Morphological Processing Research Articles

Research on Industrial Production Defect Detection Method Based on Machine Vision Technology in Industrial Internet of Things

The realization of automatic operation of production by the industrial Internet of Things needs the functional assistance of machine vision technology. Different from the recognition and detection of some known features, it is difficult to realize defect detection in machine vision applications. Therefore, this article studies the industrial production defect detection method based on machine vision technology in industrial Internet of Things. Firstly, in the second chapter, the images of industrial products collected by machine vision system are preprocessed and thinned to obtain more ideal detection accuracy and measurement accuracy. The methods of image binarization, morphological processing, thinning and burr elimination are given in detail. In the third chapter, product defect detection model is constructed based on U-Net network, and residual structure, hole convolution module, strip pooling module and attention mechanism module are introduced to optimize the network model. Experimental results verify the effectiveness of the model for product defect detection.

Oral Tumor Segmentation and Detection using Clustering and Morphological Process

Oral tumor is one of the most widely recognized tumors growing globally, continuously promoting a high mortality rate. Because early detection and treatment remain the most effective interventions in improving oral cancer outcomes, developing complementary vision-based technologies that can reveal potential evil high-quality oral diseases (OPMDs), which carry the risk of developing cancer, represent significant opportunities for the oral screening process. This paper proposes a morphological algorithm to preserve edge details and prominent features in dental radiographs. This technique, in the early stage identifies the oral tumor detection using clustering and morphological processing. This algorithm would allow for the identification of tumors in these images. Applying pre-processing in images leads to over-segmentation even though it is pre-processed.

Detachment levels of Colombian caribbean mud volcanoes

Regional analysis of mud volcanoes demonstrates the regional extension of these processes in Northern Colombia. Mud volcanoes are active systems that manifest the characteristics of the underlying sedimentary sequences on the surface, as well as the presence of hydrocarbons. These may which provide information about the oil systems and the characterization of new migration paths. New data acquired during field geology studies, along with the evaluation of acquired aerial images by dron, allowed to observe variations in terms of morphology and neotectonic process, being distinctive between mud volcanoes formed in different structural domains. Mud volcanoes formed in areas of basement without thrust faults (back stop zone) are usually circular, connected to the basement by regional faults. Other mud volcanoes formed in older and younger deformed belts tend to present ellipsoidal shapes, with drainages patterns that suggest local stress fields associated with regional strike slip movements of major faults. The analysis of U/Pb ages in detrital zircons extracted from mud volcanoes and outcropping sedimentary sequences in the Colombian Caribbean, together with the analysis of foraminiferal and palynomorph faunas, suggest different levels of detachment. Clay mineralogy and geochemistry indicate that mud volcanoes formed in the back stop and the Northern part of the San Jacinto deformed belt have sludge material originated in sedimentary sequences with contributions from continental basement rocks, while the mud volcanoes located in the central and Southern parts of the studied area tend to show sediments provided from deepest stratigraphic levels, derived from less evolved magmatic sources (dioritic basements). Gas and water analysis obtained from studied mud volcanoes suggest that the old deformed belt, Paleocene accretionary wedge and back stop areas, have evidences of thermogenic oil systems, while in the domain of the younger deformed belt the tendency is to indicate evidences of microbial process.

Combined Detection and Segmentation of Overlapping Erythrocytes in Microscopy Images Using Morphological Image Processing

Segmentation of clusters of erythrocytes into their constituent single cells is a procedure needed in various biomedical applications related to microscopy images. This task is part of the general problem of splitting clumps of objects in images which continues being an open research topic in the Image Processing field. This work presents a unified morphological method to detect and segment clusters of erythrocytes in microscopy images, and proposes two main contributions. The first one is to formulate and evaluate a method to detect clusters as connected components in binary images, obtained from a previous coarse segmentation, which is not capable of further dividing a cluster into its constituent cells. Secondly, to propose the best alternative to split the clusters into their constituent individual cells after evaluating three algorithms based in the combination of the transforms: H-maxima, weighted external distance and marker-controlled watershed. Evaluation of the proposed cluster detection methods was made in terms of standard measures of effectiveness. Segmentation accuracy was evaluated comparing the segmented objects obtained to a manually segmented ground truth, by means of the Jaccard index. Then the Friedman test allowed validating the advantages of the proposed method in comparison to the other alternatives studied here.

Efficient regulation of active layer morphology and interfacial charge-transfer process by porphyrin-based additive in organic solar cells

Active layer morphology and interfacial charge-transfer (CT) properties in organic solar cells (OSCs) greatly affect device performance but are difficult to control. Here, a porphyrin derivative meso- tetrakis(3,5-bis(trifluoromethyl)phenyl)porphyrin (TBTPP) is applied as additive in OSCs to tune the morphology and interfacial CT process of donor PM6 and acceptor Y6 blend. In combination with molecular dynamics (MD), density functional theory (DFT), and time-dependent DFT (TD-DFT), we systematically investigate the active layer morphology and interfacial properties of PM6/Y6 and PM6/Y6/TBTPP. The theoretical calculations confirm that TBTPP can significantly regulate active layer morphology and interfacial CT characteristics. The results decipher that blend PM6/Y6/TBTPP features much stronger intermolecular interactions than PM6/Y6 and more phase separation interfaces. Moreover, after adding TBTPP, the percentage of CT states increases from 53% to 73%, and the net charge-transferred amount of almost all CT states enlarges. Under the TBTPP-addition condition, the charge separation degree of 60% excitons is improved. This research demonstrates that the introduction of TBTPP is of great significance for developing high-performance OSCs because it possesses the dual efficacy of regulating morphology and simultaneously improving CT properties.

Calcium-Lignosulfonate-Filled Rubber Compounds Based on NBR with Enhanced Physical-Mechanical Characteristics.

Calcium lignosulfonate in the amount 30 phr was incorporated into rubber compounds based on pure NBR and an NBR carbon black batch, in which the content of carbon black was 25 phr. Glycerine, as a cheap and environmentally friendly plasticizer, was applied into both types of rubber formulations in a concentration scale ranging from 5 to 20 phr. For the cross-linking of rubber compounds, a sulfur-based curing system was used. The work was aimed at the investigation of glycerine content on the curing process and rheological properties of rubber compounds, cross-link density, morphology and physical-mechanical properties of vulcanizates. The results show that glycerine influences the shapes of curing isotherms and results in a significant decrease between the maximum and minimum torque. This points to the strong plasticizing effect of glycerine on rubber compounds, which was also confirmed from rheological measurements. The application of glycerine resulted in better homogeneity of the rubber compounds and in the better dispersion and distribution of lignosulfonate within the rubber matrix, which was subsequently reflected in the significant improvement of tensile characteristics of vulcanizates. A higher cross-link density as well as better physical-mechanical properties were exhibited by the vulcanizates based on the carbon black batch due to the presence of a reinforcing filler.

The circadian clock influences T cell responses to vaccination by regulating dendritic cell antigen processing

Dendritic cells play a key role in processing and presenting antigens to naïve T cells to prime adaptive immunity. Circadian rhythms are known to regulate many aspects of immunity; however, the role of circadian rhythms in dendritic cell function is still unclear. Here, we show greater T cell responses when mice are immunised in the middle of their rest versus their active phase. We find a circadian rhythm in antigen processing that correlates with rhythms in both mitochondrial morphology and metabolism, dependent on the molecular clock gene, Bmal1. Using Mdivi-1, a compound that promotes mitochondrial fusion, we are able to rescue the circadian deficit in antigen processing and mechanistically link mitochondrial morphology and antigen processing. Furthermore, we find that circadian changes in mitochondrial Ca2+ are central to the circadian regulation of antigen processing. Our results indicate that rhythmic changes in mitochondrial calcium, which are associated with changes in mitochondrial morphology, regulate antigen processing.

Medical image enhancement strategy based on morphologically processing of residuals using a special kernel

AbstractMedical imaging is playing a pivotal role in the domain of medical diagnosis. But the major problems related to medical images is that most of the images (of different modalities) are suffered from noise and other quality‐related problems such as poor contrast, blurring, and difficulties in extracting appropriate information. Therefore, it is necessary to construct some techniques that could improve medical images in such a way that it will be ideal for diagnostic applications. Medical image enhancement is the process of increasing the contrast quality of intensity variations and improves the visual representation of medical images. To provide suitable interpretation and clearer image for the observers with reduced noise levels, this article proposes a novel competent medical image enhancement method based on morphologically processing of residuals using a special kernel. First, it combines linear low pass filtering with nonlinear technique that allows for selection of essential regions where edges will get well preserved. The selection of those regions is based on morphological processing of linear filter residuals and then aims to find significant regions specified by edges of high amplitude and appropriate size. The reconstructed regions are combined with the output of low pass filtering to recovers the original shape of edges. In addition, the method allows to control the contrast to avoid blurring while preserving significant image information. In the end, a special kernel is convolved with an image to obtain the sharper image. Experiments on the different types of medical images are performed and the results are compared using different standard evaluation metrics. The quantitative results obtained through proposed method for all the metrics are optimal compared to other competing methods. It is observed that the results on various test images affirm that the proposed method generates excellent image visual quality and significantly enhances the contrast of all images which helps with better diagnosis and treatment.

Nonuniform ISRJ suppression based on time shift alignment and morphological processing

Non-uniform interrupted-Sampling Repeater Jamming is a coherent interference technology based on the principle of undersampling, and it has a salient feature over several uniform interferences in terms of pseudo-randomness, which makes it more difficult for radar to detect real targets. Aiming at the target detection problem of non-uniform interrupted-sampling repeater jamming, a method for radar based on time-frequency domain interference suppression is proposed in this paper. Firstly, according to the short-term Fourier transform strategy, the echo signal is converted to the time-frequency domain, and then we select one of the columns in the time-frequency matrix as the reference column for translating the signal perpendicular to the timeline. Furthermore, the interference distribution area is accurately extracted and filtered out according to the morphological processing. Finally, the simulation results prove that the proposed algorithms have an advantage over non-uniform interrupted-sampling repeater jamming in terms of interference suppression.

Typhoon Identification and Positioning Using the FY-4A AGRI Thermal Infrared Data

This paper addresses typhoon identification and positioning by using the thermal infrared data acquired by the Advanced Geostationary Radiation Imager (AGRI) on the Chinese Fengyun 4A (FY-4A) satellite. First, a training dataset, a validation dataset, and a test dataset of typhoons in the West Pacific Ocean close to China are created from the FY-4A AGRI thermal infrared data. Then, the YOLOX neural network is configured and trained, in which an average precision (AP) of 33.2 is obtained for the test dataset. Finally, with the prior knowledge that the brightness temperature of the typhoon eye is higher than that of its surroundings, the typhoon eyes are located using the morphological image processing method. The results of typhoon eye positioning are generally consistent with the Optimal Path (OP) dataset of tropical cyclones created by the China Meteorology Administration (CMA), and the mean errors in latitude and longitude are 0.0391° and 0.0334°, respectively.

Online Assessment of Parafoveal Morphological Processing/Awareness during Reading among Chinese and Korean Adults

ABSTRACT Purpose The present study tested parafoveal morphological processing during sentence reading with two eye-tracking experiments, making use of an implicit measurement of morphological awareness. In Chinese and Korean, each character form typically corresponds to multiple mental lexicons, leading to morphological ambiguity. Method Using the gaze-contingent boundary paradigm, we manipulated the relation between the homographic parafoveal preview morphemes and the target words in Chinese and Korean, respectively, in two experiments. We tested 57 Chinese and 45 Korean university students. Together with baseline conditions in which the previews were either identical or unrelated to the target, we had two critical conditions in which the homographs shared/did not share the same morphemic meaning (i.e., same morpheme/different morpheme) with the target morpheme. Results Across the two experiments, the differences between the same and different morpheme conditions in a number of eye movement indices were significant, consistently showing that appropriate morpho-semantic information facilitates lexical processing. The different-morpheme previews facilitated the target word processing in Chinese but not in Korean reading. Conclusion These findings suggest that morphemic meanings are activated early on during word recognition in Chinese, a logographic orthography, and Korean Hangul, a phonologically transparent writing system, before the word is fixated upon.

Development of a Technique for the Spectral Description of Curves of Complex Shape for Problems of Object Classification

Vascular pathology symptoms can be determined by retinal image segmentation and classification. However, the retinal images from non-invasive diagnostics have a complex structure containing tree-like vascular beds, multiple segment boundaries, false segments, and various distortions. It should be noted that complex structure images’ segmentation does not always provide a single solution. Thus, the goal is to increase the efficiency of vascular diagnostics. This study aims to develop a technique for describing the geometric properties of complexly structured image segments used for classifying vascular pathologies based on retinal images. The advantages and disadvantages of the existing methods and algorithms of segmentation were considered. The most effective use areas of the mentioned methods and algorithms are revealed. Through detecting retinal thrombosis, the algorithm's efficiency for constructing a mathematical model of an arbitrary shape segment based on the morphological processing of binary and halftone images was justified. A modified variant of this algorithm based on the spectral analysis procedure of arbitrary shape boundary curves was used for the spectral description of complex shape curves for classifying vascular pathologies based on retinal images. Two approaches have been developed. The first one allows obtaining a closing segment of the curve from a symmetric mapping of the initial parametric curves. The second involves intelligent data processing and obtaining contours of minimum thickness, forming convex sets. The results of experiments confirm the possibility of practical use of the developed technique to solve problems of vascular pathology classification based on retinal images, showing the correct forecast probability was 0.93 with all associated risk factors. Doi: 10.28991/ESJ-2022-06-06-015 Full Text: PDF

Easy control of surface morphology through a natural phenomenon

Easy control of surface morphology through a natural phenomenon

Retracted: A Graph Neural Network (GNN) Algorithm for Constructing the Evolution Process of Rural Settlement Morphology

Retracted: A Graph Neural Network (GNN) Algorithm for Constructing the Evolution Process of Rural Settlement Morphology

The processing of English prefixed and suffixed words by Chinese-English bilinguals

Aims and Objectives/Purpose/Research Questions: This study had two specific research goals. First, it investigated the relative importance of meaning and form in bilingual morphological processing of English prefixed and suffixed words. Second, it probed how target language proficiency and morphological type moderated bilingual morphological processing. Design/Methodology/Approach: This study implemented the masked morphological priming paradigm that administered three prime types (Transparent, Opaque, and Form) from two morphological types (prefix and suffix) to three Chinese-English bilingual groups (advanced, intermediate, and lower-intermediate). The critical stimuli included the Transparent (e.g., visualize-VISUAL; disagreement-DISAGREE), the Opaque (e.g., vanity-VAN; submission-MISSION), and the Form (e.g., example-EXAM; apparent-PARENT) English words. Data and Analysis: A total of 120 Chinese-English bilinguals representing three levels of distinct English competence participated in a masked priming lexical decision experiment. Direct comparisons were made using the linear mixed-effects models on bilingual groups’ priming effects from the Transparent, the Opaque, and the Form conditions of both English prefixed and suffixed words. Findings/Conclusion: The results exhibited that compared to suffixed words Chinese-English bilinguals altogether were less sensitive to the internal structure of prefixed words. The results presented that target language proficiency and morphological type moderated bilingual morphological processing, with the advanced Chinese-English bilinguals approximating previous native English speakers in processing English suffixed words. Originality: This study compared the priming effects from the Transparent, the Opaque, and the Form conditions of both English prefixed and suffixed words among three Chinese-English bilingual groups with distinct English competence. This study therefore should be the first empirical study that simultaneously evaluates the effects of target language proficiency and morphological type on bilingual morphological processing of prefixed and suffixed words. Significance/Implications: The present results indicate that target language proficiency and morphological type interact to impact bilingual morphological processing. Besides, this study provides important methodological and statistical implications for future studies.

Effect of Chlorpyrifos Insecticide On The Ossification of Wader Pari Fish Vertebrae (Rasbora Lateristriata Bleeker, 1854)

Due to high growth, chlorpyrifos was one of the solution to increase food production. However, this compound is dangerous because it belongs to organophosphate group which blocking the activity of acetylcholinesterase (ache) enzyme and caused nervouse failure to animal. Due to heavy rain this insecticide will run-off and contaminate the body of the river and effect the aquatic live. Wader pari was non-target animal of chlorpyrifos. The purpose of this study was to determine the effect of chlorpyrifos exposure on the behaviour of wader's feeding and swimming response, as well as the morphology and ossification process of the vertebrae. The study was conducted for 7 days.  4 groups of fish were exposed to chlorpyrifos with concentrations of 0, 0.001, 0.005 and 0.01 ppm. Observation of the ossification and morphological process of vertebrae is carried out using AR-Ab bone staining. Observation of wader’s behaviours is carried out using descriptive analysis. It was found that the fish which exposed to chlorpyrifos showed some behavioural abnormalities in swimming and feeding response. Fish exposed to 0.005 ppm chlorpyrifos showed vertebral abnormalities which is haemal kyphosis. Kyphosis refers to Λ-shaped vertebral curvature Fragkoulis et.al, (2019). However, the ossification process that represented by Ar-Ab staining are going well.Â

A multispectral UV–vis absorption technique for quantitative high-speed field-sequential imaging of fuel films and soot in combustion

Non-evaporated liquid fuel films are the main cause of soot formation in gasoline direct-injection engines. In this study, a UV–vis absorption technique was developed to image the fuel-film thickness after direct injection in a heated constant-flow experiment. A six-hole GDI injector sprayed fuel at 100 bar onto a transparent plate 30 mm from the nozzle. The fuel consisted of a mixture of 30% toluene / 70% isooctane (boiling points 383 and 372 K, respectively). The gas and wall temperature were 376 and 352 K, respectively, and the gas pressure 1 bar. The evaporated part of the fuel was ignited, and the ensuing combustion next to the evaporating fuel film led to soot formation. Transmission of diffused backlighting from pulsed LED illumination was imaged on an intensified high-speed CMOS camera. The UV absorbance of liquid toluene was targeted with an LED at 265 nm. However, at this wavelength, absorption by toluene vapor, scattering by the liquid, extinction by soot and soot precursors, and soot incandescence all interfere with the liquid-fuel absorbance. To estimate the contributions of scattering and soot extinction, LEDs at 310, 365, and 520 nm were added to the beam path and pulsed to coincide with consecutive frames on the high-speed camera at a frame rate of 32 kHz. A dark frame was acquired to account for soot incandescence, such that the repetition rate of the resulting 5-image sequence was 6.4 kHz. Absorption by toluene vapor was estimated with a morphological image processing developed in a previous work to separate the diffuse, moving vapor cloud from the sharp, stationary features of the fuel film. The multi-spectral approach permitted obtaining spatio-temporally resolved fuel-film thickness measurements and additional information on the soot.

Semantic Theory versus Semantic “Lumping”: Reply to Bertinetto et al. (2015) The acquisition of tense and aspect in a morphology-sensitive framework: data from Italian and Austrian-German children

Abstract The crosslinguistic investigation of child language has revealed the frequent co-occurrence of certain values of Aktionsart, aspect and tense. Specifically, dynamic-atelic predicates are likely to be observed with unbounded values of aspect in the non-past tense and dynamic-telic predicates with bounded aspect and past tense morphology. This observation has motivated theories of language acquisition that incorporate the semantic structure of predicates in relation to clause structure. Pier Marco Bertinetto and colleagues have claimed that inferences regarding the role of predicate structure in the acquisition process have been erroneously derived from “lumping” together stative and activity predicates. Furthermore, without acknowledging the prior theory of “typological bootstrapping”, they present their presumably unique theory of information processing to explain their Italian and German child language data. The purpose of this reply is to show that the stative-activity “lumping” assertion is a “straw man” argument, and a theory of morphological information processing is both well-known and compatible with semantically based theories of acquisition.

Monitoring of the Dehydration Process of Apple Snacks with Visual Feature Extraction and Image Processing Techniques

Monitoring food processing is mandatory for controlling and ensuring product quality. Most of the used techniques are destructive, arduous, and time-consuming. Non-destructive analyses are convenient for rapid and conservative food quality assessment. Color images of apple slices during the manufacturing of healthy snacks were used for monitoring the drying processing. The implementation of the image-based analysis was straightforward, feasible, and low-cost. The parameters analyzed during imagen acquisition for normalizing were: contrast enhancement, binarization, and morphologic processing, varying the illumination and reference between the positions of the camera and object under analysis. Several apple features related to color, texture, and shape were extracted with computer vision techniques and also analyzed. During image analysis, the entropy was one of the most relevant computed features according to principal component analysis, and it was also relevant in terms of physical interpretation. The average percentage of entropy increase was 19.81% in the green and blue channels, while it was 16.82% in the red channel. Other relevant visual features were the skewness and kurtosis in the RGB channels; and textural information such as contrast, correlation, and variance.

Particle image recognition in the measurement of workpiece cleanliness

Monitoring the cleaning degree of workpiece surface cleaning is a key step in high-end equipment manufacturing. The use of image recognition technology to identify the cleaning degree of workpiece surface can effectively improve the quality and efficiency of workpiece cleaning. In this paper, a particle image recognition technology based on opencv was proposed, which uses a series of methods such as grayscale, binarization, morphological processing, line contour detection, contour extraction to statistically calculate the number and average size of particles. So that the surface cleanliness of the workpiece can be determined. Judging the surface cleanliness classification according to the particle size and quantity is a precise quantitative cleaning method.