Browsing by Author "Chen, Ssu-Han"

Now showing 1 - 6 of 6

A novel internal thread defect auto-inspection system
(2010-03-01)
Perng, Der-Baau
;
Chen, Ssu-Han
;
Chang, Yuan-Shuo
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This paper describes a novel optical thread plug gauge (OTPG) for internal thread inspection using machine vision. The OTPG is composed of a rigid industrial endoscope, a charge-coupled device camera, and a two degree-of-freedom motion control unit. A sequence of partial wall images of an internal thread are retrieved and reconstructed into a 2D unwrapped image. Then, a digital image processing and classification procedure is used to normalize, segment, and determine the quality of the internal thread. The proposed OTPG provides an orientation-free and convenient method for detecting defects such as scratches, collapses, and flaws in an internal thread.
An AOI Approach for IC Lead Index Auto-verification
(2010)
Perng, Der-Baau
;
Chang, Guei-Ci
;
Lee, Shu-Ming
;
Chen, Ssu-Han
;
工業工程與管理學系
To wire-bond automatically, the IC lead positions on the CAD drawing and the corresponding ones on the extracted substrate image should be pre-verified. This paper proposed an AOI approach for IC lead index auto-verification which conquered the lead shape distortion, golden exposed, shifting, rotation, and scaling difficulties of extracted substrate image. Experimentations revealed that the proposed AOI approach can accurately verify the corresponding leads between a CAD drawing and the extracted substrate image with high repeatability.
Automatic Surface Inspection for Directional Textures Using Discrete Cosine Transform
(2009)
Chen, Ssu-Han
;
Perng, Der-Baau
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
A new global image restoration scheme using discrete cosine transform (DCT) is proposed in this paper. This DCT-based image restoration scheme can be used for inspecting the defects in directional texture surfaces automatically. The input spatial domain image is first transformed into DCT domain. The dominating directions of the textures in the input image will be compacted to orthogonal straight lines, respectively, throughout the direct current (DC) component in the spectrum. The linear primitives associated with high-energy frequency components in the DCT domain are eliminated by reducing them to zero and then transformed back to the spatial domain. This procedure will have all directional textures be blurred and will preserve only local defects if they are initially embedded in the input image. Experiments on a variety of product surfaces with directional texture such as straight, slant, orthogonal, and slant orthogonal linear primitives are given to demonstrate the effectiveness and robustness of the proposed method.
Automatic surface inspection for directional textures using nonnegative matrix factorization
(2010-05-01)
Perng, Der-Baau
;
Chen, Ssu-Han
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
A global image restoration scheme using nonnegative matrix factorization (NMF) is proposed in this paper. This NMF-based image restoration scheme can be used for inspecting the defects in directional texture surfaces automatically. Decomposing the gray level of image pixels into an ensemble of row vectors, we first reduce the data set from original data space into a lower-dimensional NMF space. The repetitive and periodical primitives are well reconstructed by two lower-dimensional basis and weight matrices with nonnegative elements, named nonnegative matrix approximation (NMA). Then the local defects will be revealed by applying image subtraction between the original image and the NMA. As a consequence, the directional textures are eliminated, and only local defects are preserved if they initially are embedded in the surface. A supervised heuristic, elbow of residual curve rule, is devised which helps users to determine a proper basis space size of a specific image. Experiments on a variety of directional texture surfaces are given to demonstrate the effectiveness and robustness of the proposed method.
Directional textures auto-inspection using discrete cosine transform
(2011)
Perng, Der-Baau
;
Chen, Ssu-Han
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This paper describes a global image restoration scheme using a discrete cosine transform (DCT) that can be used to detect defects in directional textured surfaces automatically. The input spatial domain image is first transformed into the DCT domain so that the dominant directions of the texture in the input image will be compacted into the orthogonal straight lines or impulses through the direct current (DC) component of the spectrum. The linear primitives associated with the high-energies in the DCT domain are eliminated by reducing them to zero before transforming back to the spatial domain. Finally, the defects, if any, are extracted by the thresholding method. Experiments on a variety of product surfaces with directional textures such as straight, slanted, orthogonal, slanted orthogonal, and oblique linear primitives were conducted in this paper. The proposed scheme would blur directional textures and preserved only local defects if they were initially embedded in the image. Furthermore, some preliminary experiments were also conducted to demonstrate the proposed scheme was insensitive to horizontal and vertical shifting, changes in illumination, and image rotation.
Directional textures auto-inspection using principal component analysis
(2011-08-01)
Chen, Ssu-Han
;
Perng, Der-Baau
;
工業工程與管理學系
;
Department of Industrial Engineering and Management
This paper describes a global image restoration scheme using a principal component analysis that can be used to inspect defects in directional textured surfaces automatically. Decomposing the gray level of image pixels into an ensemble of row vectors, the input spatial domain image is transformed into principal component space so that the directional textures are well approximated by first k major components and their corresponding weight vectors, named truncated component solution (TCS). Then the local defects will be revealed by applying image subtraction between the original image and the TCS. This procedure blurs all directional textures and preserves only the local defects that were initially embedded in the input image. These defects, if any, are finally extracted by thresholding. Experiments on a variety of product surfaces with directional textures such as straight, slanted, orthogonal, slanted orthogonal, and oblique linear primitives were conducted to demonstrate the effectiveness and robustness of the proposed method. Furthermore, some preliminary experiments were also conducted to demonstrate the proposed scheme was insensitive to horizontal and vertical shifting, changes in illumination, and image rotation.