Binary Masking Research Articles

MOVING OBJECTS DETECTION, CLASSIFICATION AND TRACKING OF VIDEO STREAMING BY IMPROVED FEATURE EXTRACTION APPROACH USING K-SVM

The computer vision plays a vital role in variety of applications such as traffic surveillance, robotics, human interaction devices, etc. The video surveillance system has designed to detect, track and classify the moving objects. The moving object detection, classification and tracking of video streaming has various challenges, which utilizes various novel approaches. The existing work uses spatiotemporal feature analysis using sample consistency algorithm for moving object detection and classification. It is not performed well with the complex scene on the video. The binary masking representation of moving object is the challenging task for the researchers. These video streams are partitioned based on the frames, shots, and scenes; here the proposed research work utilizes kernel-Support Vector Machine learning technique for moving object detection and tracking. In this approach, the MIO-TCD DATASET is used for moving object detection. Here the feature extraction is the major part of foreground and background analysis in the video streaming, which utilizes the vehicle features based video data. The SURF (Speeded-Up Robust Feature) feature is used to recognize/register the object and it also used for classification of moving objects. Here the optical flow method is to quantify the relative motion of object in the video streams. Based on the differences on the partitioned frames, the optical flow features hold the object for measuring the pixel of the moving objects. The feature extraction process is improved by combining feature class with intensity level of optical flow result, which makes the gradient analysis of first order derivative function. The proposed method achieves the result of recall, precision, and f-measures than the existing work. The proposed method is done with the help of MATLAB 2018a. Keywords: Computer Vision and Pattern Recognition; Kernel-SVM; SURF features; Optical Flow; Texture feature; Moving object detection, tracking and classification;

Invisible Unicode Programming

Invisible Unicode programming (IUP) can be defined as the art and science of hiding information in data that can be read by the computer. Invisible Unicode Programming (IUP) has the explicit goal of converting traditional character encodings to invisible encoding. This paper presents a new method to hide text. This systematic method uses the binary format of invisible character to hide and extract secret information. Creating a secret message involves four main steps, first using the binary format of the original letters in the message.nextcreating the appropriate Binary Masking Value (BMV)to cover the text, and subtracting the Binary Value (BV) from the Binary Masking Value (BMV)text to get Binary Invisible Unicode (BIU), and finally masking secret text using Binary Invisible Character (BIU). This Invisible Unicode Programming (IUP) Concept uses the 54 Invisible Unicode characters to make the text invisible. The results of the experiments show that this IUP method creates highly secured invisible information using the multi-level complexity algorithm to avoid the hackers.

Parameter Estimation for Precession Cone-Shaped Targets Based on Range–Frequency–Time Radar Data Cube

A radar echo signal received from a cone-shaped target with precession contains micro-Doppler (m-D) information from different effective scattering centers. By taking full advantage of the m-D information, this paper proposes a parameter estimation algorithm for precession cone-shaped targets based on the range–frequency–time radar data cube (RDC). We build scattering center models of precession cone-shaped targets with the occlusion effect. The Binary Mask method is first utilized to obtain a high-resolution range-Doppler (RD) sequence. On this basis, the range–frequency–time RDC can be extracted from the RD sequence. In order to approach the actual case, we discuss the parameter estimation algorithm under different radar lines-of-sight (LOS). The most attractive attribute of this algorithm is that it can conduct in-depth research on m-D parameter estimation from a three-dimensional (3D) domain. Finally, the experimental results illustrate the effectiveness of the proposed method.

AFD-StackGAN: Automatic Mask Generation Network for Face De-Occlusion Using StackGAN.

To address the problem of automatically detecting and removing the mask without user interaction, we present a GAN-based automatic approach for face de-occlusion, called Automatic Mask Generation Network for Face De-occlusion Using Stacked Generative Adversarial Networks (AFD-StackGAN). In this approach, we decompose the problem into two primary stages (i.e., Stage-I Network and Stage-II Network) and employ a separate GAN in both stages. Stage-I Network (Binary Mask Generation Network) automatically creates a binary mask for the masked region in the input images (occluded images). Then, Stage-II Network (Face De-occlusion Network) removes the mask object and synthesizes the damaged region with fine details while retaining the restored face’s appearance and structural consistency. Furthermore, we create a paired synthetic face-occluded dataset using the publicly available CelebA face images to train the proposed model. AFD-StackGAN is evaluated using real-world test images gathered from the Internet. Our extensive experimental results confirm the robustness and efficiency of the proposed model in removing complex mask objects from facial images compared to the previous image manipulation approaches. Additionally, we provide ablation studies for performance comparison between the user-defined mask and auto-defined mask and demonstrate the benefits of refiner networks in the generation process.

Cloud-probability-based estimation of black-sky surface albedo from AVHRR data

Abstract. This paper describes a new method for cloud-correcting observations of black-sky surface albedo derived using the Advanced Very High Resolution Radiometer (AVHRR). Cloud cover constitutes a major challenge for surface albedo estimation using AVHRR data for all possible conditions of cloud fraction and cloud type with any land cover type and solar zenith angle. This study shows how the new cloud probability (CP) data to be provided as part of edition A3 of the CLARA (CM SAF cLoud, Albedo and surface Radiation dataset from AVHRR data) record from the Satellite Application Facility on Climate Monitoring (CM SAF) project of EUMETSAT can be used instead of traditional binary cloud masking to derive cloud-free monthly mean surface albedo estimates. Cloudy broadband albedo distributions were simulated first for theoretical cloud distributions and then using global cloud probability (CP) data for 1 month. A weighted mean approach based on the CP values was shown to produce very-high-accuracy black-sky surface albedo estimates for simulated data. The 90 % quantile for the error was 1.1 % (in absolute albedo percentage) and that for the relative error was 2.2 %. AVHRR-based and in situ albedo distributions were in line with each other and the monthly mean values were also consistent. Comparison with binary cloud masking indicated that the developed method improves cloud contamination removal.

Speech encryption using hybrid-hyper chaotic system and binary masking technique

Speech encryption using hybrid-hyper chaotic system and binary masking technique

Improving Millimeter Radar Attenuation Corrections in High-Latitude Mixed-Phase Clouds via Radio Soundings and a Suite of Active and Passive Instruments

Supercooled liquid clouds are very frequent in high-latitude regions. In addition to their substantial effect on visible and infrared radiation, they affect the signal of millimeter radars by producing nonnegligible attenuation. Such attenuation must be properly corrected if the information of millimeter radars is used in quantitative retrievals for inferring ice microphysical properties. This study proposes a multisensor scheme for refining the vertical distribution of supercooled liquid water content (SLWC) compared to state-of-the-art methods that equipartition the liquid water path measured by microwave radiometer to all pixels identified as cloudy by the radars and warmer than −40 °C. Our methodology is applicable in high-latitude, mixed-phase environments based on the synergy between radar and lidar binary cloud phase masking, microwave radiometer, and radio sounding observations. The technique is demonstrated via data collected by the U.S. Department of Energy (DoE) Atmospheric Radiation Measurement (ARM) Program climate research facility at the North Slope of Alaska (NSA) and compared with the state-of-the-art methods. Path integrated attenuation (PIA) at W- and G-band frequencies (>95 GHz) is then assessed. Results indicate that the different in-cloud distributions of the liquid condensate lead to round-trip PIA discrepancies of cloudy volumes that range in [2, 5] dB at W- and G-band frequencies. These differences far exceed those encountered when changing some of the algorithm’s arbitrary assumptions and weighting functions.

Land Cover Image Segmentation Based on Individual Class Binary Masks

Remote sensing techniques have been developed over the past decades to acquire data without being in contact of the target object or data source. Their application on land-cover image segmentation has attracted significant attention during recent years. With the help of satellites, scientists and researchers can collect and store high-resolution image data that can be further be processed, segmented, and classified. However, these research results have not yet been synthesized to provide coherent guidance on the effect of variant land-cover segmentation processes. In this paper, we present a novel model that augments segmentation using smaller networks to segment individual classes. The combined network is trained on the same data but with the masks, combined and trained using categorical cross entropy. Experimental results show that the proposed method produces the highest mean IoU (Intersection of Union) as compared against several existing state-of-the-art models on the DeepGlobe dataset.

Image processing algorithm to estimate ice-plant leaf area from RGB images under different light conditions

The productivity of horticultural crops in an artificial light condition are highly influenced by the structure of plant and the area coverage. Accurate measurement of leaf area is very important for predicting plant water demand and optimal growth. In this paper, we proposed an image processing algorithm to estimate the ice-plant leaf area from the RGB images under the artificial light condition. The images were taken using a digital camera and the RGB images were transformed to grayscale images. A binary masking was applied from a grayscale image by classifying each pixel, belonging to the region of interest from the background. Then the masked images were segmented and the leaf region was filled using region filling technique. Finally, the leaf area was calculated from the number of pixel and using known object area. The experiment was carried out in three different light conditions with same plant variety (Ice-plant, Mesembryanthemum crystallinum). The results showed that the correlation between the actual and measured leaf area was found over 0.97 (R2:0.973) by our proposed method. Different light condition also showed significant impact on plant growth. Our results inspired further research and development of algorithms for the specific applications.

Using ideal binary masking based on signal-to-noise ratio of temporal amplitude envelope to improve the intelligibility of speech in noise

Ideal Binary Masking (IBM), using prior information, improves speech intelligibility by attenuating noisy components with a scaling factor applied to the noise. The main challenge is to construct an appropriate decision-making model to identify noise- or speech- dominant components. In this study, we utilized the signal-to-noise ratio (SNR) of the temporal amplitude envelope in the frequency-time domain. We firstly divided the noisy speech from 200 Hz to 6 kHz, processed by MATLAB, into 16 contiguous subbands each with bandwidth approximately 1.5 times an equivalent rectangular bandwidth. The subband envelopes were produced by means of the absolute value of the signal. SNRs of the temporal envelope were calculated for 40 ms windows. The mask was unity when the SNR was greater than −5dB; otherwise, it was 0.5. We evaluated the performance of the proposed IBM on word scores obtained with different speech in speech-spectrum shaped noise SNR values of −2, −4, −6, and −8 dB. Sixteen native speakers (age 28 ± 3 years) with normal hearing were recruited for the study and underwent the Modified Rhyme Test to assess intelligibility. Statistically significant increases of up to 20% in mean word scores were obtained by this IBM. [Work supported by NIOSH.]

Robust phase retrieval with green noise binary masks

Phase retrieval with pre-defined optical masks can provide extra constraints and thus achieve improved performance. Recent progress in optimization theory demonstrates the superiority of random masks in enhancing the accuracy of phase retrieval algorithms. However, traditional approaches only focus on the randomness of the masks but ignore their non-bandlimited nature. When using these masks for phase retrieval, the intensity measurements contain many significant high-frequency components that the phase retrieval algorithm cannot take care of and thus leads to degraded performance. Based on the concept of digital halftoning, this paper proposes a green noise binary masking scheme that can significantly reduce the high-frequency contents of the masks while fulfilling the randomness requirement. The resulting intensity measurements will contain data concentrated in the mid-frequency band and around zero frequency areas which can be fully utilized in the phase retrieval optimization process. Our experimental results show that the proposed green noise binary masking scheme consistently outperforms the traditional ones when using in binary coded diffraction pattern phase retrieval systems.

Non Monte Carlo Method for Intrinsic Investigation of the Potential Use of Modified Uniformly Redundant Arrays (Muras) Coded Apertures for Early Breast Tumor Imaging

This is a continuous investigation of a possible application of Coded Aperture (CA) for breast tumor imaging. This paper describes a novel non-Monte Carlo method that based on a simple attractive approach called Binary Mask Shift.

Study of Optical Modulation based on Binary Masks with Finite Pixels

Binary holography has been applied with fast switching digital masks, e.g., digital micromirror device (DMD), to modulate light in recent years for a wide range of optical and scientific applications, such as trapping of cold atoms and 3D random-access two-photon fluorescence microscopy. However, the binarized modulation errors associated with the effect of discrete sampling, finite pixels, and intrinsic noises of algorithms have yet to be systematically investigated. In this paper, we present the development of an analytical model for a general binary mask with finite pixels. The model has established a deterministic link between the quality of the reconstructed wavefront to important parameters of the binary mask, including pixel size, pixel geometry, fill factor, and aperture. Based on the model, three case studies are presented, including (1) beam shaping, (2) 3D random-access scanning, and (3) multi-focus generation based on binary masks. The results show the model can precisely predict the wavefront distortion, power efficiency, position accuracy, and intensity uniformity for multi-focus generation as a function of binary mask parameters. As digital systems are highly repeatable, the predicted errors, e.g., position errors, can be compensated by adding appropriate phase to the designed holograms. The model and the simulation results may provide useful guidance to select appropriate binary devices and optimization algorithms for specific optical engineering applications, e.g., nanofabrication or nonlinear microscopy.

Unsupervised machine fault diagnosis for noisy domain adaptation using marginal denoising autoencoder based on acoustic signals

Recently, with the desperate demand for data-driven deep learning methods in practical industrial applications, increasing popularity of deep learning methods for machine fault diagnosis under noisy environments has been observed. However, the existing studies have encountered two limitations: 1) the domain shift problem has not been researched enough to ensure a functional adaptation model across different noisy domains; 2) those deep learning frameworks are generally complicated and require massive computational space. To address those problems, we propose a Noisy Domain Adaptive marginal Stacking Denoising Auto-encoder (NDAmSDA) based on acoustic signals for domain adaptation between different noise levels. Specifically, a modified mSDA, integrated with a dimensionality reduction method based on Transfer Component Analysis (TCA), not only facilitates the training acceleration by replacing the traditional gradient descent method of backpropagation with a forward closed-form solution, but also promotes gapping the discrepancy between various noise levels and transferring the classifier built from one noisy domain to others. This enables us to extend diagnostic models’ capability to real-world scenarios because of the unavoidable background noise in the collected signals. To validate the effectiveness of our proposed approach, datasets mixed with additive white Gaussian noise (AWGN) and binary masking noise (BMN) from the gear tests and motor tests are constructed for validation. Comparisons with representative and popular fault diagnosis approaches confirm the superiority of the proposed method.

The utility of built environment geospatial data for high-resolution dasymetric global population modeling

Several global gridded population data sets are available at unprecedented high-resolution, including recent releases at 100-m, 30-m, and 10-m resolution. These data sets are the result of the application of advanced methods to disaggregate census population counts from administrative units and facilitated by the proliferation of increasingly high-resolution spatial information pertaining to the built environment (e.g. built-up and building footprint data). Accordingly, these gridded population data are increasingly dependent on a single ancillary data set to inform the distribution of populations across space. Our study tests several combinations of binary masking variables (land areas, all building footprints, residential building footprints) and density variables (building footprint areas, building volumes) derived from characteristics of the built environment at 20× and 8000× downscaling using a flexible equation for high-resolution global dasymetric population modeling. The assessment is applied in New York City, where large spatial heterogeneities exist across confined geographic areas. Results confirm that the performance of the model generally improves as: (i) the binary masking variable becomes increasingly limiting; and, (ii) the density variable becomes more pronounced. However, application requires careful consideration due to their propensity to amplify both positive results and errors.

Interpreting a recurrent neural network’s predictions of ICU mortality risk

Deep learning has demonstrated success in many applications; however, their use in healthcare has been limited due to the lack of transparency into how they generate predictions. Algorithms such as Recurrent Neural Networks (RNNs) when applied to Electronic Medical Records (EMR) introduce additional barriers to transparency because of the sequential processing of the RNN and the multi-modal nature of EMR data. This work seeks to improve transparency by: 1) introducing Learned Binary Masks (LBM) as a method for identifying which EMR variables contributed to an RNN model’s risk of mortality (ROM) predictions for critically ill children; and 2) applying KernelSHAP for the same purpose. Given an individual patient, LBM and KernelSHAP both generate an attribution matrix that shows the contribution of each input feature to the RNN’s sequence of predictions for that patient. Attribution matrices can be aggregated in many ways to facilitate different levels of analysis of the RNN model and its predictions. Presented are three methods of aggregations and analyses: 1) over volatile time periods within individual patient predictions, 2) over populations of ICU patients sharing specific diagnoses, and 3) across the general population of critically ill children.

Speech Intelligibility Enhancement Algorithm Based on Multi-Resolution Power-Normalized Cepstral Coefficients (MRPNCC) for Digital Hearing Aids

Speech intelligibility enhancement in noisy environments is still one of the major challenges for hearing impaired in everyday life. Recently, Machine-learning based approaches to speech enhancement have shown great promise for improving speech intelligibility. Two key issues of these approaches are acoustic features extracted from noisy signals and classifiers used for supervised learning. In this paper, features are focused. Multi-resolution power-normalized cepstral coefficients (MRPNCC) are proposed as a new feature to enhance the speech intelligibility for hearing impaired. The new feature is constructed by combining four cepstrum at different time–frequency (T–F) resolutions in order to capture both the local and contextual information. MRPNCC vectors and binary masking labels calculated by signals passed through gammatone filterbank are used to train support vector machine (SVM) classifier, which aim to identify the binary masking values of the T–F units in the enhancement stage. The enhanced speech is synthesized by using the estimated masking values and wiener filtered T–F unit. Objective experimental results demonstrate that the proposed feature is superior to other comparing features in terms of HIT-FA, STOI, HASPI and PESQ, and that the proposed algorithm not only improves speech intelligibility but also improves speech quality slightly. Subjective tests validate the effectiveness of the proposed algorithm for hearing impaired.

Blind Adaptive Mask to Improve Intelligibility of Non-Stationary Noisy Speech

This letter proposes a novel blind acoustic mask (BAM) designed to adaptively detect noise components and preserve target speech segments in time domain. A robust standard deviation estimator is applied to the non-stationary noisy speech to identify noise masking elements. The main contribution of the proposed solution is the use of this noise statistics to derive an adaptive information to define and select samples with lower noise proportion. Thus, preserving speech intelligibility. Additionally, no information of the target speech and noise signals statistics is previously required to this non-ideal mask. The BAM and three competitive methods, Ideal Binary Mask (IBM), Target Binary Mask (TBM), and Non-stationary Noise Estimation for Speech Enhancement (NNESE), are evaluated considering speech signals corrupted by three non-stationary acoustic noises and six values of signal-to-noise ratio (SNR). Results demonstrate that the BAM technique achieves intelligibility gains comparable to ideal masks while maintaining good speech quality.

Corrections to “Binary Masks of Concentric Rings as a Method to Approximate Identification of Diatoms Using Images”

In the above article [1] , although references [2] – [6] to equations (1)–(11) presented in Section II-B “Concentric Ring Binary Masks” under Section II “Methods” are adequate to understand the framework related to image processing; the methodology of concentric ring binary masks was developed in [7] and [8] , the following changes should be considered in [1] :

Brown Spot Disease Severity Level Detection using Binary-RGB Image Masking

Agriculture is known as one of the main factor for a growth of a country. Paddy plantation is the most widely planted crop in Malaysia. The rice produced is the main food source to Malaysian’s people and source of income to this country as well. However, a disease known as Brown Spot (BS) attacks the paddy plants and threats their quality. This disease caused by bipolar fungus, which represent by the development of an oval, dark brown to purplish-brown spot on leaf. This disease observed as among the hazardous disease that may result in degradation of paddy production. Brown Spot disease could spread through airborne spores from plant to plant on the field. In this research, a system that could help people, especially farmers, to detect the disease at early stage is developed. The real image capture at paddy field is processed in the MATLAB software with image enhancement, background removal as well as binary and RGB image masking process. To determine the Brown Spot area, pixel intensity between the infected and non-infected areas is calculated. The severity level table developed by Horsfall and Heuberger is then used as reference to classify the severity level of Brown Spot disease. A GUI is created to detect the Brown Spot disease automatically. From the study conducted, the accuracy of Brown Spot detection is approximately 89% accurate compared to manual evaluation by plant pathology.