Real-time defect detection on highly reflective curved surfaces

Real-Time Curvature Defect Detection on Outer Surfaces Using Best-Fit Polynomial Interpolation

“…In the final analysis it is recommended that to inspect surfaces with high precision, the system should install high-resolution cameras and use low interpolation-error to achieve more accurate results. Compare to the other methods such as [1,2,4,5] that inspect outer surface for blob, weld and spot, our method is only able to detect blobs and welds approximately as large as 0.3 mm. Moreover, methods in [3,5–7] are specified to find flatness and waviness defect of outer surface, our method is accurate to find flatness with 0.33 mm −1 deviation.…”

“…Previous works concentrated their efforts on capturing and analyzing the outer surfaces of spheres and cylindrical objects by locating the camera above these objects [1]. In our proposed method, the camera inspects the outer surface of a cylinder from the side, as illustrated in Figure 1.…”

“…Using a mirror causes reflected noises to decrease, and a camera captures the surface indirectly, with less noise [1]. Jia et al proposed a real-time inspection system for steel surfaces with complicated defect patterns.…”

Automatic Defect Classification on a Production Line

“…To the scope, the statistics of the defect local width and local orientation is computed as described for threads in "Threads" section (Eqs. (7,8). In particular, the mean and standard deviation of the local defect width, μ S and σ S , allow determining a degree of compactness, c, of the blob:…”

“…Quality control of the production is a key element for the success on the market in very different fields [1][2][3][4][5][6] and different technologies have been adopted according to the peculiarities of the material and of the defects, ranging from X-rays [7], to B N. Alberto Borghese alberto.borghese@unimi.it http://ais-lab.dsi.unimi.it 1 Applied Intelligent Systems Laboratory, AIS-Lab, Department of Computer Science, Università degli Studi di Milano, Via Comelico, 39,20135 Milano, Italy laser [8][9][10], microscopy [11], ultrasound, [12], thermal [13] or electromagnetic field [13]. In the field of textile industry, defect identification is carried out mainly by video-inspection systems that analyze in real-time the material passing at high speed on a production line [14][15][16][17][18] (Fig.…”