scholarly journals Analysis of the Region of Interest According to CNN Structure in Hierarchical Pattern Surface Inspection Using CAM

Materials ◽  
2021 ◽  
Vol 14 (9) ◽  
pp. 2095
Author(s):  
In Yong Moon ◽  
Ho Won Lee ◽  
Se-Jong Kim ◽  
Young-Seok Oh ◽  
Jaimyun Jung ◽  
...  
Keyword(s):  
Surface Defects ◽  
Raw Materials ◽  
Region Of Interest ◽  
Defect Inspection ◽  
Number Of Layers ◽  
Important Region ◽  
Optimized Model ◽  
Human Inspection ◽  
Inspection Performance ◽  
Hierarchical Pattern

A convolutional neural network (CNN), which exhibits excellent performance in solving image-based problem, has been widely applied to various industrial problems. In general, the CNN model was applied to defect inspection on the surface of raw materials or final products, and its accuracy also showed better performance compared to human inspection. However, surfaces with heterogeneous and complex backgrounds have difficulties in separating defects region from the background, which is a typical challenge in this field. In this study, the CNN model was applied to detect surface defects on a hierarchical patterned surface, one of the representative complex background surfaces. In order to optimize the CNN structure, the change in inspection performance was analyzed according to the number of layers and kernel size of the model using evaluation metrics. In addition, the change of the CNN’s decision criteria according to the change of the model structure was analyzed using a class activation map (CAM) technique, which can highlight the most important region recognized by the CNN in performing classification. As a result, we were able to accurately understand the classification manner of the CNN for the hierarchical pattern surface, and an accuracy of 93.7% was achieved using the optimized model.

scholarly journals Mirror Neuron System Activation in Children With Unilateral Cerebral Palsy During Observation of Actions Performed by a Pathological Model

2019 ◽  
Vol 33 (6) ◽  
pp. 419-431 ◽  
Author(s):  
Antonino Errante ◽  
Giuseppe Di Cesare ◽  
Chiara Pinardi ◽  
Fabrizio Fasano ◽  
Silvia Sghedoni ◽  
...  
Keyword(s):  
Cerebral Palsy ◽  
Mirror Neuron System ◽  
Action Observation ◽  
Mirror Neuron ◽  
Region Of Interest ◽  
Typically Developing ◽  
Neuron System ◽  
Important Region ◽  
Pathological Model ◽  
Unilateral Cerebral Palsy

Background. Recent evidence suggested that Action Observation Therapy (AOT), based on observation of actions followed by immediate reproduction, could be a useful rehabilitative strategy for promoting functional recovery of children affected by unilateral cerebral palsy (UCP). AOT most likely exploits properties of the parieto-premotor mirror neuron system (MNS). This is more intensely activated when participants observe actions belonging to their own motor repertoire. Objective. The aim of the present study was to investigate the issue of whether MNS of UCP children is better activated by actions performed by a paretic hand rather than a healthy one. Methods. Using functional magnetic resonance imaging, we assessed brain activation in a homogeneous group of 10 right UCP children compared with that of 10 right-handed typically developing (TD) children, during observation of grasping actions performed by a healthy or a paretic hand. Results. The results revealed a significant activation within the MNS in both UCP and TD children, more lateralized to the left hemisphere in the TD group. Most important, region of interest (ROI) analysis on parietal and premotor regions showed that, in UCP, the MNS was more strongly activated by observation of actions performed by the paretic hand, a motor model more similar to the observer’s motor repertoire. Conclusions. This study shows that children affected by spastic UCP exhibit enhanced activation of the MNS during observation of goal-directed actions performed by a pathological model with respect to a healthy one.

Region of Interest-Based Coding Technique of Medical Images Using Varying Grading of Compression

2020 ◽  
pp. 2150021
Author(s):  
Urvashi Sharma ◽  
Meenakshi Sood ◽  
Emjee Puthooran
Keyword(s):  
Medical Image ◽  
Region Of Interest ◽  
Block Size ◽  
Threshold Value ◽  
Hospital Performance ◽  
Jpeg 2000 ◽  
Compression Method ◽  
Compression Efficiency ◽  
Important Region

A region of interest (ROI)-based compression method for medical image datasets is a requirement to maintain the quality of the diagnostically important region of the image. It is always a better option to compress the diagnostic important region in a lossless manner and the remaining portion of the image with a near-lossless compression method to achieve high compression efficiency without any compromise of quality. The predictive ROI-based compression on volumetric CT medical image is proposed in this paper; resolution-independent gradient edge detection (RIGED) and block adaptive arithmetic encoding (BAAE) are employed to ROI part for prediction and encoding that reduce the interpixel and coding redundancy. For the non-ROI portion, RIGED with an optimal threshold value, quantizer with optimal [Formula: see text]-level and BAAE with optimal block size are utilized for compression. The volumetric 8-bit and 16-bit standard CT image dataset is utilized for the evaluation of the proposed technique, and results are validated on real-time CT images collected from the hospital. Performance of the proposed technique in terms of BPP outperforms existing techniques such as JPEG 2000, M-CALIC, JPEG-LS, CALIC and JP3D by 20.31%, 19.87%, 17.77%, 15.58% and 13.66%, respectively.

Preparation of Anode-Supported SOFC Electrolyte Membrane and Porous Anode Material

2016 ◽  
Vol 848 ◽  
pp. 383-388
Author(s):  
Fei Li ◽  
Jing De Zhang ◽  
Jun Peng Luan ◽  
Ya Lei Liu
Keyword(s):  
Anode Material ◽  
Raw Materials ◽  
Monomethyl Ether ◽  
Ethylene Glycol Monomethyl Ether ◽  
Glycol Monomethyl Ether ◽  
Electrolyte Membrane ◽  
Number Of Layers ◽  
Before And After ◽  
Shock Resistance ◽  
Porous Anode

The graphite was used as pore-forming agent to prepare porous NiO-Yttria-stabilized zirconia (YSZ) anode material. The influence of the content of pore-forming agent of the anode material, and the change of the anode material before and after the reduction of NiO were investigated. It was found that the porosity and shrinkage rate of the anode increased with the addition of the pore-forming agent, and the thermal shock resistance also improved. We chose Y(NO3)3·6H2O and ZrOCl2·8H2O as raw materials, ethylene glycol monomethyl ether as solvents to make collosol. And electrolyte membrane on the Si piece was prepared by spin-coating. The electrolyte membrane would be thinner if it spined faster and longer. Then we chose the anode material as support to prepare electrolyte membrane. The thickness of the electrolyte membrane increased with the increase of the number of layers. Two layers were the most appropriate.

scholarly journals Natural Rail Surface Defect Inspection and Analysis Using 16-Channel Eddy Current System

2021 ◽  
Vol 11 (17) ◽  
pp. 8107
Author(s):  
Se-Gon Kwon ◽  
Taek-Gyu Lee ◽  
Sang-Jun Park ◽  
Jeong-Won Park ◽  
Jong-Min Seo
Keyword(s):  
Eddy Current ◽  
Surface Defects ◽  
Safety Management ◽  
Current System ◽  
Detection Sensitivity ◽  
Defect Inspection ◽  
Artificial Defect ◽  
Eddy Current Inspection ◽  
Train Operation ◽  
Inspection Systems

Trains are used as the fastest mode of transportation for both people and cargo. The train moves along a special path called 'rail,' where fatigue can be accumulated due to wheel-rail contact load as a result of continuous train operation. Consistent and regularly scheduled safety management is required since corrosion rate of the rails located on outside environment is very high. Researchers have actively investigated and developed rail defect inspection systems employing non-destructive techniques to address these problems. In particular, the eddy current inspection technique does not involve contact with the surface of the test specimen and offers the advantage of excellent rail defect detection sensitivity. Therefore, a 16 Ch array eddy current inspection device was developed to inspect the surface defects of the rail. An equation was derived to predict the correlation between the depth and phase of an artificial defect using the eddy current inspection device, and the derived equation was applied to the natural defect specimen.

scholarly journals Applications of Mechanochemically Prepared Layered Double Hydroxides as Adsorbents and Catalysts: A Mini-Review

Nanomaterials ◽  
2019 ◽  
Vol 9 (1) ◽  
pp. 80 ◽  
Author(s):  
Jun Qu ◽  
Lin Sha ◽  
Chenjie Wu ◽  
Qiwu Zhang
Keyword(s):  
Surface Defects ◽  
Raw Materials ◽  
High Surface ◽  
Chemical Properties ◽  
Dry Milling ◽  
Application Performance ◽  
Double Hydroxide ◽  
Double Hydroxides ◽  
Unique Chemical ◽  
Catalytic Performances

Mechanochemically prepared layered double hydroxide (M-LDH), which usually possesses high surface chemical activity and a substantial amount of surface defects, has presented outstanding application performance especially in the area of environmental protection. Recently published works on the mechanochemical synthesis of LDH were first introduced to provide a comprehensive summary on the preparation of the materials. Ensuing discussion provided an overview of recent research on the applications of M-LDH products as adsorbents and catalysts. The excellent adsorption performance and fast adsorption rate of the precursor of LDH produced by dry milling of raw materials was identified. The catalytic performances of M-LDH as catalysts, mainly photocatalysts, were then introduced. It is foreseeable that by rational utilization of mechanochemical processes and the unique chemical properties of M-LDH, increasing numbers of applications using M-LDH could be expected.

Combined Electron Beam Induced Current Imaging (EBIC) and Focused Ion Beam (FIB) Techniques for Thin Film Solar Cell Characterization

2010 ◽  
Author(s):  
Frank Altmann ◽  
Jan Schischka ◽  
Vinh Van Ngo ◽  
Stacey Stone ◽  
Laurens F. Tz. Kwakman ◽  
...  
Keyword(s):  
Thin Film ◽  
Electron Beam ◽  
Focused Ion Beam ◽  
Surface Defects ◽  
Ion Beam ◽  
Three Dimensional ◽  
Region Of Interest ◽  
Induced Current ◽  
Large Area ◽  
Electron Beam Induced Current

Abstract A novel analytical method applying combined electron beam induced current (EBIC) imaging based on scanning electron microscopy (SEM) and focused ion beam (FIB) cross sectioning in a SEM/FIB dualbeam system is presented. The method is demonstrated in several case studies for process characterization and failure analysis of thin film technology based Solar cells, including Silicon (CSG), Cadmium Telluride (CdTe) and Copper Indium Selenide (CIS) absorbers. While existing techniques such as electro-, photoluminescence spectroscopy and lock-in thermography are able to locate the larger, electrically active defects reasonably fast on a large area, the FIB-SEM EBIC system is uniquely capable of detecting sub-micron, sub-surface defects and of analysing these defects in the same system. In combination with a FIB, the localized region of interest can be easily cross sectioned and additional EBIC analysis can be applied for a three dimensional analysis of the p/n junction.

Investigation of the Influence of Technological Regimes of High-Temperature Firing on the Structure and Properties of Silicate-Enamel Coatings for Carbon Steels

2021 ◽  
Vol 316 ◽  
pp. 752-757
Author(s):  
A.V. Ryabova ◽  
L.V. Klimova ◽  
D.A. Golovko
Keyword(s):  
Enamel Coating ◽  
Raw Materials ◽  
Single Layer ◽  
Metal Substrate ◽  
Carbon Steels ◽  
Structure And Properties ◽  
Physicochemical Processes ◽  
Number Of Layers ◽  
Enamel Composition ◽  
Slip Layer

The silicate-enamel coating becomes the actual coating as a result of firing, which is a process of heating steel products coated with a “biscuit” dried slip layer, until completely melted, and a continuous coating is obtained on a metal substrate. With the constantly increasing requirements for the technical and operational properties of enameled products in the production of steel pipelines, it is advisable to use single-layer enameling, which saves raw materials and energy, due to the reduction in the number of layers and firing cycles of products. Its use for large-sized products, such as pipelines, eliminates their warping that occurs during repeated firing. In addition, the use of single-layer coatings makes it possible to obtain a better surface of products, since with a decrease in the resulting coating thickness it becomes more elastic and impact-resistant. All of the above is predetermined both by the structure of the glass coating itself and the generally formed steel - enamel composition. Therefore, knowledge of the structure, as well as of the physicochemical processes that occur during the firing of the enameled product, is necessary to solve technological issues successfully.

Use of Computer Based Training for Aircraft Inspectors: Findings and Recommendations

2000 ◽  
Vol 44 (22) ◽  
pp. 779-782 ◽  
Author(s):  
Anand K. Gramopadhye ◽  
Brian J. Melloy ◽  
Stacye Chen ◽  
Jamie Bingham ◽  
Reena Master ◽  
...  
Keyword(s):  
Intervention Strategy ◽  
Safety Training ◽  
Automated System ◽  
Training Simulator ◽  
Computer Based Training ◽  
Computer Based ◽  
Inspection And Maintenance ◽  
Self Instruction ◽  
Human Inspection ◽  
Inspection Performance

Research in aircraft inspection and maintenance has revealed the criticality of human inspection performance in improving aviation safety. Training has been identified as the primary intervention strategy in improving the quality and reliability of aircraft inspection performance. If training is to be successful, it is clear that we need to provide aircraft inspectors with tools to help enhance their inspection skills and improve performance. In response to this need, the Clemson research team developed a high fidelity inspection-training simulator (ASSIST: Automated System of Self Instruction for Specialized Training) - a specialized inspection software focused on improving aircraft inspection performance. Following the development a detailed usability evaluation was conducted and is reported as a part of this paper.

Use of 0.0 mm Pathlength Gas Cell to Eliminate CO(g) Absorbance from High-CO-Pressure Solid-State IR Spectra of Nonclassical Metal Carbonyls

1998 ◽  
Vol 52 (8) ◽  
pp. 1035-1038 ◽  
Author(s):  
Jeffrey J. Rack ◽  
Oleg G. Polyakov ◽  
Christine M. Gaudinski ◽  
John W. Hammel ◽  
Peter Kasperbauer ◽  
...  
Keyword(s):  
Metal Carbonyl ◽  
Region Of Interest ◽  
Metal Carbonyls ◽  
Carbonyl Complexes ◽  
Gas Cell ◽  
Weak Band ◽  
Metal Carbonyl Complexes ◽  
Spectral Bands ◽  
Important Region ◽  
Gas Pressures

A transmission-IR gas cell was constructed from 18%-Ni maraging steel so that two parallel 10 mm diameter × 3 mm thick sapphire windows were held approximately 0.1 mm apart. The cell was engineered to withstand static gas pressures up to 150 atm. When 100 atm CO was placed in the cell, the % transmittance was essentially zero between 2200 and 2080 cm−1 because of the intense v(CO) band centered at 2143 cm−1 (this is an important region of interest for the growing subset of metal carbonyl complexes known as nonclassical metal carbonyls). When the cell was assembled with Nujol or Fluorolube mulls of several microcrystalline copper(I) and silver(I) salts between the windows and CO gas was added to the cell, the gas dissolved in the mulling agents and reacted with the metal salts, but no gaseous CO was observed in the spectrum. New spectral bands were observed that are attributed to unusual metal carbonyl species that are stable only under high CO pressure. A relatively weak band due to free CO dissolved in the mulling agents was detected at 2138–2135 cm−1. The new cell was used to demonstrate that the compound Ag(OTeF5) takes up only one equivalent of CO at 100 atm and that the compound Cu(CF3SO3) takes up two equivalents of CO at 136 atm.

scholarly journals The investigation on defect recognition system using gaussian smoothing and template matching approach

2020 ◽  
Vol 18 (2) ◽  
pp. 812
Author(s):  
M. H. Harun ◽  
M. F. Yaakub ◽  
A. F. Z. Abidin ◽  
A. H. Azahar ◽  
M. S. M. Aras ◽  
...  
Keyword(s):  
Defect Detection ◽  
Template Matching ◽  
Recognition Rate ◽  
Region Of Interest ◽  
Recognition System ◽  
Automated Inspection ◽  
Gaussian Smoothing ◽  
Important Region ◽  
Detection Approach ◽  
Defect Recognition

<p>This paper investigates various approaches for automated inspection of gluing process using shape-based matching application. A new supervised defect detection approach to detect a class of defects in gluing application is proposed. Creating of region of interest in important region of object is discussed. Gaussian smoothing features is proposed in determining better image processing. Template matching in differentiates between reference and tested image are proposed. This scheme provides high computational savings and results in high defect detection recognition rate. The defects are broadly classified into three classes: 1) gap defect; 2) bumper defect; 3) bubble defect. This system does lessen execution time, yet additionally produce high precision in deformity location rate. It is discovered that the proposed framework can give precision at 95.77% recognition rate in recognizing imperfection for gluing application.</p>

Sign in / Sign up

Export Citation Format

Share Document