Original Image Research Articles

Magnifying Networks for Histopathological Images with Billions of Pixels.

Amongst the other benefits conferred by the shift from traditional to digital pathology is the potential to use machine learning for diagnosis, prognosis, and personalization. A major challenge in the realization of this potential emerges from the extremely large size of digitized images, which are often in excess of 100,000 × 100,000 pixels. In this paper, we tackle this challenge head-on by diverging from the existing approaches in the literature-which rely on the splitting of the original images into small patches-and introducing magnifying networks (MagNets). By using an attention mechanism, MagNets identify the regions of the gigapixel image that benefit from an analysis on a finer scale. This process is repeated, resulting in an attention-driven coarse-to-fine analysis of only a small portion of the information contained in the original whole-slide images. Importantly, this is achieved using minimal ground truth annotation, namely, using only global, slide-level labels. The results from our tests on the publicly available Camelyon16 and Camelyon17 datasets demonstrate the effectiveness of MagNets-as well as the proposed optimization framework-in the task of whole-slide image classification. Importantly, MagNets process at least five times fewer patches from each whole-slide image than any of the existing end-to-end approaches.

Clothing image attribute editing based on generative adversarial network, with reference to an upper garment

PurposeNowadays, artificial intelligence (AI) technology has demonstrated extensive applications in the field of art design. Attribute editing is an important means to realize clothing style and color design via computer language, which aims to edit and control the garment image based on the specified target attributes while preserving other details from the original image. The current image attribute editing model often generates images containing missing or redundant attributes. To address the problem, this paper aims for a novel design method utilizing the Fashion-attribute generative adversarial network (AttGAN) model was proposed for image attribute editing specifically tailored to women’s blouses.Design/methodology/approachThe proposed design method primarily focuses on optimizing the feature extraction network and loss function. To enhance the feature extraction capability of the model, an increase in the number of layers in the feature extraction network was implemented, and the structure similarity index measure (SSIM) loss function was employed to ensure the independent attributes of the original image were consistent. The characteristic-preserving virtual try-on network (CP_VTON) dataset was used for train-ing to enable the editing of sleeve length and color specifically for women’s blouse.FindingsThe experimental results demonstrate that the optimization model’s generated outputs have significantly reduced problems related to missing attributes or visual redundancy. Through a comparative analysis of the numerical changes in the SSIM and peak signal-to-noise ratio (PSNR) before and after the model refinement, it was observed that the improved SSIM increased substantially by 27.4%, and the PSNR increased by 2.8%, serving as empirical evidence of the effectiveness of incorporating the SSIM loss function.Originality/valueThe proposed algorithm provides a promising tool for precise image editing of women’s blouses based on the GAN. This introduces a new approach to eliminate semantic expression errors in image editing, thereby contributing to the development of AI in clothing design.

The EDGE-CALIFA Survey: An Extragalactic Database for Galaxy Evolution Studies

The EDGE-CALIFA survey provides spatially resolved optical integral-field unit and CO spectroscopy for 125 galaxies selected from the Calar Alto Legacy Integral Field Area Survey (CALIFA) Data Release 3 sample. The Extragalactic Database for Galaxy Evolution (EDGE) presents the spatially resolved products of the survey as pixel tables that reduce the oversampling in the original images and facilitate comparison of pixels from different images. By joining these pixel tables to lower-dimensional tables that provide radial profiles, integrated spectra, or global properties, it is possible to investigate the dependence of local conditions on large-scale properties. The database is freely accessible and has been utilized in several publications. We illustrate the use of this database and highlight the effects of CO upper limits on the inferred slopes of the local scaling relations between the stellar mass, star formation rate (SFR), and H2 surface densities. We find that the correlation between H2 and SFR surface density is the tightest among the three relations.

Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques

Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate cancer diagnosis. Stain variation between hospitals hampers the performance of CBHIR tools. This paper explores the effects of color normalization (CN) in a recently proposed CBHIR approach to tackle this issue. In this paper, three different CN techniques were used on the CAMELYON17 (CAM17) data set, which is a breast cancer data set. CAM17 consists of images taken using different staining protocols and scanners in five hospitals. Our experiments reveal that a proper CN technique, which can transfer the color version into the most similar median values, has a positive impact on the retrieval performance of the proposed CBHIR framework. According to the obtained results, using CN as a pre-processing step can improve the accuracy of the proposed CBHIR framework to 97% (a 14% increase), compared to working with the original images.

Galaxy morphology classification based on Convolutional vision Transformer (CvT)

Context. The classification of galaxy morphology is among the most active fields in astronomical research today. With the development of artificial intelligence technology, deep learning is a useful tool in the classification of the morphology of galaxies and significant progress has been made in this domain. However, there is still some room for improvement in terms of classification accuracy, automation, and related issues. Aims. Convolutional vision Transformer (CvT) is an improved version of the Vision Transformer (ViT) model. It improves the performance of the ViT model by introducing a convolutional neural network (CNN). This study explores the performance of the CvT model in the area of galaxy morphology classification. Methods. In this work, the CvT model was applied, for the first time, in a five-class classification task of galaxy morphology. We added different types and degrees of noise to the original galaxy images to verify that the CvT model achieves good classification performance, even in galaxy images with low signal-to-noise ratios (S/Ns). Then, we also validated the classification performance of the CvT model for galaxy images at different redshifts based on the low-redshift dataset GZ2 and the high-redshift dataset Galaxy Zoo CANDELS. In addition, we visualized and analyzed the classification results of the CvT model based on the t-distributed stochastic neighborhood -embedding (t-SNE) algorithm. Results. We find that (1) compared with other five-class classification models of galaxy morphology based on CNN models, the average accuracy, precision, recall, and F1_score evaluation metrics of the CvT classification model are all higher than 98%, which is an improvement of at least 1% compared with those based on CNNs; (2) the classification visualization results show that different categories of galaxies are separated from each other in multi-dimensional space. Conclusions. The application of the CvT model to the classification study of galaxy morphology is a novel undertaking that carries important implications for future studies.

Improving noise characteristics using a modified image pyramid with guided filtering and Bayesian shrinkage threshold in low-dose animal radiography

Radiography is a commonly used diagnostic tool in animal practice to provide clinical information. The recent market for animal radiography is rapidly growing owing to the increasing awareness of the welfare of companion animals and the expansion of animal clinics. As the clinical use of radiography in animal hospitals has grown rapidly, radiologists continuously seek ways to reduce the radiation dose to animals. This study proposes an effective noise removal method using a modified image pyramid with guided filtering and Bayesian shrinkage threshold for low-dose animal radiography. This study aims to model a modified image pyramid-based denoising algorithm and to confirm its applicability in an animal radiographic system. We conducted an experiment on a companion dog and cat using a commercially-available veterinary radiographic system and quantitatively evaluated the image quality using the peak signal-to-noise ratio (PSNR) and structural similarity (SSIM). The PSNR and SSIM values measured in the denoised image of the dog using the proposed denoising algorithm were 39.54 and 0.96, respectively, which are improvements of approximately 11.3% and 5.5% of the values obtained in the original noisy image. Consequently, the proposed method is highly efficient in reducing image noise in animal radiography, thereby improving the image quality.

Enhance or Leave It: An Investigation of the Image Enhancement in Small Object Detection in Aerial Images

Recent years of object detection (OD), a fundamental task in computer vision, have witnessed the rise of numerous practical applications of this sub-field such as face detection, self-driving, security, and more. Although existing deep learning models show significant achievement in object detection, they are usually tested on datasets having mostly clean images. Thus, their performance levels were not measured on degraded images. In addition, images and videos in real-world scenarios often involve several natural artifacts such as noise, haze, rain, dust, and motion blur due to several factors such as insufficient light, atmospheric scattering, and faults in image sensors. This image acquisition-related problem becomes more severe when it comes to detecting small objects in aerial images. In this study, we investigate the small object identification performance of several state-of-the-art object detection models (Yolo 6/7/8) under three conditions (noisy, motion blurred, and rainy). Through this inspection, we evaluate the contribution of an image enhancement scheme so-called MPRNet. For this aim, we trained three OD algorithms with the original clean images of the VisDrone dataset. Followingly, we measured the detection performance of saved YOLO models against (1) clean, (2) degraded, and (3) enhanced counterparts. According to the results, MPRNet-based image enhancement promisingly contributes to the detection performance and YOLO8 outperforms its predecessors. We believe that this work presents useful findings for researchers studying aerial image-based vision tasks, especially under extreme weather and image acquisition conditions

The Effect Of Country Of Origin, Perceived Quality, And Brand Image On Purchase Intention (Case Study On Consumers Of Samsung Smartphone Users In Bandung City)

Indonesia is one of the countries withhuge numbers of Internet users. Indonesia's population of 250 million is a big market. Indonesian smartphone users are alsoproliferating. One of the smartphone market leaders is Samsung. This study aimed to determine the effect of country of origin, perceived quality, and brand image on purchase intention. The research design used in this research is causal explanatory. The samplehas beenusing a Samsung Smartphone for more than 1 year and is a student. the number of respondents used is 130 respondents. Based on the results of the study, there is an influence of Country of origin on Purchase Intention of Samsung Smartphone users. There is an influence of Perceived quality on the Purchase Intention of Samsung Smartphone users. There is an influence of Brand image onthePurchase Intention of Samsung Smartphone users. For this reason, researchers suggest Samsung smartphones, to be able to improve Country of origin, Perceived quality, and Brand image as variables that can encourage consumer Purchase Intentions.

Human Skin Detection and Segmentation Based on Convolutional Neural Networks

Human skin detection is the process of classifying the image pixels or regions as skin or non-skin. Skin detection has many applications, such as face tracking, skin diseases, nudity recognition, hand gestures, video surveillance, web content filtering, and pornographic content filtering. Skin detection is a challenging problem due to skin color variation, the human race, aging, gender, makeup, complex backgrounds, etc. This paper suggests detecting the skin region in the image and finding the location of the skin based on a convolutional neural network. In this proposal, the proposed CNN will be modified by adding two layers before the first layer of CNN and after the last layer of CNN. The main purpose of these layers is to prepare the input image by using a sliding window, which inputs an indexed small part of the image into the CNN. The network classifies each part as skin or non-skin and then sends the result into the second suggested layer. After processing all the image pixels, the non-skin blocks are mapped to the original image as black regions. The final image contains the skin regions with black in the background. The contribution of the proposed method is the ability to detect the skin from any part of the human body, unlike previous works, which focused on one part of the body. The input image is processed as blocks instead of the entire image as in the previous works, and then in the output, the original image is reconstructed. This method works well with most of the challenges that face the detection of skin, and finally, the designed network facilitates the localization and segmentation of the skin region almost accurately, while the previous networks focused on the classification of the image as skin or non-skin. The accuracy of the detection of skin when testing with images different from the training images was 95.4%.

Detection of Illegal Goods using X-ray Image Enhancement Algorithm

Abstract: In order to facilitate the security personnel to identify the items in the X-ray image, it is necessary to enhance the security X-ray image to highlight the color, edge, shape and other details of the different items in the image, so that the security personnel can identify the inspected items more accurately and quickly, to ensure the safe operation of the airport. Aiming at the problem of color distortion in CLAHE enhanced airport security X-ray images, an X-ray image enhancement algorithm combining USM+CLAHE is proposed. In this work, First, we calculate the grayscale images on the R, G, and B channels of the X-ray image and perform Contrast Limited Adaptive Histogram Equalization (CLAHE) enhancement respectively, and then merge the enhanced R, G, and B grayscale images. Next, we perform the Unsharp Mask (USM) sharpening operation on the Xray image enhanced by CLAHE, and finally merge the original image and the USM sharpened image according to the weight. The experimental results show that the USM+CLAHE algorithm can effectively enhance the security X-ray image, and at the same time can suppress the color distortion of the enhanced image.

Image Division Using Threshold Schemes with Privileges

Threshold schemes are used among cryptographic techniques for splitting visual data. Such methods allow the generation of a number of secret shares, a certain number of which need to be assembled in order to reconstruct the original image. Traditional techniques for partitioning secret information generate equal shares, i.e., each share has the same value when reconstructing the original secret. However, it turns out that it is possible to develop and use partitioning protocols that allow the generation of privileged shares, i.e., those that allow the reconstruction of secret data in even smaller numbers. This paper will therefore describe new information sharing protocols that create privileged shares, which will also use visual authorization codes based on subject knowledge to select privileged shares for secret restoration. For the protocols described, examples of their functioning will be presented, and their complexity and potential for use in practical applications will be determined.

Technical innovation in the art of hyper-realism

In the period following World War II, a postmodern period in which cultural activity increased and the creation of new characteristics and patterns of form in social and economic life and is no longer the old artistic pressure is dominant, but the media, technology and the market and called the community the term consumer or multinational capitalism emerged new movements, including the art of hyperrealism subject of research has included the first chapter of the research problem, which ended with the following question:(what is the property of technical renewal brought by excessive realism)The aim of the study was to know the renewal in the art of hyperrealism and the techniques used in the works of art, the limits of the research included models of the art of hyperrealism for the period(1969/1979) in Europe/ America. The second chapter included two sections, the first dealt with intellectual and cultural transformations and their impact on postmodern arts and the second came on two axes, the first; the points of difference between the original image and the imaginary image and its relationship to the art of hyperrealism, and the second: the artistic characteristics of hyperrealism and its artists. In the third chapter, the research procedures, where the descriptive approach was relied on to analyze the sample taken from the research community, which is a set of works that have been viewed through books and scientific sources and the selection of a sample representing the subject in an intentional manner amounted to 3 drawing works with the use of the observation tool and what was stated in the indicators for analysis. Keywords: renewal, technical, art, realism, excessive.

Predicting Time-to-Healing from a Digital Wound Image: A Hybrid Neural Network and Decision Tree Approach Improves Performance

Despite the societal burden of chronic wounds and despite advances in image processing, automated image-based prediction of wound prognosis is not yet in routine clinical practice. While specific tissue types are known to be positive or negative prognostic indicators, image-based wound healing prediction systems that have been demonstrated to date do not (1) use information about the proportions of tissue types within the wound and (2) predict time-to-healing (most predict categorical clinical labels). In this work, we analyzed a unique dataset of time-series images of healing wounds from a controlled study in dogs, as well as human wound images that are annotated for the tissue type composition. In the context of a hybrid-learning approach (neural network segmentation and decision tree regression) for the image-based prediction of time-to-healing, we tested whether explicitly incorporating tissue type-derived features into the model would improve the accuracy for time-to-healing prediction versus not including such features. We tested four deep convolutional encoder–decoder neural network models for wound image segmentation and identified, in the context of both original wound images and an augmented wound image-set, that a SegNet-type network trained on an augmented image set has best segmentation performance. Furthermore, using three different regression algorithms, we evaluated models for predicting wound time-to-healing using features extracted from the four best-performing segmentation models. We found that XGBoost regression using features that are (i) extracted from a SegNet-type network and (ii) reduced using principal components analysis performed the best for time-to-healing prediction. We demonstrated that a neural network model can classify the regions of a wound image as one of four tissue types, and demonstrated that adding features derived from the superpixel classifier improves the performance for healing-time prediction.

Subjective and objective image quality of low-dose CT images processed using a self-supervised denoising algorithm.

This study aimed to assess the subjective and objective image quality of low-dose computed tomography (CT) images processed using a self-supervised denoising algorithm with deep learning. We trained the self-supervised denoising model using low-dose CT images of 40 patients and applied this model to CT images of another 30 patients. Image quality, in terms of noise and edge sharpness, was rated on a 5-point scale by two radiologists. The coefficient of variation, contrast-to-noise ratio (CNR), and signal-to-noise ratio (SNR) were calculated. The values for the self-supervised denoising model were compared with those for the original low-dose CT images and CT images processed using other conventional denoising algorithms (non-local means, block-matching and 3D filtering, and total variation minimization-based algorithms). The mean (standard deviation) scores of local and overall noise levels for the self-supervised denoising algorithm were 3.90 (0.40) and 3.93 (0.51), respectively, outperforming the original image and other algorithms. Similarly, the mean scores of local and overall edge sharpness for the self-supervised denoising algorithm were 3.90 (0.40) and 3.75 (0.47), respectively, surpassing the scores of the original image and other algorithms. The CNR and SNR for the self-supervised denoising algorithm were higher than those for the original images but slightly lower than those for the other algorithms. Our findings indicate the potential clinical applicability of the self-supervised denoising algorithm for low-dose CT images in clinical settings.

Low-cost architecture performance evaluation strategy based on pixel difference degree contrast measurement

The time and effort required to manually design deep neural architectures is extremely high, which has led to the development of neural architecture search technology as an automatic architecture design method. However, the neural architecture search convergence process is slow and expensive, and the process requires training a large number of candidate architectures to get the final result. If the final accuracy of an architecture can be predicted from its initial state, this problem can be greatly alleviated. Therefore, this paper proposes a low-cost architecture performance evaluation strategy based on pixel difference degree contrast measurement, which takes 1) the difference matrix value between the feature map generated in the untrained architecture and the original image, and 2) the predicted accuracy of the neural network as evaluation indices. A new multi-index weight comprehensive measurement strategy was introduced to comprehensively score the multi-index, the real architecture performance can be approximately represented by score, which greatly reduces the cost of architecture evaluation. The experimental show that the proposed scoring strategy is highly correlated with real architecture accuracy. In the practical engineering application research, this strategy can search a high-performance architecture with an accuracy of 96.2% within 343.3 s, which proves that the proposed strategy can significantly improve the search efficiency in practical applications, reduce the subjectivity of artificial architecture design, and promote the application of practical time-consuming projects.

An Image Classification Method of Unbalanced Ship Coating Defects Based on DCCVAE-ACWGAN-GP

Affected by the improper operation of the workers, environmental changes during drying and curing or the quality of the paint itself, diverse defects are produced during the process of ship painting. The traditional defect recognition method relies on expert knowledge or experience to detect defects, which is not conducive to ensuring the effectiveness of defect recognition. Therefore, this paper proposes an image generation and recognition model which is suitable for small samples. Based on a deep convolutional neural network (DCNN), the model combines a conditional variational autoencoder (DCCVAE) and auxiliary conditional Wasserstein GAN with gradient penalty (ACWGAN-GP) to gradually expand and generate various coating defect images for solving the overfitting problem due to unbalanced data. The DCNN model is trained based on newly generated image data and original image data so as to build a coating defect image classification model suitable for small samples, which is conducive to improving classification performance. The experimental results showed that our proposed model can achieve up to 92.54% accuracy, an F-score of 88.33%, and a G mean value of 91.93%. Compared with traditional data enhancement methods and classification algorithms, our proposed model can identify various defects in the ship painting process more accurately and consistently, which can provide effective theoretical and technical support for ship painting defect detection and has significant engineering research value and application prospects.

OralEpitheliumDB: A Dataset for Oral Epithelial Dysplasia Image Segmentation and Classification.

Early diagnosis of potentially malignant disorders, such as oral epithelial dysplasia, is the most reliable way to prevent oral cancer. Computational algorithms have been used as an auxiliary tool to aid specialists in this process. Usually, experiments are performed on private data, making it difficult to reproduce the results. There are several public datasets of histological images, but studies focused on oral dysplasia images use inaccessible datasets. This prevents the improvement of algorithms aimed at this lesion. This study introduces an annotated public dataset of oral epithelial dysplasia tissue images. The dataset includes 456 images acquired from 30 mouse tongues. The images were categorized among the lesion grades, with nuclear structures manually marked by a trained specialist and validated by a pathologist. Also, experiments were carried out in order to illustrate the potential of the proposed dataset in classification and segmentation processes commonly explored in the literature. Convolutional neural network (CNN) models for semantic and instance segmentation were employed on the images, which were pre-processed with stain normalization methods. Then, the segmented and non-segmented images were classified with CNN architectures and machine learning algorithms. The data obtained through these processes is available in the dataset. The segmentation stage showed the F1-score value of 0.83, obtained with the U-Net model using the ResNet-50 as a backbone. At the classification stage, the most expressive result was achieved with the Random Forest method, with an accuracy value of 94.22%. The results show that the segmentation contributed to the classification results, but studies are needed for the improvement of these stages of automated diagnosis. The original, gold standard, normalized, and segmented images are publicly available and may be used for the improvement of clinical applications of CAD methods on oral epithelial dysplasia tissue images.

AI-assisted deepfake detection using adaptive blind image watermarking

This paper proposes a new adaptive blind watermarking technology for deepfake detection, which can embed deepfake detection information into the image and verify the image's authenticity without requiring additional information. The proposed scheme utilizes mixed modulation combined with partly sign-altered mean value to embed a set of coefficients that enhance robustness against attacks while maintaining high image quality. Additionally, blind adaptive deepfake detection technology with the tamper detection mean value is employed to detect relative positions adaptively, even when face images are slightly modified or deepfaked. To further improve the performance of the proposed scheme, a gray wolf optimizer is introduced to optimize parameters, and a denoising autoencoder is employed to facilitate the identification of extracted watermarks. This technology will adaptively embed watermark information while preserving the original face image, thereby maintaining the authenticity of the face in the image and verifying the owner of the image. The code is available at https://github.com/lyhsu01/AwDD.

Target Image Processing Based on Super-resolution Reconstruction and Deep Machine Learning Algorithm

In dictionary-based single-frame image reconstruction algorithms, dictionaries rely on the design of artificial shallow features and are limited in their ability to represent image features. Therefore, this paper proposes a high-accuracy reconstruction method based on deep learning feature dictionary. This algorithm first uses a deep network to learn high-resolution and low-resolution training example images with deep features; Then co-train the feature dictionary under the super dense framework of the sparse dictionary; Finally, a single low-resolution image can be input and a super-resolution reconstruction can be performed using a dictionary. From the theoretical analysis, the introduction of deep network to extract the deep-level features of the image and its use in dictionary training is more beneficial to complement the high-frequency information in the low-resolution image. Experiments show that the proposed method achieves the best results in terms of both the peak signal-to-noise ratio and the gradient energy function of the reconstructed images. This shows that compared with traditional interpolation methods and some deep learning methods, the proposed method can recover image details to a high degree while preserving the original image damage information. This proves that the subjective visual and objective evaluation indicators of the algorithm presented in this article are higher than those of the comparative algorithm.

Creation and environmental applications of 15-year daily inundation and vegetation maps for Siberia by integrating satellite and meteorological datasets

As a result of climate change, the pan-Arctic region has seen greater temperature increases than other geographical regions on the Earth’s surface. This has led to substantial changes in terrestrial ecosystems and the hydrological cycle, which have affected the distribution of vegetation and the patterns of water flow and accumulation. Various remote sensing techniques, including optical and microwave satellite observations, are useful for monitoring these terrestrial water and vegetation dynamics. In the present study, satellite and reanalysis datasets were used to produce water and vegetation maps with a high temporal resolution (daily) and moderate spatial resolution (500 m) at a continental scale over Siberia in the period 2003–2017. The multiple data sources were integrated by pixel-based machine learning (random forest), which generated a normalized difference water index (NDWI), normalized difference vegetation index (NDVI), and water fraction without any gaps, even for areas where optical data were missing (e.g., cloud cover). For the convenience of users handling the data, an aggregated product is provided, formatted using a 0.1° grid in latitude/longitude projection. When validated using the original optical images, the NDWI and NDVI images showed small systematic biases, with a root mean squared error of approximately 0.1 over the study area. The product was used for both time-series trend analysis of the indices from 2003 to 2017 and phenological feature extraction based on seasonal NDVI patterns. The former analysis was used to identify areas where the NDVI is decreasing and the NDWI is increasing, and hotspots where the NDWI at lakesides and coastal regions is decreasing. The latter analysis, which employed double-sigmoid fitting to assess changes in five phenological parameters (i.e., start and end of spring and fall, and peak NDVI values) at two larch forest sites, highlighted a tendency for recent lengthening of the growing period. Further applications, including model integration and contribution to land cover mapping, will be developed in the future.