid medical mistakes while examining newborns. The optic disk (OD) is an integral part of the retina for grading the severity and progression of ROP. Due to the uneven brightness and lack of a defined OD border, the use of retinal images of infants is very challenging for OD diagnosis. This paper provides an innovative model of OD segmentation based on attention gate. Initially, the images were collected and preprocessed and inputted into a novel deep convolutional neural network consisting of attention in skip connections. The architecture is comprised of a two-stage convolutional network. Different outputs are obtained from two individual branches of the original image and image features in the first stage. The outputs were concatenated to transfer into the post-processing stage to identify the area related to the OD. The final results based on the Dice coefficient (Dice) and the Intersection-Over-Union (IoU) were 94.22% and 86.1%, respectively.

DenseHashNet: A Novel Deep Hashing for Medical Image Retrieval

With the wide application of imaging modalities such as X-ray and Computed Tomography (CT) in clinical practice, Content-based Medical Image Retrieval (CBMIR) has become a current research hotspot. Related studies have shown that hash-based image retrieval algorithms can retrieve relevant images faster and more accurately than traditional image retrieval methods. Therefore, in this paper, we propose a novel deep hashing method for medical image retrieval, called DenseHashNet. Specifically, we first use DenseNet to extract the original image features, and introduce the Spatial Pyramid Pooling (SPP) layer after the last Dense Block so that features at different scales can be extracted and multi-scale features fused with information from multiple regions. Then, the output of the SPP layer is subjected to Power-Mean Transformation (PMT) operation to enhance the nonlinearity of the model and improve the performance of the model. Finally, we map the output of PMT to hash codes through fully connected layers. Experimental results show that our method achieves better performance, compared with some representative methods.

A Position-Aware Transformer for Image Captioning

Image captioning aims to generate a corresponding description of an image. In recent years, neural encoder-decoder models have been the dominant approaches, in which the Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) are used to translate an image into a natural language description. Among these approaches, the visual attention mechanisms are widely used to enable deeper image understanding through fine-grained analysis and even multiple steps of reasoning. However, most conventional visual attention mechanisms are based on high-level image features, ignoring the effects of other image features, and giving insufficient consideration to the relative positions between image features. In this work, we propose a Position-Aware Transformer model with image-feature attention and position-aware attention mechanisms for the above problems. The image-feature attention firstly extracts multi-level features by using Feature Pyramid Network (FPN), then utilizes the scaled-dot-product to fuse these features, which enables our model to detect objects of different scales in the image more effectively without increasing parameters. In the position-aware attention mechanism, the relative positions between image features are obtained at first, afterwards the relative positions are incorporated into the original image features to generate captions more accurately. Experiments are carried out on the MSCOCO dataset and our approach achieves competitive BLEU-4, METEOR, ROUGE-L, CIDEr scores compared with some state-of-the-art approaches, demonstrating the effectiveness of our approach.

DCT Coefficients Weighting (DCTCW)-Based Gray Wolf Optimization (GWO) for Brightness Preserving Image Contrast Enhancement

Image contrast enhancement (CE) is a frequent image enhancement requirement in diverse applications. Histogram equalization (HE), in its conventional and different further improved ways, is a popular technique to enhance the image contrast. The conventional as well as many of the later versions of HE algorithms often cause loss of original image characteristics particularly brightness distribution of original image that results artificial appearance and feature loss in the enhanced image. Discrete Cosine Transform (DCT) coefficient mapping is one of the recent methods to minimize such problems while enhancing the image contrast. Tuning of DCT parameters plays a crucial role towards avoiding the saturations of pixel values. Optimization can be a possible solution to address this problem and generate contrast enhanced image preserving the desired original image characteristics. Biological behavior-inspired optimization techniques have shown remarkable betterment over conventional optimization techniques in different complex engineering problems. Gray wolf optimization (GWO) is a comparatively new algorithm in this domain that has shown promising potential. The objective function has been formulated using different parameters to retain original image characteristics. The objective evaluation against CEF, PCQI, FSIM, BRISQUE and NIQE with test images from three standard databases, namely, SIPI, TID and CSIQ shows that the presented method can result in values up to 1.4, 1.4, 0.94, 19 and 4.18, respectively, for the stated metrics which are competitive to the reported conventional and improved techniques. This paper can be considered a first-time application of GWO towards DCT-based image CE.

АЛГОРИТМ ПРЕДВАРИТЕЛЬНОЙ ОБРАБОТКИ ВИДЕОИЗОБРАЖЕНИЙ ДЛЯ ПОВЫШЕНИЯ ТОЧНОСТИ ОБНАРУЖЕНИЯ МАЛОРАЗМЕРНЫХ ОБРАЗОВ

Recognition of certain patterns in video images captured by a camera is carried out usingtraining methods based on convolutional neural networks. The larger the number of images withmultiple features and the more diverse the training sample of video images, the better the convolutionalneural networks extract features from the sequence of video images that were not included inthe training sample. This is a consequence of increasing the accuracy of detecting visual images onvideo images containing features of target images. However, there are limitations in improving thedetection performance when the size of the image to be detected is much smaller than the backgroundarea, or when the image is described with little information. To solve problems of this kind, the authorsof the article have developed an algorithm for the spatio-temporal integration of informationabout the movement of dynamic images. The algorithm processes a fixed number of video images atcertain points in time and extracts new independent signs of motion of dynamic images based onspace-time processing of video images. Further, it combines new local motion features with the originalvideo image features. This allows you to add a motion feature of dynamic images while preservingthe original image features that describe static images. Areas of the video image that characterizethe motion feature are displayed in a «color» cluster. The use of pre-processing is aimed at improving the accuracy of pattern detection, provided there are dynamic visual images on a static background.If the camera is in scan mode, a static background can be provided with a video stabilizer.Experimentally, estimates of integral criteria for the accuracy of detection neural network algorithmshave been obtained, showing an increase in the accuracy of detecting visual images usingthe algorithm for spatial-temporal integration of motion information.

Underexposed Vision-Based Sensors’ Image Enhancement for Feature Identification in Close-Range Photogrammetry and Structural Health Monitoring

This paper describes an alternative structural health monitoring (SHM) framework for low-light settings or dark environments using underexposed images from vision-based sensors based on the practical implementation of image enhancement algorithms. The proposed framework was validated by two experimental works monitored by two vision systems under ambient lights without assistance from additional lightings. The first experiment monitored six artificial templates attached to a sliding bar that was displaced by a standard one-inch steel block. The effect of image enhancement in the feature identification and bundle adjustment integrated into the close-range photogrammetry were evaluated. The second validation was from a seismic shake table test of a full-scale three-story building tested at E-Defense in Japan. Overall, this study demonstrated the efficiency and robustness of the proposed image enhancement framework in (i) modifying the original image characteristics so the feature identification algorithm is capable of accurately detecting, locating and registering the existing features on the object; (ii) integrating the identified features into the automatic bundle adjustment in the close-range photogrammetry process; and (iii) assessing the measurement of identified features in static and dynamic SHM, and in structural system identification, with high accuracy.

IAS-NET: Joint intraclassly adaptive GAN and segmentation network for unsupervised cross-domain in neonatal brain MRI segmentation.

In neonatal brain magnetic resonance image (MRI) segmentation, the model we trained on the training set (source domain) often performs poorly in clinical practice (target domain). As the label of target-domain images is unavailable, this cross-domain segmentation needs unsupervised domain adaptation (UDA) to make the model adapt to the target domain. However, the shape and intensity distribution of neonatal brain MRI images across the domains are largely different from adults'. Current UDA methods aim to make synthesized images similar to the target domain as a whole. But it is impossible to synthesize images with intraclass similarity because of the regional misalignment caused by the cross-domain difference. This will result in generating intraclassly incorrect intensity information from target-domain images. To address this issue, we propose an IAS-NET (joint intraclassly adaptive generative adversarial network (GAN) (IA-NET) and segmentation) framework to bridge the gap between the two domains for intraclassalignment. Our proposed IAS-NET is an elegant learning framework that transfers the appearance of images across the domains from both image and feature perspectives. It consists of the proposed IA-NET and a segmentation network (S-NET). The proposed IA-NET is a GAN-based adaptive network that contains one generator (including two encoders and one shared decoder) and four discriminators for cross-domain transfer. The two encoders are implemented to extract original image, mean, and variance features from source and target domains. The proposed local adaptive instance normalization algorithm is used to perform intraclass feature alignment to the target domain in the feature-map level. S-NET is a U-net structure network that is used to provide semantic constraint by a segmentation loss for the training of IA-NET. Meanwhile, it offers pseudo-label images for calculating intraclass features of the target domain. Source code (in Tensorflow) is available at https://github.com/lb-whu/RAS-NET/. Extensive experiments are carried out on two different data sets (NeoBrainS12 and dHCP), respectively. There exist great differences in the shape, size, and intensity distribution of magnetic resonance (MR) images in the two databases. Compared to baseline, we improve the average dice score of all tissues on NeoBrains12 by 6% through adaptive training with unlabeled dHCP images. Besides, we also conduct experiments on dHCP and improved the average dice score by 4%. The quantitative analysis of the mean and variance of the synthesized images shows that the synthesized image by the proposed is closer to the target domain both in the full brain or within each class than that of the comparedmethods. In this paper, the proposed IAS-NET can improve the performance of the S-NET effectively by its intraclass feature alignment in the target domain. Compared to the current UDA methods, the synthesized images by IAS-NET are more intraclassly similar to the target domain for neonatal brain MR images. Therefore, it achieves state-of-the-art results in the compared UDA models for the segmentation task.

A Novel Steganography Scheme for Color Image Based on HLS Translation

In recent years, steganography has attracted extensive attention, but most of steganography schemes are aimed at grayscale images. Therefore, a novel steganography scheme for color image based on HLS translation is proposed in this paper. Firstly, the color cover image is decomposed from RGB three channels to HLS three channels. Then the image of H channel is selected as the cover image for embedding secret information due to its texture feature of original image. The universal distortion function UNIWARD is utilized to embed the secret information into the image of H channel. Finally, the steg image transmitted in common channel is obtained by inverse HLS transform using the single channel image embedding the secret information. The extensive experimental results indicate that our scheme has high security and can also resist the detection of steganalysis schemes based on CNN.