Binary Image Research Articles

Evaluation of the degree of starch pyrodextrinization by binary digital image colorimetry

Evaluation of the degree of starch pyrodextrinization by binary digital image colorimetry

Fabrication of PZT/PVDF composite film and the influence of homogeneity to dielectric constant

AbstractThe Lead Zirconate Titanate/polyvinylidene fluoride (PZT/PVDF) piezoelectric composite with various volume fractions of PZT is successfully fabricated by the proposed solution casting and hot press methods. The aim of this study is to determine the quality of the composite material being fabricated by its homogeneity. Homogeneity can be determined by computing the free path space between particles based on the binary image of SEM, using dispersion and distribution quantitative methods, to gain a comprehensive understanding of the particles' scattering conditions. In comparison to several selected models providing adjustable factors that are highly related to the effect of homogeneity of the composite's internal structure, a suitable model is found.

Deep Learning and Neural Architecture Search for Optimizing Binary Neural Network Image Super Resolution.

The evolution of super-resolution (SR) technology has seen significant advancements through the adoption of deep learning methods. However, the deployment of such models by resource-constrained devices necessitates models that not only perform efficiently, but also conserve computational resources. Binary neural networks (BNNs) offer a promising solution by minimizing the data precision to binary levels, thus reducing the computational complexity and memory requirements. However, for BNNs, an effective architecture is essential due to their inherent limitations in representing information. Designing such architectures traditionally requires extensive computational resources and time. With the advancement in neural architecture search (NAS), differentiable NAS has emerged as an attractive solution for efficiently crafting network structures. In this paper, we introduce a novel and efficient binary network search method tailored for image super-resolution tasks. We adapt the search space specifically for super resolution to ensure it is optimally suited for the requirements of such tasks. Furthermore, we incorporate Libra Parameter Binarization (Libra-PB) to maximize information retention during forward propagation. Our experimental results demonstrate that the network structures generated by our method require only a third of the parameters, compared to conventional methods, and yet deliver comparable performance.

Zigzag persistence for image processing: New software and applications

Topological image analysis is a powerful tool for understanding the structure and topology of images, being persistent homology one of its most popular methods. However, persistent homology requires a chain of inclusions of topological spaces, which can be challenging for digital images. In this article, we explore the use of zigzag persistence, a recent variant of traditional persistence, for digital image processing. To this end, new algorithms are developed to build a simplicial complex associated to a digital image and to compute the relationships between homology classes of a sequence of binary images via zigzag persistence. Additionally, we provide a simple software to use them. We demonstrate its effectiveness by applying it to a real-world problem of analyzing honey bee sperm videos.

A novel method of ultrasonic tomographic imaging of defects in the coating layer by image fusion and binarization techniques

A novel method of ultrasonic tomographic imaging of defects in the coating layer by image fusion and binarization techniques

Approximate ground truth generation for semantic labeling of historical documents with minimal human effort

Deep learning approaches have shown high performance for layout analysis of historical documents, provided that enough labeled data is available. This is not an issue for generic tasks such as image binarization, text graphics separation, or text line and text block detection but can become an impediment for more specialized tasks specific to one or a few books only. This paper addresses layout analysis of medieval books with rich and complex layouts, for which no labeled data is initially available. The proposed strategy consists of training an initial model with artificial data created to reflect the rules a deep neural network should learn. Then, the model is iteratively fine-tuned by mixing the artificial data with real data obtained by previous predictions, post-processed, and manually selected by an expert user. Such a strategy needs less human effort than manual ground truthing. The approach is qualitatively and quantitatively assessed and shows that the system converges to an accurate model that finally produces approximate ground truth stable and good enough to train a final model to solve the targeted task with high accuracy.

An Efficient Transformer–CNN Network for Document Image Binarization

Color image binarization plays a pivotal role in image preprocessing work and significantly impacts subsequent tasks, particularly for text recognition. This paper concentrates on document image binarization (DIB), which aims to separate an image into a foreground (text) and background (non-text content). We thoroughly analyze conventional and deep-learning-based approaches and conclude that prevailing DIB methods leverage deep learning technology. Furthermore, we explore the receptive fields of pre- and post-network training to underscore the Transformer model’s advantages. Subsequently, we introduce a lightweight model based on the U-Net structure and enhanced with the MobileViT module to capture global information features in document images better. Given its adeptness at learning both local and global features, our proposed model demonstrates competitive performance on two standard datasets (DIBCO2012 and DIBCO2017) and good robustness on the DIBCO2019 dataset. Notably, our proposed method presents a straightforward end-to-end model devoid of additional image preprocessing or post-processing, eschewing the use of ensemble models. Moreover, its parameter count is less than one-eighth of the model, which achieves the best results on most DIBCO datasets. Finally, two sets of ablation experiments are conducted to verify the effectiveness of the proposed binarization model.

A Comprehensive Study on Image Segmentation Using Pulse-Coupled Neural Networks

Pulse-Coupled Neural Network (PCNN) operates as a matrix of neurons, each uniquely corresponding to a pixel in the image being processed. Unlike traditional neural networks, PCNN does not require any training, making it highly suitable for image segmentation tasks. However, the complexity of PCNN arises from its numerous parameters, making parameter selection a challenging endeavor. In this work, we introduce a simplified PCNN architecture that includes an automatic parameter determination method. This approach is specifically designed for binary image segmentation and has been tested on various images, yielding results with distinct and desirable features. The proposed network iterates only four times, enhancing its efficiency. During pre-processing, RGB images are converted to HSV color space, and the V component undergoes further processing. This component is first filtered using an averaging filter, followed by a sharpening filter. The parameters for the PCNN are then generated automatically, eliminating the need for manual selection and making the network highly suitable for real-time image processing. The performance of the proposed network has been verified through tests on a variety of images. Key Words: Neural Networks, Pulse Coupled Neural Networks, Image Processing

Automated Analysis of Neuronal Morphology in 2D Fluorescence Micrographs through an Unsupervised Semantic Segmentation of Neurons

Brain function emerges from a highly complex network of specialized cells that are interlinked by billions of synapses. The synaptic connectivity between neurons is established between the elongated processes of their axons and dendrites or, together, neurites. To establish these connections, cellular neurites have to grow in highly specialized, cell-type dependent patterns covering extensive distances and connecting with thousands of other neurons. The outgrowth and branching of neurites are tightly controlled during development and are a commonly used functional readout of imaging in the neurosciences. Manual analysis of neuronal morphology from microscopy images, however, is very time intensive and prone to bias. Most automated analyses of neurons rely on reconstruction of the neuron as a whole without a semantic analysis of each neurite. A fully-automated classification of all neurites still remains unavailable in open-source software. Here we present a standalone, GUI-based software for batch-quantification of neuronal morphology in two-dimensional fluorescence micrographs of cultured neurons with minimal requirements for user interaction. Single neurons are first reconstructed into binarized images using a Hessian-based segmentation algorithm to detect thin neurite structures combined with intensity- and shape-based reconstruction of the cell body. Neurites are then classified into axon, dendrites and their branches of increasing order using a geodesic distance transform of the cell skeleton. The software was benchmarked against a published dataset and reproduced the phenotype observed after manual annotation. Our tool promises accelerated and improved morphometric studies of neuronal morphology by allowing for consistent and automated analysis of large datasets.

A New R35 and Fractal Joint Rock Typing Method Using MICP Analysis: A Case Study in Middle East Iraq

Reservoir characterization in carbonate formations plays a crucial role in understanding the complex pore structures and permeability properties. While absolute pore-throat radius (APTR) and R35 have been widely accepted in pore-scale rock typing, they fall short of providing detailed pore-throat distribution (PTD) information. To address this limitation and enhance PTD indication during rock classification, we introduce a novel approach—the R35 and fractal joint rock typing method—incorporating a new parameter, Dn (fractal dimension). This method is developed based on the analysis of mercury injection capillary pressure (MICP) data obtained from 20 carbonate samples in the Middle East, specifically Iraq. We delve into the discussion of APTR and R35 methods, employing both PTD and thin-section images to gain comprehensive insights into rock typing. Our approach incorporates a whole curve fractal-based model to determine the fractal dimension, Dn. The analysis reveals that Dn in each R35 rock type exhibits a decreasing trend with higher Hg intrusion peaks and wider pore-throat radius, providing valuable information on the distribution of pores within the rock samples. Furthermore, we extend our analysis to include the surface fractal dimension, Ds, obtained through two-dimensional (2D) fractal analysis on typical pores in binary thin-section images. The consistent decreasing trend of Dn aligns with the findings from Ds analysis, underscoring the effectiveness of parameter Dn in capturing the intricate pore structures within carbonate formations. Our results suggest that parameter Dn has the potential to serve as a standalone criterion in rock typing, eliminating the need for pretyping by R35 or APTR. The versatility of Dn as an indicator of pore distribution and complexity underscores its significance in advancing our understanding of carbonate reservoirs. As a recommendation, further exploration through additional fractal-based analyses is encouraged to solidify the role of parameter Dn in becoming a pivotal factor in the evolving field of rock typing.

Intelligent Trash Level Detection for Sustainable Urban Waste Management

Abstract This paper introduces an advanced trash bin fill ratio detection system, addressing the challenges of municipal solid waste management. Utilising the ESP32 CAM module, the system captures and transmits bin images via the ESP MESH protocol, enhancing waste management efficiency. The hardware relies on sustainable energy sources, including a photovoltaic cell and LiPo battery, ensuring continuous operation. On the software front, a client-server architecture is employed. The client-side captures images, while the server-side processes these images using a Python script and SQL database to determine bin fill levels. This innovative approach offers a scalable, cost-effective solution for improving urban waste collection and management.

Deep Learning Approach for Early Detection of Alzheimers Disease

Abstract: Alzheimer’s disease (AD) is a chronic, irreversible brain disorder, no effective cure for it till now. However, available medicines can delay its progress. Therefore, the early detection of AD plays a crucial role in preventing and controlling its progression. The main objective is to design an end-to-end framework for early detection of Alzheimer’s disease and medical image classification for various AD stages. A deep learning approach, specifically convolutional neural networks (CNN), is used in this work. Four stages of the AD spectrum are multi-classified. Furthermore, separate binary medical image classifications are implemented between each two-pair class of AD stages.

Dental Carries Prediction and Prevention

Abstract: A large percentage of people worldwide suffer from dental cavities, which are prevalent disorders. They caused by bacterial activity, can lead to permanent damage to teeth. They pose a risk to tooth health without timely intervention. In order to stop additional harm, early identification and treatment are essential. Traditionally, x-rays or a direct visual inspection are done by dentists to detect cavities. On the other hand, automated systems that employ image processing methods including region recognition, binary image synthesis, and RGB to Gray conversion can help locate cavities in x-ray pictures. Automated tools that utilize ordinary cameras for dental image analysis are also being explored, showing promising results.

An improved convolutional neural network for predicting porous media permeability from rock thin sections

Permeability prediction is a crucial aspect of investigating fluid flow capacity in porous media, and rapidly predicting the permeability of rock thin sections aids in reservoir assessment. In recent years, significant progress has been made regarding the use of deep learning for predicting porous media permeability, effectively overcoming the limitations associated with time-consuming conventional permeability determination methods. To address the issues of low prediction accuracy and insufficient generalization capability of previous permeability prediction models, this study proposes an improved convolutional neural network for porous media permeability and applies it to predict the permeability of rock thin sections. Given the difficulty of obtaining a large amount of rock thin section data, we synthetically generated 1000 binary images of porous media and calculated the corresponding permeability labels using computational fluid dynamics. These data were used as foundational data for training the model. The proposed model achieved accurate and efficient permeability prediction of porous media with a correlation of 0.9667 on testing set. Simultaneously, we employed class activation mapping technology to visualize the permeability prediction process of the neural network, thereby elucidating the working principles of the neural network during porous media permeability prediction. Subsequently, based on an optimally pretrained neural network, transfer learning was utilized to predict the permeability of rock thin sections, which achieved a correlation of 0.9032. Our study extends the rock thin section applications and provides technical support for reservoir evaluation.

Computer-Vision- and Deep-Learning-Based Determination of Flow Regimes, Void Fraction, and Resistance Sensor Data in Microchannel Flow Boiling.

The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection, and histogram comparison to separate vapor from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called U-net to extract meaningful features from video frames. Both approaches enabled the automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially CNN demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1% and classify the above flow regimes with an overall classification accuracy of 91%. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10-6.

Binary image embedding and restoration in speech signal

AbstractIn this paper, we propose a method of embedding images into a speech signal. An image is embedded in the high frequency band above 16 kHz of the speech signal to be difficult to perceive for humans. In the proposed method, the image is embedded after being binarized by the error diffusion method. When the image is embedded, we apply an iterative phase restoration method to avoid noise generation. We also investigate a compensation method for an extracted image whose quality degrades due to transmission channel characteristics. Simulation and real‐environmental experiments showed that the proposed method significantly improved the quality of the extracted image on the receiver side.

An Advanced Terrain Vegetation Signal Detection Approach for Forest Structural Parameters Estimation Using ICESat-2 Data

Accurate forest structural parameters (such as forest height and canopy cover) support forest carbon monitoring, sustainable forest management, and the implementation of silvicultural practices. The Ice, Cloud, and land Elevation Satellite-2 (ICESat-2), which is a spaceborne Light Detection and Ranging (LiDAR) satellite, offers significant potential for acquiring precise and extensive information on forest structural parameters. However, the ICESat-2 ATL08 product is significantly influenced by the geographical environment and forest characteristics, maintaining considerable potential for enhancing the accuracy of forest height estimation. Meanwhile, it does not focus on providing canopy cover data. To acquire accurate forest structural parameters, the Terrain Signal Neural Network (TSNN) framework was proposed, integrating Computer Vision (CV), Ordering Points to Identify the Clustering Structure (OPTICS), and deep learning. It encompassed an advanced approach for detecting terrain vegetation signals and constructing deep learning models for estimating forest structural parameters using ICESat-2 ATL03 raw data. First, the ATL03 footprints were visualized as Profile Raster Images of Footprints (PRIF), implementing image binarization through adaptive thresholding and median filtering denoising to detect the terrain. Second, the rough denoising buffers were created based on the terrain, combining with the OPTICS clustering and Gaussian denoising algorithms to recognize the terrain vegetation signal footprints. Finally, deep learning models (convolutional neural network (CNN), ResNet50, and EfficientNetB3) were constructed, training standardized PRIF to estimate forest structural parameters (including forest height and canopy cover). The results indicated that the TSNN achieved high accuracy in terrain detection (coefficient of determination (R2) = 0.97) and terrain vegetation signal recognition (F-score = 0.72). The EfficientNetB3 model achieved the highest accuracy in forest height estimation (R2 = 0.88, relative Root Mean Squared Error (rRMSE) = 13.5%), while the CNN model achieved the highest accuracy in canopy cover estimation (R2 = 0.80, rRMSE = 18.5%). Our results have significantly enhanced the accuracy of acquiring ICESat-2 forest structural parameters, while also proposing an original approach combining CV and deep learning for utilizing spaceborne LiDAR data.

Mountainous road vector data update method based on matching point pair grouping

ABSTRACT The vector information of mountainous roads is great significance, including regional economics, emergency response, disaster management, among others. Nevertheless, there are irregular deformations in existing vector data, coupled with incomplete extraction results for mountainous roadways. These issues pose challenges in establishing a matching model between road extraction results and existing vector data, significantly reducing the efficiency of automated updates for the current vector data. Targeting roads as a distinct artificial feature and leveraging their topological connectivity, we propose a vector data updating method based on matching point pair grouping. Firstly, we employ the SDUNet model to extract mountainous road and utilize the Superglue model to match road binary images with vector binary images, resulting in sets of initial matching point pairs. Subsequently, we propose a road line extraction model that groups matching point pairs, eliminates misaligned pairs based on road topological connectivity, and establishes a mapping relationship between road lines and vector lines. Ultimately, through road line optimization and vector line optimization methods, we accomplish the automatic updating of vector data for mountainous roadways. Through a comprehensive analysis of over 2600 vector data, our method demonstrates substantial advantages in terms of both F1 and IoU compared to alternative methods.

Standardizing technical parameters and terms for abdominopelvic photon-counting CT: laying the groundwork for innovation and evidence sharing.

Photon-counting detector CT (PCD-CT) is a new technology that has multiple diagnostic benefits including increased spatial resolution, iodine signal, and radiation dose efficiency, as well as multi-energy imaging capability, but which also has unique challenges in abdominal imaging. The purpose of this work is to summarize key features, technical parameters, and terms, which are common amongst current abdominopelvic PCD-CT systems and to propose standardized terminology (where none exists). In addition, user-selectable protocol parameters are highlighted to facilitate both scientific evaluation and early clinical adoption. Unique features of PCD-CT systems include photon-counting detectors themselves, energy thresholds and bins, and tube potential considerations for preserved spectral separation. Key parameters for describing different PCD-CT systems are reviewed and explained. While PCD-CT can generate multi-energy images like dual-energy CT, there are new types of images such as threshold images, energy bin images, and special spectral images. The standardized terms and concepts herein build upon prior interdisciplinary consensus and have been endorsed by the newly created Society of Abdominal Radiology Photon-counting CT Emerging Technology Commission.

PCP auto count: a novel Fiji/ImageJ plug-in for automated quantification of planar cell polarity and cell counting.

Introdution: During development, planes of cells give rise to complex tissues and organs. The proper functioning of these tissues is critically dependent on proper inter- and intra-cellular spatial orientation, a feature known as planar cell polarity (PCP). To study the genetic and environmental factors affecting planar cell polarity, investigators must often manually measure cell orientations, which is a time-consuming endeavor. To automate cell counting and planar cell polarity data collection we developed a Fiji/ImageJ plug-in called PCP Auto Count (PCPA). Methods: PCPA analyzes binary images and identifies "chunks" of white pixels that contain "caves" of infiltrated black pixels. For validation, inner ear sensory epithelia including cochleae and utricles from mice were immunostained for βII-spectrin and imaged with a confocal microscope. Images were preprocessed using existing Fiji functionality to enhance contrast, make binary, and reduce noise. An investigator rated PCPA cochlear hair cell angle measurements for accuracy using a one to five agreement scale. For utricle samples, PCPA derived measurements were directly compared against manually derived angle measurements and the concordance correlation coefficient (CCC) and Bland-Altman limits of agreement were calculated. PCPA was also tested against previously published images examining PCP in various tissues and across various species suggesting fairly broad utility. Results: PCPA was able to recognize and count 99.81% of cochlear hair cells, and was able to obtain ideally accurate planar cell polarity measurements for at least 96% of hair cells. When allowing for a <10° deviation from "perfect" measurements, PCPA's accuracy increased to 98%-100% for all users and across all samples. When PCPA's measurements were compared with manual angle measurements for E17.5 utricles there was negligible bias (<0.5°), and a CCC of 0.999. Qualitative examination of example images of Drosophila ommatidia, mouse ependymal cells, and mouse radial progenitors revealed a high level of accuracy for PCPA across a variety of stains, tissue types, and species. Discussion: Altogether, the data suggest that the PCPA plug-in suite is a robust and accurate tool for the automated collection of cell counts and PCP angle measurements.