Defect detection in thermal image using thresholding technique

This paper proposes a technique to detect defects as depicted in a thermal image. The technique is based on a local neighborhood pixel operation using kernel window 3×3. All pixels within this window will be mapped to only a single pixel value. Next, the thresholding technique is used. The main focus of the employed thresholding technique is the popular Otsu method and testing with other global thresholding technique is also given in the text. From the results obtained, it is shown that the proposed method is able to detect defects occur in a thermal image using any standard thresholding technique which is not designed for thermal images. The technique is easy to implement yet the result is promising.

[1]  S. Araki,et al.  Segmentation of thermal images using the fuzzy C-means algorithm , 1993, [Proceedings 1993] Second IEEE International Conference on Fuzzy Systems.

[2]  Xavier Maldague,et al.  Theory and Practice of Infrared Technology for Nondestructive Testing , 2001 .

[3]  R. Sapina.  Computing textural features based on co-occurrence matrix for infrared images , 2001, ISPA 2001. Proceedings of the 2nd International Symposium on Image and Signal Processing and Analysis. In conjunction with 23rd International Conference on Information Technology Interfaces (IEEE Cat..

[4]  Majumder Dtuta,et al.  Digital Image Processing and Analysis , 2004 .

[5]  Josef Kittler,et al.  On threshold selection using clustering criteria , 1985, IEEE Transactions on Systems, Man, and Cybernetics.

[6]  T. W. Ridler,et al.  Picture thresholding using an iterative selection method. , 1978 .

[7]  Naser A Hamadani.  Automatic target cueing in IR imagery , 1981 .

[8]  Liu Jian,et al.  Infrared image segmentation via intelligent genetic algorithm based on maximum entropy , 2004, Proceedings 7th International Conference on Signal Processing, 2004. Proceedings. ICSP '04. 2004..

[9]  Kozo Saito,et al.  IR self-referencing thermography for detection of in-depth defects , 2005 .

[10]  Behrooz Kamgar-Parsi.  Improved image thresholding for object extraction in IR images , 2001, Proceedings 2001 International Conference on Image Processing (Cat. No.01CH37205).

[11]  R. Ghys.  [Infrared thermography]. , 1970, Les cahiers du nursing.

[12]  Denis Poussart,et al.  Thermographic nondestructive evaluation (NDE): an algorithm for automatic defect extraction in infrared images , 1990, IEEE Trans. Syst. Man Cybern..

[13]  Jun-Wei Hsieh,et al.  New automatic multi-level thresholding technique for segmentation of thermal images , 1997, Image Vis. Comput..

[14]  Chein-I Chang,et al.  Unsupervised approach to color video thresholding , 2004 .

[15]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .