Image Scaling Research Articles

Inverse Interpolation and Its Application in Robust Image Steganography

Traditional steganography methods are usually designed on a lossless channel; thus, messages are often not extracted correctly from an image transmitted over a lossy channel that includes attacks such as scaling. To address this issue, in recent years, the field of robust steganography has emerged. In this paper, the process of image scaling by interpolation is first observed and serves as the basis for proposing the idea of inverse interpolation. Subsequently, the idea of constructing an inverse interpolation equation set is proposed to solve the problem of intersectional blocks during the inverse interpolation process. Then, the scaling factor’s valid range of inverse interpolation is analyzed. Next, the inverse interpolation is successfully applied in robust image steganography. A method that combines antiscaling and antidetection is proposed. Afterward, actual tests on the top 9 mobile phone brands with 28 models and 2 social communication apps that are currently popular in China are done. The scaling factor’s valid range of the proposed method is verified to match the actual lossy channel. The experimental results show that the proposed method achieves a reliable extraction of embedded messages for common interpolation scaling attacks while maintaining high statistical detection resistance.

Self‐adaptive‐deer hunting optimization‐based optimal weighted features and hybrid classifier for automated disease detection in plant leaves

AbstractThis main intention of this paper is to adopt a new disease detection model for plant leaves. The proposed model involves several steps such as pre‐processing, leaf segmentation, abnormality segmentation, feature extraction and detection. Image scaling and contrast enhancement are performed during the pre‐processing phase. Once the pre‐processing is done, the segmentation phase starts with leaf segmentation by binary thresholding method and abnormality segmentation by K‐means clustering. Further, the local binary pattern and grey‐level co‐occurrence matrix features are extracted and a dimensionality reduced technique called principle component analysis is determined. As the main novelty, the weighted feature extraction is performed, in which the weight functions are optimized by the self‐adaptive deer hunting optimization (SA‐DHOA). Another contribution of this paper is to implement a hybrid classifier for disease detection. Here, the extracted weighted features are subjected to a support vector machine, and the abnormality segmented image is subjected to convolutional neural network (CNN), which is a deep learning algorithm that can learn the features automatically. Here, the same SA‐DHOA is used to improve the performance of CNN, which is termed as SA‐DHOA‐SCNN. Finally, the performance analysis confirms the maximum success rate of the proposed model over other conventional methods.

Design and Implementation of MQIR Image Scaling

Design and Implementation of MQIR Image Scaling

Scaling up and down of 3-D floating-point data in quantum computation

In the past few decades, quantum computation has become increasingly attractive due to its remarkable performance. Quantum image scaling is considered a common geometric transformation in quantum image processing, however, the quantum floating-point data version of which does not exist. Is there a corresponding scaling for 2-D and 3-D floating-point data? The answer is yes. In this paper, we present a quantum scaling up and down scheme for floating-point data by using trilinear interpolation method in 3-D space. This scheme offers better performance (in terms of the precision of floating-point numbers) for realizing the quantum floating-point algorithms than previously classical approaches. The Converter module we proposed can solve the conversion of fixed-point numbers to floating-point numbers of arbitrary size data with p+q qubits based on IEEE-754 format, instead of 32-bit single-precision, 64-bit double-precision and 128-bit extended-precision. Usually, we use nearest-neighbor interpolation and bilinear interpolation to achieve quantum image scaling algorithms, which are not applicable in high-dimensional space. This paper proposes trilinear interpolation of floating-point data in 3-D space to achieve quantum algorithms of scaling up and down for 3-D floating-point data. Finally, the quantum scaling circuits of 3-D floating-point data are designed.

특징점 추출 및 매칭을 이용한 ISAR 영상의 수직-거리 스케일링 기법 연구

A method that utilizes two sequential inverse synthetic aperture radar (ISAR) images to estimate the rotation velocity of the target and perform cross-range scaling of ISAR images is proposed. First, features/scatterers that are robust against the change in aspect angle and the scintillation between two sequential ISAR images are extracted. Next, extracted features are matched such that the same feature corresponds between the two sequential ISAR images. To accomplish this, scale-invariant feature transform is adopted for feature extraction, followed by feature matching through nearest-neighbor distance ratio and random sample consensus techniques. In this way, a homography between two sequential ISAR images can be obtained and the rotational velocity of the target can be deduced without prior knowledge of the equivalent rotational center of the target. To demonstrate the effectiveness of the proposed method, the results of a simulation dataset for point scatterers are provided.

"Mitigation and Identification of Camouflage Attack Over Computer Vision Applications"

Computer vision technologies are now commonly used in real-time image and video recognition applications using deep neural networks. Scaling or Mitigation is the basic input pre-processing feature in these implementations. Image scaling methods are designed to maintain visual elements before and after scaling, and are widely utilized in a variety of visual and image processing applications. Content disguising attacks may be carried out by taking advantage of the picture scaling mechanism, which causes the machine's extracted content to be drastically different from the input before scaling. In this project the actual input image with dimension Am×n is resized to an attacked image dimension Om1×n1, which will mislead the classifier as the input is attacked image. To illustrate the threats from such camouflage attacks, some computer vision applications taken as targeted victims that includes multiple image classification applications based on popular deep learning frameworks like OpenCV, pillow. This attack is not detected while checking with the YOLOV4 demo. To defend against such attacks, in this project using Dhash i.e., difference hash concept. The hash the value of the actual image and the resized are same when using the Dhash. If the image is camouflaged the means the content is modified so the Dhash value of the image also changed if the image is not camouflaged the then the hash value of the actual image and resized images are same. By using the Dhash concept detecting the image is camouflaged or not.

Larger images are better remembered during naturalistic encoding

We are constantly exposed to multiple visual scenes, and while freely viewing them without an intentional effort to memorize or encode them, only some are remembered. It has been suggested that image memory is influenced by multiple factors, such as depth of processing, familiarity, and visual category. However, this is typically investigated when people are instructed to perform a task (e.g., remember or make some judgment about the images), which may modulate processing at multiple levels and thus, may not generalize to naturalistic visual behavior. Visual memory is assumed to rely on high-level visual perception that shows a level of size invariance and therefore is not assumed to be highly dependent on image size. Here, we reasoned that during naturalistic vision, free of task-related modulations, bigger images stimulate more visual system processing resources (from retina to cortex) and would, therefore, be better remembered. In an extensive set of seven experiments, naïve participants (n = 182) were asked to freely view presented images (sized 3° to 24°) without any instructed encoding task. Afterward, they were given a surprise recognition test (midsized images, 50% already seen). Larger images were remembered better than smaller ones across all experiments (∼20% higher accuracy or ∼1.5 times better). Memory was proportional to image size, faces were better remembered, and outdoors the least. Results were robust even when controlling for image set, presentation order, screen resolution, image scaling at test, or the amount of information. While multiple factors affect image memory, our results suggest that low- to high-level processes may all contribute to image memory.

An improved scheme for image scaling, cropping and colour correction in encrypted domain

While outsourcing of image storage and processing is an important service provided by cloud computing, ensuring data confidentiality in the cloud is one of the main concerns. Image processing in encrypted domain (or in a privacy-preserving manner), which performs operations over encrypted images, is receiving more and more attention. Having studied state-of-the-art solutions for image scaling, cropping and colour correction, we notice that the solutions are not compatible with each other so that there is no solution supporting all these operations; in addition, they all need extra overhead in image storage. In this work, we propose a scheme that supports image scaling, cropping, and colour correction in encrypted domain with minimum storage overhead. Its compatibility with modified Paillier-based cryptosystem scheme and optimised ElGamal cryptosystem is analysed. Storage performance is compared with existing solutions. Analysis shows storage requirement is drastically reduced while performance otherwise remains unchanged.

Tomato Leaf Disease Detection using Deep Learning Techniques

Plant diseases cause low agricultural productivity. Plant diseases are challenging to control and identify by the majority of farmers. In order to reduce future losses, early disease diagnosis is necessary. This study looks at how to identify tomato plant leaf disease using machine learning techniques, including the Fuzzy Support Vector Machine (Fuzzy-SVM), Convolution Neural Network (CNN), and Region-based Convolution Neural Network (R-CNN). The findings were confirmed using images of tomato leaves with six diseases and healthy samples. Image scaling, color thresholding, flood filling approaches for segmentation, gradient local ternary pattern, and Zernike moments’ features are used to train the pictures. R-CNN classifiers are used to classify the illness kind. The classification methods of Fuzzy SVM and CNN are analyzed and compared with R-CNN to determine the most accurate model for plant disease prediction. The R-CNN-based Classifier has the most remarkable accuracy of 96.735 percent compared to the other classification approaches.

Sequential ISAR Target Classification Based on Hybrid Transformer

To make full use of the sequential information obtained by continuous inverse synthetic aperture radar (ISAR) imaging, this article proposes a sequential ISAR target classification network based on hybrid transformer (HT). First, a temporal–spatial encoder based on the attention mechanism is designed to extract long-term and global features from sequential images. Meanwhile, a local feature encoder based on the 3-D convolution neural network is designed to extract short-term and local features. Then, the above two features are fused and the classification labels are obtained by a channel encoder–decoder. In 4-satellite target classification experiments, the proposed HT shows high accuracy and robustness to the unknown image scaling, rotation, and combined deformations.

Аналіз сучасних досягнень програмної інженерії для створення універсального алгоритму ASCII-ART конвертації

The paper considers the advantages of using ASCII-art technologies. The wide availability and popularity of textual communication channels encourages the use of ASCII-art to represent images. Modern approaches to creating a drawing in the ASCII-art style are analyzed. In the course of the study, various ways of creating ASCII drawings using computer programs were shown. Efficient modern algorithms for converting images into ASCII format have been identified. A perfect algorithm for converting an arbitrary image into ASCII format is proposed, which allows you to evaluate all the advantages of ASCII-art, such as small size of the picture, universality, internationality. Designed and developed a perfect and convenient mobile application that allows you to download the target image from the internal storage or instant photo from the camera and optimizes the process of converting images to ASCII-art. The designed system is a software application that provides more advanced functionality than existing analogues and is an independent product that is not based on any existing systems. To create a software application, a statically typed object-oriented programming language Kotlin was used, and AndroidStudio was chosen as an integrated development environment. The application is intended for sole use. The algorithm for converting images into an ASCII format consists of the following steps: preparing an image for processing, which makes it possible to eliminate incorrect image scaling in the ratio itself and image processing. Experiments were carried out on the independent creation of ASCII-art drawings. The obtained results indicate that the creation of modules for converting ASCII art images will reduce the amount of information stored on servers, attract new users by following the youth direction along with global trends and popularize ASCII graphics among already registered users. The use of the developed application will allow creative individuals to expand the ways of self-realization with the help of modern technologies, overcoming the limitations caused by the onset of the global COVID-19 pandemic. Drawings with symbols are a universal means of communication designed to connect humanity, overcome the barriers of natural languages and state borders.

Face Mask Wearing Detection Based on YOLOv5

Abstract In recent years, COVID-19 has swept the world, and people in crowded public places are usually large. In order to reduce the risk of virus transmission, stop the spread of the epidemic and reduce cross-infection, wearing masks correctly has become an important measure to prevent the virus. Aiming at the time-consuming and laborious situation of wearing masks manually, this paper proposes a mask wearing detection method based on yolov5. The input layer is mainly used for mosaic data enhancement, that is, adaptive anchor box and adaptive image scaling technology; Yolov5 in backbone mainly adopts focus and CSP (cross stage partial) structure; The neck layer adopts spp (spatial pyramid pooling) module and FPN (feature pyramid networks) + pan (pixel aggregation network) structure; The output mainly adopts ciou for the bounding box loss function_Loss is the average index of NMS (non maximum suppression). This method uses 8000 preprocessed images as the data set and trains 200 epochs to get the final model. The algorithm visually displays the training and test results through tensor board, and inputs the pictures captured by the camera into the model to detect whether the face wears a mask. The accuracy, recall and mean accuracy (map) of the algorithm on the test set are 94.8%, 89.0% and 93.5% respectively, which are higher than the detection results of yolov3 and yolov4 algorithms.

Hand gesture recognition algorithm combining hand-type adaptive algorithm and effective-area ratio for efficient edge computing

Most existing gesture recognition algorithms have low recognition rates under rotation, translation, and scaling of hand images as well as different hand types. We propose a new hand gesture recognition algorithm that combines the hand-type adaptive algorithm and effective-area ratio based on feature matching. Samples are divided into several groups according to the subjects’ palm shapes and the algorithm is trained using self-collected data. The user’s hand type is paired with one of the sample libraries by the hand-type adaptive algorithm. To further improve the accuracy, the effective-area ratio of the gesture is calculated based on the minimum bounding rectangle, and the preliminary gesture is recognized by the effective-area ratio feature method. The results of experiments demonstrate that the proposed algorithm could accurately recognize gestures in real time and exhibits good adaptability to different hand types. The overall recognition rate is over 94%. The recognition rate still exceeds 93% when hand gesture images are rotated, translated, or scaled.

Adaptive UNet-based Lung Segmentation and Ensemble Learning with CNN-based Deep Features for Automated COVID-19 Diagnosis.

COVID-19 disease is a major health calamity in twentieth century, in which the infection is spreading at the global level. Developing countries like Bangladesh, India, and others are still facing a delay in recognizing COVID-19 cases. Hence, there is a need for immediate recognition with perfect identification of infection. This clear visualization helps to save the life of suspected COVID-19 patients. With the help of traditional RT-PCR testing, the combination of medical images and deep learning classifiers delivers more hopeful results with high accuracy in the prediction and recognition of COVID-19 cases. COVID-19 disease is recently researched through sample chest X-ray images, which have already proven its efficiency in lung diseases. To emphasize corona virus testing methods and to control the community spreading, the automatic detection process of COVID-19 is processed through the detailed medication reports from medical images. Although there are numerous challenges in the manual understanding of traces in COVID-19 infection from X-ray, the subtle differences among normal and infected X-rays can be traced by the data patterns of Convolutional Neural Network (CNN). To improve the detection performance of CNN, this paper plans to develop an Ensemble Learning with CNN-based Deep Features (EL-CNN-DF). In the initial phase, image scaling and median filtering perform the pre-processing of the chest X-ray images gathered from the benchmark source. The second phase is lung segmentation, which is the significant step for COVID detection. It is accomplished by the Adaptive Activation Function-based U-Net (AAF-U-Net). Once the lungs are segmented, it is subjected to novel EL-CNN-DF, in which the deep features are extracted from the pooling layer of CNN, and the fully connected layer of CNN are replaced with the three classifiers termed “Support Vector Machine (SVM), Autoencoder, Naive Bayes (NB)”. The final detection of COVID-19 is done by these classifiers, in which high ranking strategy is utilized. As a modification, a Self Adaptive-Tunicate Swarm Algorithm (SA-TSA) is adopted as a boosting algorithm to enhance the performance of segmentation and detection. The overall analysis has shown that the precision of the enhanced CNN by using SA-TSA was 1.02%, 4.63%, 3.38%, 1.62%, 1.51% and 1.04% better than SVM, autoencoder, NB, Ensemble, RNN and LSTM respectively. The comparative performance analysis on existing model proves that the proposed algorithm is better than other algorithms in terms of segmentation and classification of COVID-19 detection.

Identity verification using palm print microscopic images based on median robust extended local binary pattern features and k-nearest neighbor classifier.

Automatic identity verification is one of the most critical and research-demanding areas. One of the most effective and reliable identity verification methods is using unique human biological characteristics and biometrics. Among all types of biometrics, palm print is recognized as one of the most accurate and reliable identity verification methods. However, this biometrics domain also has several critical challenges: image rotation, image displacement, change in image scaling, presence of noise in the image due to devices, region of interest (ROI) detection, or user error. For this purpose, a new method of identity verification based on median robust extended local binary pattern (MRELBP) is introduced in this study. In this system, after normalizing the images and extracting the ROI from the microscopic input image, the images enter the feature extraction step with the MRELBP algorithm. Next, these features are reduced by the dimensionality reduction step, and finally, feature vectors are classified using the k-nearest neighbor classifier. The microscopic images used in this study were selected from IITD and CASIA data sets, and the identity verification rate for these two data sets without challenge was 97.2% and 96.6%, respectively. In addition, computed detection rates have been broadly stable against changes such as salt-and-pepper noise up to 0.16, rotation up to 5°, displacement up to 6 pixels, and scale change up to 94%.

Increasing Message Capacity in Images Using Advanced Least Significant Bit and Image Scaling

Purpose: Steganography is the science of writing hidden or hiding messages so that apart from the sender and the recipient, no one can know or realize that a message is hidden. This paper aims to analyze the method of advanced LSB to increase message capacity. Methods/Study design/approach: The steganography technique advanced LSB algorithm develops pre-existing steganographic algorithms such as LSB by utilizing a range of media pixel values cover (images that are used as media to hide messages) with different insertion rules from LSB. Image scaling in digital image processing is known as resampling. Resampling is a mathematical technique used to produce a new image from the previous image with different pixel size, often called interpolation. Increasing the pixel size of the previous image is called upsampling and in this study we will only use twice the image magnification. Result/Findings: The results of each test method using advanced LSB without image scaling and advanced LSB using image scaling were compared to obtain detailed comparison results of each method. Novelty/Originality/Value: Advanced LSB and image scaling in this study can increase the message capacity three times compared to only using the advanced LSB method without image scaling. It depends on the image pixels used.

HoloUS: Augmented reality visualization of live ultrasound images using HoloLens for ultrasound-guided procedures

Microsoft HoloLens is a pair of augmented reality (AR) smart glasses that could improve the intraprocedural visualization of ultrasound-guided procedures. With the wearable HoloLens headset, an ultrasound image can be virtually rendered and registered with the ultrasound transducer and placed directly in the practitioner's field of view. A custom application, called HoloUS, was developed using the HoloLens and a portable ultrasound machine connected through a wireless network. A custom 3D-printed case with an AR-pattern for the ultrasound transducer permitted ultrasound image tracking and registration. Voice controls on the HoloLens supported the scaling and movement of the ultrasound image as desired. The ultrasound images were streamed and displayed in real-time. A user study was performed to assess the effectiveness of the HoloLens as an alternative display platform. Novices and experts were timed on tasks involving targeting simulated vessels using a needle in a custom phantom. Technical characterization of the HoloUS app was conducted using frame rate, tracking accuracy, and latency as performance metrics. The app ran at 25 frames/s, had an 80-ms latency, and could track the transducer with an average reprojection error of 0.0435 pixels. With AR visualization, the novices' times improved by 17% but the experts' times decreased slightly by 5%, which may reflect the experts' training and experience bias. The HoloUS application was found to enhance user experience and simplify hand-eye coordination. By eliminating the need to alternately observe the patient and the ultrasound images presented on a separate monitor, the proposed AR application has the potential to improve efficiency and effectiveness of ultrasound-guided procedures.

Limiting COVID-19 infection by automatic remote face mask monitoring and detection using deep learning with IoT

During the current outbreak of the COVID-19 pandemic, controlling and decreasing the possibilities of infections are massively required. One of the most important solutions is to use Artificial Intelligence (AI), which combines both fields of deep learning (DL) and the Internet of Things (IoT). The former one is responsible for detecting any face, which is not wearing a mask. Whereas, the latter is exploited to manage the control for the entire building or a public area such as bus, train station, or airport by connecting a Closed-Circuit Television (CCTV) camera to the room of management. The work is implemented using a Core-i5 CPU workstation attached with a Webcam. Then, MATLAB software is programmed to instruct both Arduino and NodeMCU (Micro-Controller Unit) for remote control as IoT. In terms of deep learning, a 15-layer convolutional neural network is exploited to train 1,376 image samples to generate a reference model to use for comparison. Before deep learning, preprocessing operations for both image enhancement and scaling are applied to each image sample. For the training and testing of the proposed system, the Simulated Masked Face Recognition Dataset ( SMFRD) has been exploited. This dataset is published online. Then, the proposed deep learning system has an average accuracy of up to 98.98 %, where 80 % of the dataset was used for training and 20 % of the samples are dedicated to testing the proposed intelligent system. The IoT system is implemented using Arduino and NodeMCU_TX (for transmitter) and RX (for receiver) for the signal transferring through long distances. Several experiments have been conducted and showed that the results are reasonable and thus the model can be commercially applied

The Effect of Ultrasonic Instrumentation on Finish Line Integrity

Purpose: Ultrasonic scaler is frequently used for temporary cement remnants removal from abutment teeth. A major concern is the alteration of the structural integrity of the abutment finishing line by the ultrasonic scaler. The current study evaluates the influence of ultrasonic scaling on the integrity of the finish line. The effect of finish line design (chamfer or feather edge), and its location (dentin or enamel) was also evaluated. Methods: Intact 22 human extracted molars were divided into 2 groups: finish line was prepared on enamel (n=11) and dentin (n=11), and further subdivided to finish line configuration groups (chamfer or knife-edge). Preparation of finish line was preformed following a standard repetitive procedure. 3D scans of the same tooth before and after ultrasonic instrumentation were performed. Pre and post scaling images were superimposed. The finish line alterations were evaluated and measured. The significance of the differences was evaluated using Students’ t-test. Results: The average alteration at the finish line area following ultrasonic scaling was 71.5 ± 24.6 μm. Higher alterations were found for enamel and for chamfer finish lines compared to dentin and knife edge, 134.4 ± 61.4 μm and 30.3 ±11.7 μm respectively. The highest change (228.6μm) was found for chamfer finish line located on enamel. The differences between groups were statistically significant (p<0.05). Conclusion: Ultrasonic scaling alters the topography of the finish line area of abutment teeth and thus may compromise marginal fit and integrity of the final restoration.

An 11-Categorical AI Food Classification Model Based on Mobile-Net Neural Networks

As obesity becomes increasingly common worldwide [1], more people want to lose weight to improve their health and image. According to the Centers for Disease Control and Prevention (CDC), long-term changes in daily eating habits (such as regarding food/ nutrition type, calorie intake) are successful at keeping weights off [2]. Therefore, it would be helpful to have an artificial intelligence (AI) mobile program that identifies the types of food the user consumes and automatically calculates the total calories. This paper examines the development and optimization of an 11-categorical food classification model based on the Mobile-Net neural network using Python. Specifically, it classifies any food image as one of bread, dairy, dessert, egg product, fried food, meat, noodles, rice, seafood, soup, or fruit/vegetables. Methods of optimization include data preprocessing and learning rate and batch size adjustments. Experimental results show that scaling image inputs to standard size (Python Numpy resize) function), 300 training epochs, dynamic learning rate (start with 0.001 and *0.1 for every 30 epochs), and a batch size of 16 yields our best model of 83.44% accuracy.