Picture Quality Research Articles

Classical Dance Hand Gesture Recognition using Image Processing and Deep Learning

Recognition of Dance posture & hand gesture in dance is most important. To get the exact names of these mudras some expertise should be there. So without expertise our proposed system recognizes the dance posture and hand geture. Indian classical dance traditionally performed as an expressive show dance type of strict execution workmanship, connected with Vedic writing. It's likewise a method of articulation of inward sentiments, assisting with creating self-conviction and fearlessness. Significance of old style dance is the activity of the whole self. Due to picture names, picture quality, uneven dataset and pixels values the accuracy is not good. So our proposed system implies the CNN and Deep Learning algorithm to recognizes the Dance posture and Hand gesture. Our system is used for all users who are interested in dance. Without a teacher can get the dance posture details. Introduced here Kathakali and Bharatnatyam Hand Mudras. Referred Kaggale site for dataset and also we added our own dataset. Each image recognizes the proper name and gives in the form sound also of Hand Mudra. Gaussian algorithm is used for more accuracy purpose.

Use of a three-dimensional head-mounted digital visualization platform in cataract surgery.

To report preliminary experience using the BeyeonicsOne (Beyeonics Vision, Haifa, Israel) digital visualization platform and the utilization of its three-dimensional (3D) head-mounted display(HMD) in cataract surgery. An interventional case series including patients who underwent cataract surgery using the 3D HMD platform at the Tel Aviv Medical Center. The system uses the HMD unit to display high-resolution real-time 3D surgical field images. Collected data included patient demographics, ocular comorbidities, risk factors for complex cataract surgery, cataract grading, preoperative and postoperative best-corrected visual acuity (BCVA), and intra- and postoperative complications. In total, 60 eyes of 60 subjects (mean age 73.1 ± 8.4 years) were included. Mean preoperative BCVA was 0.40 ± 0.30 logMAR (Snellen equivalent ~20/50) and improved to 0.10 ± 0.10 logMAR (Snellen equivalent ~20/25, p < 0.001). None of the patients suffered BCVA loss. All procedures and follow-ups were uneventful except for one case of a posterior capsular tear and one case of post-surgical cystoid macular edema. The visualization platform and its embedded 3D head-mounted display can be easily used in routine cataract surgery with the added benefits of improved ergonomics, high picture quality and enhanced image control.

Minimally invasive microsurgical decompression of the lumbar spine using a novel robotised digital microscope: A preliminary experience.

The operative microscope (OM) represents, to date, the standard for neurosurgical procedures. However, new technologies have been proposed during the latest years to overcome its limitations, from high-quality exoscopes to complex robotised visualisation systems. We report our preliminary experience with a novel digital robotised microscope, the BHS RoboticScope (RS), for minimally invasive spinal surgery. We employed the RS in five consecutive patients who underwent bilateral lumbar spine decompression through a monolateral approach. Patient outcomes, device technical characteristics and the surgeon's personal perspectives have been evaluated. No complications occurred. All procedures were concluded without switching to the microscope. Image quality, lightning, depth perception and freedom of movement were judged satisfactory as compared to the standard microscope. The easy maneuverability and the high quality of pictures provided by the RS device improve the surgeon's comfort in deep fields, representing an effective option for minimally invasive spinal procedures.

Recognizability bias in citizen science photographs.

Citizen science and automated collection methods increasingly depend on image recognition to provide the amounts of observational data research and management needs. Recognition models, meanwhile, also require large amounts of data from these sources, creating a feedback loop between the methods and tools. Species that are harder to recognize, both for humans and machine learning algorithms, are likely to be under-reported, and thus be less prevalent in the training data. As a result, the feedback loop may hamper training mostly for species that already pose the greatest challenge. In this study, we trained recognition models for various taxa, and found evidence for a 'recognizability bias', where species that are more readily identified by humans and recognition models alike are more prevalent in the available image data. This pattern is present across multiple taxa, and does not appear to relate to differences in picture quality, biological traits or data collection metrics other than recognizability. This has implications for the expected performance of future models trained with more data, including such challenging species.

VALUE OF PERIODICALLY ROTATED OVERLAPPING PARALLEL LINES WITH ENHANCED RECONSTRUCTION TECHNIQUE COMPARED TO T2 WEIGHTED TURBO SPIN ECHO SEQUENCE ON ROTATOR CUFF INJURIES IN MRI SHOULDER.

Objective: The purpose of the study is to analyze the uses of conventional T2 sequences and PROPELLER technique in view of artifact reduction, increase the image quality and identify signs of pathology on shoulder magnetic resonance imaging. A total number of 36 Materials and Method: patients who underwent shoulder MRI with pain intolerance were included in the study. We used PROPELLER and without PROPELLER technology in the same participants. The MRI scans were evaluated separately by qualied musculoskeletal radiologists. Artifacts, overall image quality, and delineation of several anatomic structures were all investigated in relation to the diagnostic value of an MR arthrography examination. The signicance of propeller was analyzed by implementing Mann Whitney U test. The TSE sequences had worse pulsation artifacts and Results: better overall image quality than PROPELLER sequences. In both Coronal Oblique and Sagittal Oblique approach, delineation of all addressed anatomic structures was much better with PROPELLER sequences than with TSE. The PROPELLER approach for MRI of the Conclusion: shoulder minimizes the frequency of sequences with diagnostic impairment owing to motion artifacts and enhances picture quality when compared to traditional TSE sequences.

Dynamic Interference Suppression for TV White Space: the Case of Thailand

In this work, we study the problem of co-existence between the LTE (Long Term Evolution) and the Digital Terrestrial Television Broadcasting (DTTB) channel. There are three scenarios: co-channel, upper and lower adjacent channels. We use the broadcasted signal from channel 3 called ThaiPBS, the actual case of Thailand for our study where the standard of digital terrestrial television broadcasting is DVB-T2 adopting 8 MHz bandwidth, while the 5 MHz bandwidth of LTE is considered as the interference. We propose a dynamic interference suppression method for increasing spectrum usage by optimizing TV white space utilization and minimizing interference. This method adopts the protection ratio concept to suppress the LTE interference on TV receiver. We implement our proposed algorithm as an adaptive interference controller using a Radio Frequency (RF) attenuator and a Raspberry Pi board for our testbed hardware. We illustrate the effectiveness of our proposed algorithm by doing experiment using our testbed and assessing the quality of the received TV signal by adopting the Quality of Experience (QoE) assessment. In our testbed hardware, a Log Periodic antenna is used for receiving the DTTB signal, while an RF digital transmitter is used for generating a 5MHz bandwidth of LTE signal, an ultra-high frequency (UHF) mixer is used to combine both signals, then a field strength meter is used to monitor video picture quality and to analyze the spectrum. According to the experiment, our proposed method can reduce the perceived video distortion by at least 62.5% for co-channel and 87.5% for adjacent channel, while the spectrum usage is increased by 100%.

Analisa Deteksi dan Pengenalan Wajah pada Citra dengan Permasalahan Visual

Facial recognition is a significant part of criminal investigations because it may be used to identify the offender when the criminal's face is consciously or accidentally recorded on camera or video. However, a majority of these digital photos have poor picture quality, which complicates and lengthens the process of identifying a face image. The purpose of this study is to discover and identify faces in these low-quality digital photographs using the Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) face identification method and the Viola-Jones face recognition method. The success percentage for the labeled face in the wild (LFW) dataset is 63.33%, whereas the success rate for face94 is 46.66%, while LDA is only a maximum of 20% on noise and brightness. One of the names and faces from the dataset is displayed by the facial recognition system. The brightness of the image, where the facial item is located, and any new objects that have entered the scene have an impact on the success rate.

Performance evaluation of image fusion techniques and implementation of new fusion technique for remote sensing satellite data

The technique of integrating images from two or more sensors that were taken from the same place or the same object is known as image fusion. The goal is to get more spectral and spatial information from the combined image as a whole than from the individual images. It is required to fuse the images in order to improve the spatial and spectral quality of both panchromatic and multispectral images. This study introduces a novel method for fusing remote sensing images that combines L0 smoothing, NSCT (Non-subsampled Contourlet Transform), SR (Sparse Representation), and MAR (Max absolute rule). The multispectral and panchromatic images are initially divided into lower and higher frequency components using the L0 smoothing filter as the method of fusion. The fusion process is then carried out, utilising a technique that combines NSCT and SR to fuse low-frequency components. Similar to this, the Max-absolute fusion rule is used to fuse high-frequency components. In conclusion, the disintegration of fused low-frequency and high-frequency data yields the final image. Our method yields an enhanced outcome in terms of the correlation coefficient, Entropy, spatial frequency, and fusion of mutual information for both the term of picture quality enhancement and visual evaluation. This suggested approach produces superior outcomes after execution. This study makes use of the Landsat-7ETM+, IKONOS, and Quick Bird datasets. Different satellites are used to take each image. There have been two examples of each image used. In comparison to previous Traditional Methods, the proposed image fusion techniques’ output has a quality that is more than 20% higher.

A STUDY ON PREFERENCES OF CONSUMERS TOWARDS INTERNATIONAL OTT PLATFORMS AND SUSTAINABILITY STRATEGY IN INDIAN MARKET

There are several social benefits generated by digital platforms, including facilitating inclusion. Communication services have been critical in accelerating the inclusion of marginalized users into formal systems, particularly for financial, health, and education services that are enabled by OTT providers. Using OTT platforms places a significant strain on energy resources, services providing music and video streaming have a far lower carbon footprint than traditional physical formats.&#x0D; Over The Top (OTT) industry is one of the fastest growing industries in the world. The usageofOTTplatformsinIndiahastremendouslyincreasedafterCOVID19.ThereasonsforthisismobilefriendlyandtheoriginalcontentthattheseOTTplatformsprovide.In India, big international players like Netflix entered and changed the entertainment industry making platform for more international as well as Indian OTT platforms. This study focuses on various international OTT platforms in India and their performance in Indian Market. The study attempts to identify current international OTT platform trends with reference to type of shows preferred by customers &amp; investigate OTT platform success factors in India. The research concluded that majority of the people preferred Netflix, followed by Disney+ HotStar and Amazon Prime Video. The respondent’s shows liking towards OTT which focus more on Original Shows and Web Series which gets frequently updating list just like Netflix. It was also observed that Disney+ HotStaris more preferred as they of digital broadcasting partner for big cricket events like IPL and World Cup. The research concludes that localization of content, affordable pricing, high quality picture quality, strong distributorship partnership, good user experience and better after sales services are the major factor for success of international OTT in Indian Market.

Single Image Reflection Removal Based on Residual Attention Mechanism

Affected by shooting angle and light intensity, shooting through transparent media may cause light reflections in an image and influence picture quality, which has a negative effect on the research of computer vision tasks. In this paper, we propose a Residual Attention Based Reflection Removal Network (RABRRN) to tackle the issue of single image reflection removal. We hold that reflection removal is essentially an image separation problem sensitive to both spatial and channel features. Therefore, we integrate spatial attention and channel attention into the model to enhance spatial and channel feature representation. For a more feasible solution to solve the problem of gradient disappearance in the iterative training of deep neural networks, the attention module is combined with a residual network to design a residual attention module so that the performance of reflection removal can be ameliorated. In addition, we establish a reflection image dataset named the SCAU Reflection Image Dataset (SCAU-RID), providing sufficient real training data. The experimental results show that the proposed method achieves a PSNR of 23.787 dB and an SSIM value of 0.885 from four benchmark datasets. Compared with the other most advanced methods, our method has only 18.524M parameters, but it obtains the best results from test datasets.

Dynamics of optical solitons in the (2 + 1)-dimensional chiral nonlinear Schrödinger equation

The [Formula: see text]-dimensional chiral nonlinear Schrödinger equation (CNLSE), which specifies the edge states of the Hall effect, is presented in this study. A complicated transformation is performed, and the bifurcation conditions are determined using the theory of planar dynamical systems. The phase pictures of the system are then produced using quantitative analysis in order to predict the family of solutions which can be found for the equation studied. It is important to note that this prediction is usually not made. The qualities of phase pictures are then used to obtain the exact solutions. As a result, this model produces some bright solitons, dark solitons and periodic wave solitons. Some of the solutions are graphically depicted in three dimensions (3D) using Matlab software to aid comprehension, and they play an important part in the creation of realistic Quantum Hall effects when Chiral excitations are known to occur. The method applied in this paper is simple and does not need an ansatz to predict the solutions as in the literature.

The Development of a Massive Open Online Course (MOOC) in Nursing Care for Patients with Myocardial Infarction

The purposes of this study were to 1) develop the Massive Open Online Course (MOOC) in nursing care for patients with myocardial infarction, 2) examine the learning achievement after learning with the MOOC, and 3) To examine satisfaction towards the MOOC in nursing care for patients with myocardial infarction. The sample consisted of 453 learners who enrolled in nursing care for patients with myocardial infarction through the PSUMOOC system. The MOOC was developed considering components to facilitate learning, including video, learning activities, and self-tests. The instruments used in this study were 1) Achievement Test and 2) Satisfaction Towards MOOC Questionnaire developed by the researchers. The validity and reliability of the instrument were assessed. The differences in learners’ scores before and after studying the MOOC, and satisfaction towards the MOOC were examined. Data were analyzed using descriptive statistics and paired t-tests. The findings revealed that there was a statistically significantly higher mean score of the learners’ scores at the posttest than at the pretest (p &lt; 0.01), indicating higher learning achievement. The learners were very satisfied towards the MOOC in the dimensions of up-to-date content, learning activities, quality of pictures and graphics, and colors used in media of the course.

Helping Visually Impaired People Take Better Quality Pictures.

Perception-based image analysis technologies can be used to help visually impaired people take better quality pictures by providing automated guidance, thereby empowering them to interact more confidently on social media. The photographs taken by visually impaired users often suffer from one or both of two kinds of quality issues: technical quality (distortions), and semantic quality, such as framing and aesthetic composition. Here we develop tools to help them minimize occurrences of common technical distortions, such as blur, poor exposure, and noise. We do not address the complementary problems of semantic quality, leaving that aspect for future work. The problem of assessing, and providing actionable feedback on the technical quality of pictures captured by visually impaired users is hard enough, owing to the severe, commingled distortions that often occur. To advance progress on the problem of analyzing and measuring the technical quality of visually impaired user-generated content (VI-UGC), we built a very large and unique subjective image quality and distortion dataset. This new perceptual resource, which we call the LIVE-Meta VI-UGC Database, contains 40K real-world distorted VI-UGC images and 40K patches, on which we recorded 2.7M human perceptual quality judgments and 2.7M distortion labels. Using this psychometric resource we also created an automatic limited vision picture quality and distortion predictor that learns local-to-global spatial quality relationships, achieving state-of-the-art prediction performance on VI-UGC pictures, significantly outperforming existing picture quality models on this unique class of distorted picture data. We also created a prototype feedback system that helps to guide users to mitigate quality issues and take better quality pictures, by creating a multi-task learning framework. The dataset and models can be accessed at: https://github.com/mandal-cv/visimpaired.

Diagnosis of Prostate Cancer Using GLCM Enabled KNN Technique by Analyzing MRI Images.

Cancer has a disproportionately large influence on the death rate of adults. A patient needs to get a diagnosis of their condition as quickly as is humanly feasible in order to have the greatest chance of surviving their sickness. Skilled medical professionals use medical imaging and other traditional diagnostic methods to search for clues that may indicate the presence of malignant tendencies inside the body. Nevertheless, manual diagnosis may be time-consuming and subjective owing to the wide range of interobserver variability induced by the enormous number of medical imaging data. This variability is caused by the fact that medical imaging data are collected. Because of this, the process of accurately diagnosing a patient could become more difficult. To execute jobs that included machine learning and the interpretation of complicated imagery, cutting-edge computer technology was necessary. Since the 1980s, researchers have been working on developing a computer-aided diagnostic system that would help medical professionals in the early diagnosis of various malignancies. According to the most recent projections, prostate cancer will be discovered in the body of one out of every seven men at some time throughout the course of their life. It is unacceptable how many men are being told that they have prostate cancer, and the condition is responsible for the deaths of a rising number of men every year. Because of the high quality and multidimensionality of the MRI pictures, you will also need a powerful diagnosis system in addition to the CAD tools. Since it has been shown that CAD technology is beneficial, researchers are looking at methods to improve the accuracy, precision, and speed of the systems that use it. The effectiveness of CAD technology has been shown. This research proposes a strategy that is both effective and efficient for the processing of images and the extraction of features as well as for machine learning. This work makes use of MRI scans and machine learning in an effort to detect prostate cancer at an early stage. Histogram equalization is used while doing the preliminary processing on photographs. The image's overall quality is elevated as a result. The fuzzy C means approach is used in order to segment the images. Using a Gray Level Cooccurrence Matrix (GLCM), it is feasible to extract features from a dataset. The KNN, random forest, and AdaBoost classification algorithms are used in the classification process.

PRAM: Penalized Resource Allocation Method for Video Services

Abstract The human visual system response to picture quality degradation due to packet loss is very different from the responses of objective quality measures. While video quality due to packet loss may be impaired by at most for one Group of Pictures (GOP), its subjective quality degradation may last for several GOPs. This has a great impact on resource allocation strategies, which normally make decisions on instantaneous conditions of multiplexing buffer. This is because, when the perceptual impact of degraded video quality is much longer than its objective degradation period, any assigned resources to the degraded flow is wasted. This paper, through both simulations and analysis shows that, during resource allocation, if the quality of a video stream is significantly degraded, it is better to penalize this degraded flow from getting its full bandwidth share and instead assign the remaining share to other flows preventing them from undergoing quality degradation.

Employing U-NET and Rotational Based Convolutional Neural Network to Build an Automatic Lung Cancer Segmentation and Classification System

The most common cancer-related cause of death globally is lung cancer. The key to effective lung cancer treatment and higher survival rates is early diagnosis. Converting a radiologist's diagnosing procedure to computer assisted results in more accurate results and an earlier diagnosis. The difficulty is that building an effective model for segmentation and classification. In this paper, we suggest a system for detecting lung cancer that makes use of a number of methods for precise and effective diagnosis. To enhance picture quality, our method pre-processes CT scan images using a Gaussian filter and contrast stretching. For the purpose of determining the borders of lung nodules with high precision, the U-Net architecture with the Adam optimizer is used. Then, a Gaussian mixture model (GMM) with EM optimisation and pixel padding is used to extract features. The rotational-based Convolutional Neural Network (RBCNN) classifier successfully categorises the nodules as benign and malignant using these form variables as inputs

Night Vision Object Tracking System Using Correlation Aware LSTM-Based Modified Yolo Algorithm

Improved picture quality is critical to the effectiveness of object recognition and tracking. The consistency of those photos is impacted by night-video systems because the contrast between high-profile items and different atmospheric conditions, such as mist, fog, dust etc. The pictures then shift in intensity, colour, polarity and consistency. A general challenge for computer vision analyses lies in the horrid appearance of night images in arbitrary illumination and ambient environments. In recent years, target recognition techniques focused on deep learning and machine learning have become standard algorithms for object detection with the exponential growth of computer performance capabilities. However, the identification of objects in the night world also poses further problems because of the distorted backdrop and dim light. The Correlation aware LSTM based YOLO (You Look Only Once) classifier method for exact object recognition and determining its properties under night vision was a major inspiration for this work. In order to create virtual target sets similar to daily environments, we employ night images as inputs; and to obtain high enhanced image using histogram based enhancement and iterative wiener filter for removing the noise in the image. The process of the feature extraction and feature selection was done for electing the potential features using the Adaptive internal linear embedding (AILE) and uplift linear discriminant analysis (ULDA). The region of interest mask can be segmented using the Recurrent-Phase Level set Segmentation. Finally, we use deep convolution feature fusion and region of interest pooling to integrate the presently extremely sophisticated quicker Long short term memory based (LSTM) with YOLO method for object tracking system. A range of experimental findings demonstrate that our technique achieves high average accuracy with a precision of 99.7% for object detection of SSAN datasets that is considerably more than that of the other standard object detection mechanism. Our approach may therefore satisfy the true demands of night scene target detection applications. We very much believe that our method will help future research.

A Comprehensive Survey on Face Quality Detection in a Video Frame

The correctness of the generated face data, which is impacted by a number of variables, significantly affects how well face analysis and recognition systems perform. By automatically analysing the face data quality in terms of its biometric value, it might be able to identify low-quality data and take the necessary action. With a focus on visible wavelength face image input, this study summarises the body of research on the evaluation of face picture quality. The use of DL-based methods is unquestionably expanding, and there are major conceptual differences between them and current approaches, such as the inclusion of quality assessment in face recognition models. In addition to image selection, which is the topic of this article, face picture quality assessment can be used in a wide range of application scenarios. The requirement for comparative algorithm assessments and the difficulty of creating Deep Learning (DL) techniques that are intelligible in addition to providing accurate utility estimates are just a few of the issues and topics that remain unanswered. For each frame, the suggested method is compared to traditional facial feature extraction, and for a collection of video frames, it is compared to well-known clustering algorithms.

Secret image scrambling and DWT-based image steganography using smoothing operation and convolution neural networks

Steganography is known as a secret data sharing technique. It is a method of data protection which allows the user to send the information in enveloped form. That means the hidden data cannot be seen by the observer because one can only see the enveloped media. This paper presents a steganography technique using Pixel swapping-Quantum Hilbert image scrambling and discrete wavelet transformation, followed by stego image smoothing operation. Initial steps of proposed image steganography include best suitable cover image selection for secret image. This process compares the secret image with the different cover image presents in senders cover image database. Before embedding (encoding), the secret image is scrambled, and then performs the DWT transformation on this scrambled image and cover image. Next steps embed both resultant images and generate a new image named as stego image. The picture quality of stego image is increased using pixel swapping based operation. The Decoding process of proposed steganography scheme is just reverse of the former encoding process followed by application of Convolutional neural networks (CNN) to improve the extracted secret image quality. The results show the strength of the proposed technique.

Image segmentation techniques using python and deep learning

Computer vision is one of the most important technology emerging in the IT market. Computer vision is a way to provide a powerful ability to see and interpret the real-time objects to the computer just like us or possibly even better than us. An image segmentation is the key processes in machine vision. It is the method of separate a high quality picture into non-overlapping multiple regions to get more precise and significant result. This technique provide us much more granular and reliable information about images like shape, color, and texture, etc. Image segmentation makes a huge impression in Image compression or Object detection techniques, Content-based image retrieval, Video surveillance, Medical imaging, and Traffic control system, etc. It is efficient to process small segments of images one by one to gather information and renounce the regions without information than to process an entire image for particular information. So, image segmentation is help us to dividing image into small segments for advance processing. We can divide a digital image using properties of images such as pixel values, intensity value, texture, shape, etc. So, we can achieve image segmentation by segmenting the images based on these properties. There are many techniques through which one can achieve image segmentation. Here, we discussed multiple techniques apply to achieve image segmentation and compare their benefits and drawbacks followed by the conclusion.