Neural Image Research Articles

Hybrid Optimization with Recurrent Neural Network-based Medical Image Processing for Predicting Interstitial Lung Disease

One of the dreadful diseases that shortens people's lives is lung disease. There are numerous potentially fatal consequences that can arise from interstitial lung disease, such as: Lung hypertension. This illness doesn't influence your overall blood pressure; instead, it only affects the arteries in your lungs. To prevent mortality, it is essential to accurately diagnose pulmonary illness in patients. Various classifiers, including SVM, RF, MLP, and others, are processed to identify lung disorders. Large datasets cannot be processed by these algorithms, which causes false lung disease identification. A combined new Spider Monkey and Lion algorithm is suggested as a solution to get around these limitations. Images of interstitial lung disease (ILD) were taken for the study from the publicly accessible MedGIFT database. The median filter is employed during the pre-processing step of ILD images to reduce noise and remove undesirable objects. The features are extracted using a hybrid spider Monkey and Lion algorithm. The lungs' damaged and unaffected regions are divided into categories using recurrent neural networks. Several metrics such as accuracy, precision, recall, and f1-score are used to evaluate the performance of the proposed system. The results demonstrate that this technique offers more precision, accuracy, and a higher rate of lung illness detection by processing a large number of computerized tomography representations quickly. When compared to other strategies already in use, the proposed model's accuracy is greater at 99.8%. This method could be beneficial for staging the severity of interstitial lung illness, prognosticating, and forecasting treatment outcomes and survival, determining risk control, and allocation of resources.

Retracted: Inspecting Decorative Ceramic Defects by Fusing Convolutional Neural Network and Image Recognition.

[This retracts the article DOI: 10.1155/2022/3983919.].

Retracted: Computer‐Aided Diagnosis of Children with Cerebral Palsy under Deep Learning Convolutional Neural Network Image Segmentation Model Combined with Three‐Dimensional Cranial Magnetic Resonance Imaging

Retracted: Computer‐Aided Diagnosis of Children with Cerebral Palsy under Deep Learning Convolutional Neural Network Image Segmentation Model Combined with Three‐Dimensional Cranial Magnetic Resonance Imaging

Lighting Search Algorithm With Convolutional Neural Network-Based Image Captioning System for Natural Language Processing

Lighting Search Algorithm With Convolutional Neural Network-Based Image Captioning System for Natural Language Processing

High-Performance Photodetectors Based on Graphene/MoS₂ Heterojunction FETs

Being an excellent representative of atomically thin 2-D materials, graphene has attracted extensive research attention in the fields of electronic and optoelectronic devices. However, its low-light absorption coefficient, gapless nature, and short carrier lifetime hinder its development in photodetectors. Another atomically thin 2-D semiconducting material molybdenum disulfide (MoS2) has stronger light interaction. Here, we show a high-performance photodetector based on graphene/MoS2 heterojunction field effect transistors (FETs), where the electrodes are fabricated in the middle of two materials. Graphene functions as a conductive material that improves the carrier transmit speed of the device. Meanwhile, MoS2 mainly functions as a light-sensitive material that promotes the generation of photogenerated carriers. The combination of the two materials substantially improves the performance of the photodetector. The photoresponsivity of our device was demonstrated up to <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${1.5} \times {10} ^{{4}}$ </tex-math></inline-formula> A/W under a 470-nm light-emitting diode (LED) light illumination, which was much higher than that of a reported photodetector based on monolayer graphene or MoS2 (~mA/W). Moreover, the photoresponsivity of the device could be easily tuned by applying buried-gate, back-gate, and source–drain voltage, which has important implications for the application of 2-D material photodetectors in neural network image sensor arrays. Our study established a method for large-scale preparation of high-performance photodetector arrays based on 2-D materials heterojunctions.

Detect Your Fingerprint in Your Photographs: Photography-based Multi-Feature Sybil Detection

A darknet market is an online marketplace typically implemented over Tor, where vendors sell illegal products or criminal services. Due to dramatic growth in the popularity of such markets, there is a recognized need for automatic investigation of the market’s ecosystem and identification of anonymous vendors. However, as they often create multiple accounts (or Sybil accounts) within or across different marketplaces, detecting Sybil accounts becomes the key to understanding the ecosystem of darknet markets and identifying the actual relationship between the vendors. This study presents a novel Sybil detection method that extracts multiple features of vendors from photographs in a fine-grained level (e.g., image similarity, main category, subcategory, and text data), and reveals the multiple Sybil accounts of them simultaneously. Each feature is extracted from multiple rich sources using an image hash algorithm, Deep Neural Network (DNN) classifier, image restoration, and text recognition tool; and merged using a weighted feature embedding model. The matching score of each vendor is then calculated to identify not only the exact Sybil accounts, but multiple potential accounts suspected of being associated to a single operator. We evaluate the efficacy of our method using real-world datasets from four large darknet markets (i.e., SilkRoad2, Agora, Evolution, Alphabay) from 2014 to 2015. Because of the anonymity of darknet market, we construct the ground-truth of Sybil accounts by randomly splitting the dataset of vendors into two even parts. We used the first set to train the model, and linked the second set to the original vendor in the first set to evaluate performance. Our experimental results demonstrated that the proposed method outperforms the existing photography-based system with an accuracy of 98%, identifying up to 700% more candidate Sybil accounts than prior work. Additionally, our method detects multiple Sybil accounts for 90% of evaluated test cases, presenting a very different picture of darknet marketplace dynamics than methods that can only detect a single Sybil account for each target vendor. Due to its fine-grained multiple feature extraction from photographs, our method can be more generically applied to various darknet markets for Sybil detection regardless of their languages or categories of items.

Machine learning for autonomous online exam fraud detection: A concept design

E-learning (EL) has emerged as one of the most valuable means for continuing education around the world, especially in the aftermath of the global pandemic that included a variety of obstacles. Real-time online assessments have become a significant concern for educational organizations. Instances of fraudulent behavior during online exams (OEs) have created considerable challenges for exam invigilators, who are unable to identify and remove such dishonest behavior. In response to this significant issue, educational institutions have used a variety of manual procedures to alleviate the situation, but none of these measures have shown to be particularly innovative or effective. The current study presents a novel strategy for detecting fraudulent actions in real time during OEs that uses convolutional neural network (CNN) algorithms and image processing. The development model will be trained using the CK and CK++ datasets. The training procedure will use 80% of the selected dataset, with the remaining 20% used for model testing to confirm the model’s efficacy and generalization capacity. This project intends to revolutionize the monitoring and prevention of fraudulent actions during online tests by integrating CNN techniques and image processing. The use of CK and CK++ datasets, as well as an 80–20 split for training and testing, contributes to the study’s thorough and rigorous approach. Educational institutions can improve their assessment procedures and maintain the credibility of EL as a credible and equitable way of continuing education by successfully using this unique technique.

A Shine Muscat Grape Berry Detection and Grape Cluster Compactness Estimation for Assessment of Grape Quality Based on Instance Segmentation Methods

Highlights Mask R-CNN ResNet-101 was analyzed to have the highest detection accuracy for grape berries. Grape cluster compactness is one of the important factors that determines the quality of grapes. Indicator DGC was used to intuitively calculate the compactness of grape cluster. An average error of 1.6 mm occurred with the verification of diameter estimation algorithm. Abstract. Consumption and cultivation of grapes are constantly increasing because they are known as alkaline foods, which relieve fatigue by accelerating carbohydrate metabolism in the human body. Among these grapes, a Shine Muscat doesn’t have the bitter taste of ordinary grapes, has low acidity, and has a crunchy texture, which results in growing interest in modern society. As the consumption of Shine Muscat increases, an automated process to save labor and time becomes essential. Particularly, one challenge that needs to be solved is the determination of grape quality based solely on visual evaluations by experts, which can result in inconsistent pricing for consumers. In this study, an algorithm was adopted to detect the grape berries from a bunch of single grapes by acquiring RGB images of the harvested Shine Muscat. Mask R-CNN, a convolutional neural network-based image segmentation technique, was used with various backbones to compare and evaluate the performance of each model. Results showed that Mask R-CNN ResNet 101 had the highest AP (Average Precision) value of 0.961 among all models. In addition, indexes such as the size (diameter) of each grape berry, the area of the grape on the image, and the area of the empty space that are required to find the compactness of the grape cluster are obtained. In particular, it was analyzed that the average error value (mm) and percent error (%) of the diameter estimation algorithm developed in this study were 1.60 mm and 4.79%, respectively. Keywords: Keywords., Density of Grape Cluster (DGC), Diameter estimation, Grape berry, Grape cluster compactness, Mask R-CNN, Object detection.

Real-time debris flow detection using deep convolutional neural network and Jetson Nano

This study aims to develop a potential system for real-time detection of debris flow motion using a deep convolutional neural network (CNN) and image processing techniques. A system consisting of a pre-trained CNN model, NVIDIA Jetson Nano, and a camera was used to identify debris flow movement. The pre-trained CNN model was trained on an image dataset derived from 12 debris flow videos obtained from small flume tests, large flume tests, and several debris flow events. The application results of the proposed system on the flume test in the laboratory reached an F1 score of 72.6 to 100%. The real-time processing speed of the CNN model achieved from 2 to 21 frames per second (FPS) on the Jetson Nano. Both the accuracy and the processing speed of CNN model depend on the size of the video input and the input size of the model CNN. The CNN model of 320 × 320 pixels with a resolution of 800 × 480 pixels gives accuracy (F1 = 99.2%) and processing speed (FPS = 20) considered the optimal model when running the Jetson Nano device; thus, it can be applied for early detection and warning systems.

Convolutional neural network-based skin image segmentation model to improve classification of skin diseases in conventional and non-standardized picture images

BackgroundFor dermatological practices, non-standardized conventional photo images are taken and collected as a mixture of variable fields of the image view, including close-up images focusing on designated lesions and long-shot images including normal skin and background of the body surface. Computer-aided detection/diagnosis (CAD) models trained using non-standardized conventional photo images exhibit lower performance rates than CAD models that detect lesions in a localized small area, such as dermoscopic images. ObjectiveWe aimed to develop a convolutional neural network (CNN) model for skin image segmentation to generate a skin disease image dataset suitable for CAD of multiple skin disease classification. MethodsWe trained a DeepLabv3 + -based CNN segmentation model to detect skin and lesion areas and segmented out areas that satisfy the following conditions: more than 80% of the image will be the skin area, and more than 10% of the image will be the lesion area. ResultsThe generated CNN-segmented image database was examined using CAD of skin disease classification and achieved approximately 90% sensitivity and specificity to differentiate atopic dermatitis from malignant diseases and complications, such as mycosis fungoides, impetigo, and herpesvirus infection. The accuracy of skin disease classification in the CNN-segmented image dataset was almost equal to that of the manually cropped image dataset and higher than that of the original image dataset. ConclusionOur CNN segmentation model, which automatically extracts lesions and segmented images of the skin area regardless of image fields, will reduce the burden of physician annotation and improve CAD performance.

Neural network-based computational holographic encryption image reconstruction scheme for chaotic iris phase mask

ä¸ºäº†æ‹“å±•å¯¹è®¡ç®—å ¨æ¯åŠ å¯†å›¾åƒçš„è§£å¯†æ–¹æ³•ï¼Œé’ˆå¯¹éžæ³•æ”»å‡»éš¾åº¦å¤§çš„å¯¹ç§°-éžå¯¹ç§°æ··åˆåŠ å¯†ç³»ç»Ÿï¼Œæå‡ºäº†ä¸€ç§åˆ©ç”¨ç¥žç»ç½‘ç»œæ¢å¤æ··æ²Œè™¹è†œç›¸ä½æŽ©æ¨¡è®¡ç®—å ¨æ¯åŠ å¯†å›¾åƒçš„æ–¹æ¡ˆã€‚å¯¹æ˜Žæ–‡å›¾åƒè¿›è¡ŒåŠ å¯†ï¼Œç”Ÿæˆè®¡ç®—å ¨æ¯çš„å¯†æ–‡å›¾åƒï¼Œåˆ¶ä½œå¤§é‡çš„å¯†æ–‡æ˜Žæ–‡å›¾åƒå¯¹ä½œä¸ºæ•°æ®é›†ã€‚é€šè¿‡æ­å»ºç¥žç»ç½‘ç»œä¸æ–­åœ°è®­ç»ƒå’Œæµ‹è¯•ï¼Œè®­ç»ƒå®ŒæˆåŽçš„ç¥žç»ç½‘ç»œå¯ä»¥æ‹Ÿåˆå‡ºå¯†æ–‡å›¾åƒåˆ°æ˜Žæ–‡å›¾åƒçš„æ˜ å°„å ³ç³»ï¼Œè§£å¯†æ—¶ä¸å†ä½¿ç”¨å ¬é’¥å’Œç§é’¥å¯¹å¯†æ–‡å›¾åƒè¿›è¡Œè§£å¯†ã€‚å®žéªŒç»“æžœè¡¨æ˜Žï¼šé€šè¿‡ç¥žç»ç½‘ç»œæ¢å¤å‡ºçš„å›¾åƒä¸Žæ˜Žæ–‡å›¾åƒç›¸æ¯”ï¼Œå¹³å‡äº’ç›¸å ³ç³»æ•°ä¸º0.984，平均峰值信噪比为61.0 dB，平均结构相似性为0.77ï¼›å¯¹å¯†æ–‡å›¾åƒè¿›è¡Œå™ªå£°æ±¡æŸ“ï¼Œä¹Ÿå¯ä»¥æ¢å¤å‡ºè¾ƒé«˜è´¨é‡çš„å›¾åƒï¼Œå®žçŽ°äº†é€šè¿‡ç¥žç»ç½‘ç»œå¯¹å¯†æ–‡å›¾åƒè§£å¯†çš„ç›®çš„ï¼Œæ–¹æ¡ˆæ˜¯å¯è¡Œçš„å¹¶å ·æœ‰è¾ƒå¥½çš„é²æ£’æ€§ã€‚

A survey on neural network-based image data hiding for secure communication

A survey on neural network-based image data hiding for secure communication

A Deep Learning Model to Generate Image Captions

How computers can automatically describe the substance of photographs using human language is a topic that interests us greatly. We choose to use the most advanced image caption generator currently available to obtain a deeper understanding of this computer vision topic. Show, attend and tell Visually attentive neural image caption generator [12]. Our machine learning-based neural network picture description generator is created in Python using the Pytorch ML framework. In our workflow, we’ve determined five key elements: Data preparation, a convolutional neural network (CNN) it helps in encoding, a recurrent neural network (RNN) it helps in decoding, a beam search to determine the best description, generation of sentences, and assessment make up the R1-R6 framework. The quality and correctness of the generated caption are evaluated using the BLEU-4 score. Each member of our group contributed equally to moving the project forward as we distributed the five elements mentioned above equally among ourselves. All five components have been completed successfully, and we can now use Kaggle Notebook to train our network. After the network has been trained and is performing satisfactorily, we continue to see the attention mechanism.

Language Model Agnostic Gray-Box Adversarial Attack on Image Captioning

Adversarial susceptibility of neural image captioning is still under-explored due to the complex multi-model nature of the task. We introduce a GAN-based adversarial attack to effectively fool encoder-decoder based image captioning frameworks. Unique to our attack is the systematic disruption of the internal representation of an image at the encoder stage which allows control over the captions generated at the decoder stage. We cause the desired disruption with an input perturbation that promotes similarity between the features of the input image with a target image of our choice. The target image provides a convenient handle to control the incorrect captions in our method. We do not assume any knowledge of the decoder module, which makes our attack ‘gray-box’. Moreover, our attack remains agnostic to the type of decoder module, thereby proving effective for RNNs as well as Transformers as the language models. This makes our attack highly pragmatic.

FoVolNet: Fast Volume Rendering using Foveated Deep Neural Networks.

Volume data is found in many important scientific and engineering applications. Rendering this data for visualization at high quality and interactive rates for demanding applications such as virtual reality is still not easily achievable even using professional-grade hardware. We introduce FoVolNet-a method to significantly increase the performance of volume data visualization. We develop a cost-effective foveated rendering pipeline that sparsely samples a volume around a focal point and reconstructs the full-frame using a deep neural network. Foveated rendering is a technique that prioritizes rendering computations around the user's focal point. This approach leverages properties of the human visual system, thereby saving computational resources when rendering data in the periphery of the user's field of vision. Our reconstruction network combines direct and kernel prediction methods to produce fast, stable, and perceptually convincing output. With a slim design and the use of quantization, our method outperforms state-of-the-art neural reconstruction techniques in both end-to-end frame times and visual quality. We conduct extensive evaluations of the system's rendering performance, inference speed, and perceptual properties, and we provide comparisons to competing neural image reconstruction techniques. Our test results show that FoVolNet consistently achieves significant time saving over conventional rendering while preserving perceptual quality.

Hybrid Refractive-Diffractive Lens with Reduced Chromatic and Geometric Aberrations and Learned Image Reconstruction

In this paper, we present a hybrid refractive-diffractive lens that, when paired with a deep neural network-based image reconstruction, produces high-quality, real-world images with minimal artifacts, reaching a PSNR of 28 dB on the test set. Our diffractive element compensates for the off-axis aberrations of a single refractive element and has reduced chromatic aberrations across the visible light spectrum. We also describe our training set augmentation and novel quality criteria called "false edge level" (FEL), which validates that the neural network produces visually appealing images without artifacts under a wide range of ISO and exposure settings. Our quality criteria (FEL) enabled us to include real scene images without a corresponding ground truth in the training process.

Neural Image Style Transfer Using Modified Histogram Matching

Neural Image Style Transfer is an algorithm which was first introduced in 2016 for transferring the style of an image using a CNN. Over the years, a large portion of the research has been devoted in balancing the trade-off between time taken by the algorithm to process the images and the quality of the results generated. In addition, the application of traditional image processing algorithms has been limited. In this paper, we aim to introduce a modification to the traditional method by utilizing a localized histogram matching algorithm combined with Contrast Limited Adaptive Histogram Equalization (CLAHE). The results show that the quality of style transferred and the colour of images obtained by this method is much better than the traditional method for the same number of iterations.

Three-stage image forgery localization with shallow feature enhancement and attention

With the development of technology, it is becoming easier and easier for people to generate tampered images that are indistinguishable from the human eye, and the malicious use of these photos in news, academic papers, and criminal crimes has brought great harm to society. This paper proposes a deep convolutional neural network-based image forgery localization method to uncover the subtle differences between doctored images and real images. Specifically, the network achieves tampering localization through a three-stage enhancement scheme. First, the dilated convolution in the deep layer of the network is used to keep the feature map resolution constant, and the number of shallow convolutions is decreased to reduce the perceptual field, so the network focuses on local regions. Second, the feature enhancement module is used to fuse shallow features with deep features to effectively filter content information and highlight tampering features, making full use of local and global information to improve the generalization ability. Finally, the attention enhancement module reweights the convolutional feature maps in terms of channels and locations, respectively, to highlight the information regions around the forgery boundaries, thus guiding the network to capture more intrinsic features for image forgery. Extensive experimental results on several public datasets show that this method outperforms other state-of-the-art methods in image forgery localization.

Pit viper thermography: the pit organ used by crotaline snakes to detect thermal contrast has poor spatial resolution.

Pit vipers detect infrared radiation by means of temperature contrasts created on their pit organ membranes. Signals from pit organs integrate with visual signals in the optic tectum, leading to the conjecture that the facial pits operate as an extension of the visual system. Because similar mechanisms underlie thermal imaging technology, imagery from thermal cameras is often used to infer how pit vipers perceive their environment. However, pit organs lack a focusing mechanism, and biophysical models predict that pit organs should have poor spatial resolution compared with thermal imaging cameras. Nevertheless, behavioral studies occasionally suggest pits may have better resolution than predicted by biophysical models, indicating that processing in the central nervous system may improve imaging. To estimate the spatial resolution of the neural image informing behavior, we recorded snake responses evoked by targets moving across backgrounds composed of two contrasting temperatures with an average temperature equal to the target temperature. An unresolved background would appear uniform; thus, the target would be detectable only if the background pattern were resolved. Western rattlesnakes (Crotalus oreganus) displayed no statistically significant responses to targets presented in front of patterned backgrounds, regardless of the temperature contrasts or spatial frequencies within the background, but responded strongly to targets presented in front of homogeneous backgrounds. We found no evidence that the pit organ system can resolve spatial details subtending an angle of 9deg or less. We discuss the implications of these results for understanding pit organ function in ecologically relevant habitats with thermal heterogeneity.

Human-centered artificial intelligence-based ice hockey sports classification system with web 4.0

Abstract Systems with human-centered artificial intelligence are always as good as their ability to consider their users’ context when making decisions. Research on identifying people’s everyday activities has evolved rapidly, but little attention has been paid to recognizing both the activities themselves and the motions they make during those tasks. Automated monitoring, human-to-computer interaction, and sports analysis all benefit from Web 4.0. Every sport has gotten its move, and every move is not known to everyone. In ice hockey, every move cannot be monitored by the referee. Here, Convolution Neural Network-based Real-Time Image Processing Framework (CNN-RTIPF) is introduced to classify every move in Ice Hockey. CNN-RTIPF can reduce the challenges in monitoring the player’s move individually. The image of every move is captured and compared with the trained data in CNN. These real-time captured images are processed using a human-centered artificial intelligence system. They compared images predicted by probability calculation of the trained set of images for effective classification. Simulation analysis shows that the proposed CNN-RTIPF can classify real-time images with improved classification ratio, sensitivity, and error rate. The proposed CNN-RTIPF has been validated based on the optimization parameter for reliability. To improve the algorithm for movement identification and train the system for many other everyday activities, human-centered artificial intelligence-based Web 4.0 will continue to develop.