Research of Recognition Method for Surface Defects of Hot-Rolled Round Steel Based on Image Processing

2015 ◽  
Vol 1090 ◽  
pp. 84-89
Author(s):  
Chang Cheng Shao ◽  
Gong Wen Xu ◽  
Hao Xu ◽  
Ming Hai Liao ◽  
Hong Luan Zhao ◽  
...  
Keyword(s):  
Image Processing ◽  
Surface Defects ◽  
Image Noise ◽  
Recognition Method ◽  
Matlab Software ◽  
The Third ◽  
Segmented Image ◽  
Image Edge ◽  
Hot Rolled

The surface defects is an important factor affecting the quality of hot-rolled round steel, so the recognition of surface defects plays a very important role in the daily usage of the hot-rolled round steel. This paper aims to bring forward an appropriate method to find out the surface defects of the hot-rolled round steel under the help of Matlab software. First of all, the image edge of the round steel was detected, and the image was segmented. Secondly, the segmented image may appear bended, so it would be straightened to make the surface defects recognition easy. The third step is to eliminate image noise. Finally the processed image was analyzed and the appropriate recognition method was figured out. The results show that the method proposed in this paper is effective and accurate.

scholarly journals Peeling Damage Recognition Method for Corn Ear Harvest Using RGB Image

2020 ◽  
Vol 10 (10) ◽  
pp. 3371 ◽  
Author(s):  
Jun Fu ◽  
Haikuo Yuan ◽  
Rongqiang Zhao ◽  
Zhi Chen ◽  
Luquan Ren
Keyword(s):  
Image Processing ◽  
Theoretical Basis ◽  
Detection System ◽  
Post Processing ◽  
Recognition Method ◽  
Damage Recognition ◽  
Working Parameters ◽  
Corn Kernels ◽  
Rgb Image

Corn ear damage caused by peeling significantly influence the output and quality of corn harvest. Ear damage recognition is the basis to adjust working parameters and to reduce damage. Image processing is attracting increasing attentions in the field of agriculture. Conventional image processing methods are difficult to be used for recognizing corn ear damage caused by peeling in field harvesting. To address the this problem, in this paper, we propose a peeling damage recognition method based on RGB image. For our method, we develop a dictionary-learning-based method to recognize corn kernels and a thresholding method to recognize ear damage regions. To obtain better performance, we also develop the corroding algorithm and the expanding algorithm for the post-processing of recognized results. The experimental results demonstrate the practicality and accuracy of the proposed method. This study could provide the theoretical basis to develop online peeling damage detection system for corn ear harvesters.

scholarly journals Transformation of cross cracks of continuously casted billet in rolled product

2019 ◽  
Vol 75 (8) ◽  
pp. 930-935
Author(s):  
N. A. Glazunova ◽  
S. V. Stefanovich ◽  
V. S. Puteev
Keyword(s):  
Rolled Product ◽  
Surface Defects ◽  
Multiple Cracks ◽  
Crack Location ◽  
Product Surface ◽  
The Cross ◽  
Hot Rolled ◽  
Discontinuity Flaws

Increased requirements to the surface quality of hot-rolled products used in automobiles manufacturing and endeavor to decrease t rejections of the metal with surface defects, stipulate the necessity to increase the quality of the initial continuously casted billet (CCB). Cracks, formed in the process of crystallization, which are transformed into surface defects of rolled products during hot deformation are attributed to the surface defects of CCB. Classification of defects presented, reasons of cross cracks on CCB and their locations considered. In the course of the experiment the samples, cut from two CCBs in the place, where cross cracks were visually revealed after shot blasting and hot etching in the 50% solution of chloric acid. The cross cracks on the surface of a sample were revealed in the zone of the big side, and the other – on a rib. The longitudinal polished sections were cut from the place of cross cracks location. At the study of the polished sections multiple cracks were discovered. The width of cracks opening was different – from 0.01 up to 0.3 mm, depth in the section of the study – up to 10 mm. The locations of the cross cracks on the billets were marked by notches from two sides (method of “marked” defects). After that the billets were rolled at a one-stand reversible mill 850 for the diameter of 100 mm. At the visual inspection of the rolled product surface, obtained from the defect CCB, surface defects in the form of discontinuity flaws were discovered. The discontinuity flaws looked as metal ruptures of longitudinal and cross orientation and sometimes having a form of tongue. The degree of defects development depends on the depth and the crack location on the initial CCB. The defects which location corresponds to the CCB side have less opening, and defects which location corresponds to the initial billet rib looked as a rough fissure. Cross samples were cut in the places of defects locations on the surface of rolled product for metal science study. At the cross polished sections the defect cavity have several branches, the cavity walls are twisting, around the cavity branches and next to them, aggregation of small globular oxides and massive decarburization were observed. The defects of rolled products surface were classified as rolled-out cracks (cross orientation). The cracks depth in the section under study was 0.6–3.5 mm. Based on the results of the study the surface defects of rolled products were properly classified and reasons of their arising revealed, that will allow avoiding their formation in the future. Based on the proper classification and avoiding of the surface defects reasons, the rolled products rejects by surface defects will be considerably decreased.

IMAQ Vision Builder Applications in SEM Image Processing of Pharmaceutical Powders

2016 ◽  
Vol 859 ◽  
pp. 99-103
Author(s):  
Monica Cretan Stamate ◽  
Corneliu Munteanu ◽  
Magdalena Birsan ◽  
Ciprian Stamate
Keyword(s):  
Image Processing ◽  
Surface Defects ◽  
Surface Irregularity ◽  
Particle Analysis ◽  
Geometric Transformations ◽  
Sem Image ◽  
Pharmaceutical Powder ◽  
Increase Productivity ◽  
Areas Of Interest

IMAQ Vision includes a set of optimized functions for image processing (filtering and geometric transformations) and analysis of different areas of interest (perimeter, area, orientation, height, length and width). Also with this program, it may determine the edges of objects, distances and angles between the edges, an object can be searched based on its shape. Particle analysis provides the ability to count objects within the pharmaceutical or biological applications. Image calibration is done to give the user instead of the unit pixel measurements, in units such as millimeters, inches, microns. This paper aims to examine the pharmaceutical powder containing ketoprofen in order to determine the quality of the particles and if this are optimal for pharmaceutical applications. It aims to detect surface defects in the deposited layer such as cracks or clusters of particles that cause surface irregularity. IMAQ Vision by processing images, increase productivity, versatility and reproducibility also reducing manufacturing costs.

QUALITY CONTROL OF POSITIONAL ACCURACY OF 1:10000 ORTHOPHOTO PRODUCTS IN THE THIRD NATIONAL LAND SURVEY

2020 ◽  
Vol XLII-3/W10 ◽  
pp. 525-528
Author(s):  
X. Ma ◽  
Q. Q. Yan ◽  
X. Wu
Keyword(s):  
Quality Control ◽  
Mean Square Error ◽  
Quality Inspection ◽  
Mean Square ◽  
Positional Accuracy ◽  
The Third ◽  
Land Survey ◽  
Image Edge ◽  
Important Test

Abstract. The third national land survey is based on the orthophotos products. Only by providing 1:10000 orthophoto products that meet the quality requirements can the third national land survey be carried out smoothly, and the third national land survey products can be guaranteed to be accurate and reliable. Positional accuracy as an important quality element of 1:10000 orthophoto products is a key factor affecting the quality of 1:10000 orthophoto products, and directly affects the quality of the third national land survey products.This paper introduces the content of the positional accuracy quality inspection in the 1:10000 orthophoto products of the third national land survey.The mean square error in plane position and the image edge match are two important test entries in the quality control of positional accuracy . The paper specifically elaborates on the quality control of the above two important test entries. The quality control indexes of mean square error in plane position and the image edge match are introduced in detail, and the quality inspection method and quality evaluation method of position accuracy are proposed. And, the main quality problems found in the positional accuracy checking are illustrated by way of case analysis. At the same time, the cause analysis was carried out for these specific quality problems, and corresponding improvement suggestions were also proposed.This paper provides technical support and reference for the quality inspection of 1:10000 orthophoto products, and also has some positive effects on quality improvement.

Design of Automatic Detection Device for Steel Bar Surface Defects

2012 ◽  
Vol 532-533 ◽  
pp. 390-393 ◽  
Author(s):  
Jian Chuan Zhang ◽  
Wu Bin Li ◽  
Chang Hou Lu
Keyword(s):  
Image Processing ◽  
Surface Quality ◽  
Automatic System ◽  
Surface Defects ◽  
Detection System ◽  
High Luminance ◽  
Linear Ccd ◽  
Steel Bar ◽  
And Performance

To inspect the surface quality of steel bar, we designed an automatic system including linear camera and laser. Through the comparison among kinds of cameras, we select linear CCD to our system. The laser is also chosen by us with its high luminance and performance. Through a series of computation, we select the appropriate camera lens to our device. At last, we draw the whole detection system. This device has been used well and provides a good foundation for prospective image processing.

Digitising Cuneiform Tablets

2005 ◽  
Author(s):  
Carlo Vandecasteele ◽  
Luc Van Gool ◽  
Karel Van Lerberghe ◽  
Johan Van Rompay ◽  
Patrick Wambacq
Keyword(s):  
Image Processing ◽  
Digital Imaging ◽  
Middle Eastern ◽  
New Method ◽  
Image Processing Algorithm ◽  
Field Methods ◽  
The Third ◽  
Enhancement Method ◽  
Pottery Sherds

In 1850, ‘Assyriology’, or the science of reading and interpreting cuneiform, was created. During this period, historians travelled to the Middle East and spent years copying cuneiform tablets. Now, at the beginning of the third millennium AD, not much has changed. Historians still rely on epigraphy which employs the copying of inscriptions and texts by hand. This method is highly subjective, tedious and time-consuming. As Middle Eastern antiquities departments do not allow the export of these tablets, historians and scholars are faced with the challenge of producing more efficient field methods. This chapter discusses a new method of recording the information taken from cuneiform tablets using digitizing. Digital imaging uses a camera wherein the picture captured is linked to a laptop which runs an image processing algorithm program to obtain the desired results. An enhancement method is then applied to improve the quality of the image. Digitizing cuneiform tablets provides historians a working document with legibility of 90 to 95 per cent. Aside from its relatively efficiency, digital imaging can also allow for the registering of various tablets in one excavation season and can be employed in the digital registration of all sealings such as pottery sherds, and fingerprints on clay vessels.

scholarly journals Establishing the true causes of defects to ensure the quality of continuously cast billets and hot‑rolled products at all stages of the process chain at OJSC “BSW – Management Company of the Holding “BMC”

2021 ◽  
pp. 35-39
Author(s):  
A. V. Tereshchenko ◽  
I. A. Kovaleva
Keyword(s):  
Surface Defects ◽  
Mechanical Damage ◽  
Steel Grade ◽  
Cast Billet ◽  
Hot Metal ◽  
Continuously Cast Billet ◽  
Continuously Cast ◽  
Metal Products ◽  
Hot Rolled

Establishing the true causes of defects is one of the main prerequisites for improving the quality of metal products. One of the undesirable phenomena in the production of continuously cast billets, hot‑rolled products is the oxidation of hot metal in the environment with the formation of scale on its surface. Defects, which are violations of the continuity of the metal and deviations from the normal specified macro‑and microstructure, signifi antly reduce the technological plasticity of the metal in the conditions of its processing and operational stability.After hot rolling of a circle of 95 mm steel grade 30MpV4, surface defects were found in the finishing line. To study and establish the nature of surface defects from hot‑rolled blanks, as well as continuously cast blanks, samples were taken.Analyzing metallographic studies of defects and the production technology of the studied steel grade 30MnB4, it was found that the defects were formed as a result of mechanical damage to the continuously cast billet in the area of the pulling‑correct unit. The reason for the formation of the defect is the ingress of scale on the guide rollers.

scholarly journals Klasifikasi Mutu Buah Pala (Myristica Fragrans Houtt) Berbasis Pengolahan Citra Menggunakan Metode Deep Learning Arsitektur Faster R-CNN

2019 ◽  
Vol 6 (2) ◽  
pp. 106
Author(s):  
Muh Subhan ◽  
Hasan Basri
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Deep Learning ◽  
Processing Time ◽  
Surface Defects ◽  
Shape Parameters ◽  
Land Area ◽  
Long Time ◽  
Myristica Fragrans Houtt

Fakfak is the number one nutmeg producing area in Indonesia with a land area of around 16,011 Ha. Nutmeg production is projected to continue to increase until 2020, recorded in 2011 the production of nutmeg in particular reached 12,884 tons or 25 percent of the total Indonesian nutmeg production. This increase was not followed by an increase in market share. One solution to get a wider nutmeg market is exports. But currently not all requests for nutmeg can be fulfilled, because the quality of the nutmeg does not meet the requirements requested. One factor is the surface defects in the nutmeg skin that affects the quality of the fruit, especially the appearance of the fruit. The sorting of nutmegs has so far been using conservative methods, namely by observation based on experience (self-taught). This manual method is felt to be less effective because it depends on the conditions and conditions of the sorting staff, different perceptions between each sorter, takes a long time, requires large costs and involves many workers. To deal with these problems, our previous research developed a method for classifying nutmeg seeds, using image processing methods with color and shape parameters combined with a neural network and sigmoid convolution classification algorithm as a validation method, an accuracy of 87%, but this has not been said to be optimal so we try to use the same approach with the latest method improvements using the R-CNN Faster obtained the best accuracy of 95% with a learning rate of 4000 with a processing time of 0.04 minutes per second.

scholarly journals A ResNet50-Based Method for Classifying Surface Defects in Hot-Rolled Strip Steel

Mathematics ◽  
2021 ◽  
Vol 9 (19) ◽  
pp. 2359
Author(s):  
Xinglong Feng ◽  
Xianwen Gao ◽  
Ling Luo
Keyword(s):  
Classification Accuracy ◽  
Surface Defects ◽  
Rolled Strip ◽  
Defect Classification ◽  
Original Solution ◽  
Automotive Manufacturing ◽  
Strip Steel ◽  
Hot Rolled Strip ◽  
Hot Rolled

Hot-rolled strip steel is widely used in automotive manufacturing, chemical and home appliance industries, and its surface quality has a great impact on the quality of the final product. In the manufacturing process of strip steel, due to the rolling process and many other reasons, the surface of hot rolled strip steel will inevitably produce slag, scratches and other surface defects. These defects not only affect the quality of the product, but may even lead to broken strips in the subsequent process, seriously affecting the continuation of production. Therefore, it is important to study the surface defects of strip steel and identify the types of defects in strip steel. In this paper, a scheme based on ResNet50 with the addition of FcaNet and Convolutional Block Attention Module (CBAM) is proposed for strip defect classification and validated on the X-SDD strip defect dataset. Our solution achieves a classification accuracy of 94.11%, higher than more than a dozen other compared deep learning models. Moreover, to adress the problem of low accuracy of the algorithm in classifying individual defects, we use ensemble learning to optimize. By integrating the original solution with VGG16 and SqueezeNet, the recognition rate of oxide scale of plate system defects improved by 21.05 percentage points, and the overall defect classification accuracy improved to 94.85%.

Characterization of homoepitaxial diamond films by Electron microscopy

1991 ◽  
Vol 49 ◽  
pp. 880-881
Author(s):  
D.P. Malta ◽  
S.A. Willard ◽  
R.A. Rudder ◽  
G.C. Hudson ◽  
J.B. Posthill ◽  
...  
Keyword(s):  
Electron Microscopy ◽  
Surface Defects ◽  
Substrate Surface ◽  
Diamond Films ◽  
Chemical Vapor ◽  
Polycrystalline Diamond ◽  
Large Degree ◽  
Rf Plasma ◽  
Semiconducting Diamond

Semiconducting diamond films have the potential for use as a material in which to build active electronic devices capable of operating at high temperatures or in high radiation environments. A major goal of current device-related diamond research is to achieve a high quality epitaxial film on an inexpensive, readily available, non-native substrate. One step in the process of achieving this goal is understanding the nucleation and growth processes of diamond films on diamond substrates. Electron microscopy has already proven invaluable for assessing polycrystalline diamond films grown on nonnative surfaces.The quality of the grown diamond film depends on several factors, one of which is the quality of the diamond substrate. Substrates commercially available today have often been found to have scratched surfaces resulting from the polishing process (Fig. 1a). Electron beam-induced current (EBIC) imaging shows that electrically active sub-surface defects can be present to a large degree (Fig. 1c). Growth of homoepitaxial diamond films by rf plasma-enhanced chemical vapor deposition (PECVD) has been found to planarize the scratched substrate surface (Fig. 1b).

Sign in / Sign up

Export Citation Format

Share Document