Image Processing and Feature Extraction Techniques for Hard Disk Platter Defect Diagnosis

Main Article Content

อาคม ทิพย์มณี


- This paper describes a result from the development of image processing and feature extraction techniques for an image of a hard disk plate containing scratch on its surface. The work is part of the development of an information system for hard disk plate defect diagnosis. Such defect is a result of a hard disk manufacturing process. Given an image taken by an electron microscope, it needs to pass through an image reprocessing step. In addition to general image enhancement, this step involves detection of annotated text placed at the bottom part of the image at the time it was taken. The location of such annotated text is needed so that it can be removed before the image is passed to the next step, which involves extraction of features representing the defect. In addition, this preprocessing step is used to recognize certain text information regarding to the magnification level used for taking the image. Such magnification level information is very important for subsequent steps. Here, location and brightness characteristics of annotated text are exploited for the estimation. A template matching technique is used for recognizing certain characters describing the magnification level. After the preprocessing step, the image is used to extract certain features characterizing scratch on a hard disk plate. In this paper, a Hough transform and an image gradient are used for feature extraction. The resulting feature is used in a subsequent process of retrieving relevant images from an image database of previous diagnosis cases. The retrieved information is useful for diagnosis of the defect’s root cause.


Article Details

How to Cite
ทิพย์มณีอ. (2010). Image Processing and Feature Extraction Techniques for Hard Disk Platter Defect Diagnosis. JOURNAL OF INFORMATION SCIENCE AND TECHNOLOGY, 1(1), 54-62.
Research Article: Soft Computing (Detail in Scope of Journal)


1. Ritendra Datta, Dhiraj Joshi, Jia Li and James Z. Wang, ``Image Retrieval: Ideas, Influences, and Trends of the New Age,'' ACM Computing Surveys, vol. 40, no. 2, article 5, pp. 1-60, 2008.

2. F. Long, H.J Zhang, D. D Feng, “Fundamentals of content-based image retrieval,” Multimedia Information Retrieval and Management, Springer, Berlin, 2003.

3. Dong-Chen HE and Li Wang, “Texture Unit, Texture Spectrum, and Texture Analysis,” IEEE Trans .On Geosciences and Remote Sensing, Vol. 28, No. 4, pp. 509-512, 1990.

4. R. M. Haralick, K. Shanmugam and I. Dinstein, “Texture Feature for Image Classification,” IEEE Trans. On Systems Man Cybernatics, p.610-621, 1973.

5. T. Acharya, and A. K. Ray, Image Processing: Principles and Applications. New Jersey: John Wiley & Sons, Inc., 2005.

6. R. C. Gonzalez, and R. E. Woods, Digital Image Processing, 2nd Ed. New Jersey: Prentice -Hall, Inc., 2002.

7. D. H. Ballard, “Generalizing the Hough Transform to detect arbitrary shapes,” Pattern Recognition. 13(2). pp. 111-122, 1981.