Abstract  One of the difficult problems recognized in image p rocessing and pattern analysis, in particular in medical imaging applications is boundary detection. The detection o f skin lesion boundaries accurately allows, skin cancer detection .There is no unified approach to this problem, which has been found to be application dependent. Early diagnosis of melanoma is a challenge, especially for general practitioners, as melanomas are hard to distinguish from common mole s, even for experienced dermatologists. Melanoma can be cured b y simple excision, when diagnosed at an early stage. Our proposed improved iterative segmentation algorithm, using ca nny edge detector, which is a simple and effective method to find the border of real skin lesions is presented, that help s in early detection of malignant melanoma and its performance is compared with the segmentation algorithm using canny detecto r [16] developed by us previously for border detection of real skin lesions. The experimental results demonstrate the successful border detection of noisy real skin lesions by our proposed improved iterative segmentation algorithm using canny detect or. We conclude that our proposed segmentation alg orithm, segments the lesion from the image even in the presence of noise for a variety of lesions and skin types and its performance is more reliable than the segmentation algorithm [16] that we have d eveloped previously that uses canny detector, for border detection of real skin lesions for noisy skin lesion diagnosis.  

References

[1] Beevi Z., Sathik M., Kannan S., Hybrid Segmentation Approach and Dominant Intensity Grouping Growing on Medical image, the Journal of Advanced Research Science, vol. 1, no. 2, pp. 103-108

[2] Beevi Z. and Sathik M., A Robust Approach for Noisy Medical Images An Improved Iterative Segmentation Algorithm using Canny Edge Detector for Skin Lesion Border Detectio n Segmentation algorithms for skin lesion border detection the proposed improved segmentation algorithm using canny edge detector an d algorithm using canny edge detector

[16] for tracing performance means the performance of the proposed improved segmentation algorithm using canny edge detector fo r tracing the border of noisy skin lesion images is better than the performance of the segmentation algorithm ] for tracing the border of In conclusion, this paper presents a simple yet effective (improved iterative segmentation algorithm using canny edge detector) f or , its performance ithm using canny ] in the border detection of real noisy skin tion of skin lesion boundaries llows, skin cancer detection. There is no this problem, which has been found To validate the capability of the segmentation algorithm in detecting the border of the lesions for skin lesion diagnosis, the algorithm was image containing experimental results successful border detection of real skin lesions by our proposed improved iterative segmentation algorithm using canny edge detector fo r with noise and make them available for further analysis and research. We proposed improved iterative segmentation algorithm using canny edge detector is of the skin lesions, even in the presence of noise for a variety of lesions, and skin types and we conclude that its performance is reliable than the segmentation algorithm that uses for border detection of noisy real Sathik M., Kannan S., and Yasmin J., Hybrid Segmentation Approach using FCM and Dominant Intensity Grouping with Region the International Research in Computer 108, 2010 . Sathik M., A Robust Segmentation Images using Fuzzy Clustering with Spatial Probability, International Arab Journal of Information Technology , vol. 9, no.

[3] Celebi E., Kingravi H., Aslandogan A., Stoecker W., J., and Marghoob A., Detection in Dermoscopy Images Statistical Region Merging, SPIE, Medical Imaging Francisco, USA, pp. 1

[4] Celebi E., Iyatomi H., Stoecker W., Lesion Dermoscopy Images Medical Imaging and Graphics pp.148-153, 2009.

[5] Ercal F., Moganti M., Stoecker W., Detection of Skin Tu Images, the IEEE Transactio Imaging , vol. 12, no. 3

[6] Garnavi R., Aldeen M., Celebi E., Bhuiyan A., Dolianitis C., and Varigos G Segmentation of Dermoscopy Images Histogram Thresholding on Optimal Color Channels, the International Journal of Biological and Life Sciences 126-134, 2012.

[7] Gonzalez R., Woods R., Image Processing using USA, 2003.

[8] Gonzalez R. and Woods R., Processing , Prentice-Hall, India

[9] Jung C. and Scharcanski J., Dermatological Color Images in the Wavelet Domain, IEEE Journa Signal Processing , vol. 3,

[10] Kang W., Yang Q., Comparative Research on Image Segmentatio Algorithms, in Proceedings of the 1 International Workshop on Education Technology and Computer Science China, pp. 703-707, 2009

[11] Mendonca T., Marcal A., Vieira A., J., Silveira M., Marques J., Comparison of Segmentation Methods for Automatic Diagnosis Images, in Proceedings of the International Conference of the IEEE EMBS Cit Internationale , 6575, 2007.

[12] Rodr guez R. and Suarez G. for Image Segmentation by Mean Shift Filtering, and Essay , vol. 1, no. 2,

[13] Shen T., Li H., and Huang X. Models for Medical Image Segmentation IEEE Transactions on Medical no. 3, pp. 774-789, 2011 An Improved Iterative Segmentation Algorithm using Canny Edge Detector for Skin Lesion Border Detectio n 331 Spatial Probability, the International Arab Journal of Information o. 1, pp. 74-83, 2012. Kingravi H., Iyatomi H., Lee J., Stoecker W., Moss R., Malters Fast and Accurate Border Dermoscopy Images using Statistical Region Merging, in Proceedings of Imaging: Image Processing , San Francisco, USA, pp. 1-10, 2007. Celebi E., Iyatomi H., and Schaefer G., and Lesion Border Detection in Images, the Computerized Medical Imaging and Graphics, vol. 33, no. 2, Ercal F., Moganti M., Stoecker W., and Moss R., Tumor Boundaries in Color IEEE Transactions on Medical no. 3, pp. 624-627, 1993. Garnavi R., Aldeen M., Celebi E., Bhuiyan A., Dolianitis C., and Varigos G., Automatic Segmentation of Dermoscopy Images using Histogram Thresholding on Optimal Color International Journal of ogical and Life Sciences, vol. 8, no. 2, pp. Gonzalez R., Woods R., and Lettings S., Digital Image Processing using Matlab, Prentice-Hall, Woods R., Digital Image Hall, India, 2008. Scharcanski J., Sharpening Dermatological Color Images in the Wavelet IEEE Journal of Selected Topics in ol. 3, no. 1, pp. 4-13, 2009. Kang W., Yang Q., and Liang R., The Comparative Research on Image Segmentation in Proceedings of the 1st orkshop on Education and Computer Science, Hubei, 2009. Marcal A., Vieira A., Nascimento , Silveira M., Marques J., and Rozeira J., Segmentation Methods for Diagnosis of Dermoscopy eedings of the 29th Annual International Conference of the IEEE EMBS Lyon, France, pp. 6572- and Suarez G., A New Algorithm Image Segmentation by using Iteratively the Mean Shift Filtering, the Scientific Research , no. 2, pp. 43-48, 2006. Shen T., Li H., and Huang X., Active Volume Models for Medical Image Segmentation, the Transactions on Medical Imaging , vol. 30, , 2011. 332 The International Arab Journal of Information Techn ology, Vol. 12, No.4, July 2015

[14] Tsai M., Chan Y., Lin Z., Yang-Mao S., and Huang P., Nucleus and Cytoplast Contour Detector of Cervical Smear Image, Pattern Recognition Letters , vol. 29, no. 9, pp. 1441- 1453, 2008.

[15] Xu L., Jackowski M., Goshtasby A., Roseman D., Bines S., Yu C., Dhawan A., and Huntley A., Segmentation of Skin Cancer Images, available at: http://noodle.med.yale.edu/~mjack/papers/skin 99.pdf, last visited 2012.

[16] Yasmin J., Sathik M., and Beevi Z., Effective Border Detection of Noisy Real Skin Lesions for Skin Lesion Diagnosis by Robust Segmentation Algorithm, the International Journal of Advanced Research in Computer Science , vol. 1, no. 3, pp. 110-116, 2010.

[17] Zortea M., Skr vseth S., Schopf T., Kirchesch H., and Godtliebsen F., Automatic Segmentation of Dermoscopic Images by Iterative Classification, the International Journal of Biomedical Imaging , vol. 2011, no. 3, pp. 1-17, 2011. Jaseema Yasmin has received her BE in ECE, from Barathidasan University, India and ME in computer and communication, Anna University, India in 1993 and 2005, respectively. She is currently pursuing her PhD degree, working with Mohamed Sathik. She is working as Associate Professor in National College of Engineering. Mohamed Sathik completed his BSc and MSc degrees from Department of Mathematics, MPhil. from Department of Computer Science, MTech from Department of Computer Science and IT, MS from Department of Counseling and Psycho Therapy and MBA degree from reputed institutions. He has two years working experience a s a coordinator for MPhil computer science program, directorate of distance and continuing education, M S University. He served as Additional Coordinator in Indra Gandhi National Open University for four year s. He headed the University Study Center for MCA Week End Course, Manonmaniam Sundaranar University for 9 years. He has been with the Department of Computer Science, Sadakathullah Appa College for more than 23 years. Currently, he is working as the Principal in the same college. He works in the field of Image Processing, specializin g particularly in medical imaging. He has guided 30 MPhil Computer Science Scholars and guiding 14 PhD Computer Science Scholar from MS University, Tirunelveli, Barathiyar University, Coimbatore and Periyar Maniammai University. He has presented 12 papers in international conferences in image processing and 10 papers in national conferences. H e has published 5 papers in International Journals an d 5 papers in proceedings with ISBN.