Abstract




 
   

IJE TRANSACTIONS B: Applications Vol. 26, No. 11 (November 2013) 1281-1288   

downloaded Downloaded: 220   viewed Viewed: 2080

  OBJECT RECOGNITION BASED ON LOCAL STEERING KERNEL AND SVM
 
R. AhilaPriyadharshini and S. Arivazhagan
 
( Received: August 25, 2012 – Accepted in Revised Form: May 16, 2013 )
 
 

Abstract    The proposed method is to recognize objects based on application of Local Steering Kernels (LSK) as Descriptors to the image patches. In order to represent the local properties of the images, patch is to be extracted where the variations occur in an image. To find the interest point, Wavelet based Salient Point detector is used. Local Steering Kernel is then applied to the resultant pixels, in order to obtain the most promising features. The features extracted will be over complete so in order to reduce dimensionality, Principal Component Analysis (PCA) is applied. Further, the sparse histogram is taken over the PCA output. The classifier used here is Support Vector Machine (SVM) Classifier. Bench mark database used here is UIUC car database and the results obtained are satisfactory. The results obtained using LSK kernel is compared by varying parameters such as patch size, number of salient points/patches, smoothing parameter and scaling parameter.

 

Keywords    Object Recognition, Salient Point Detector, Patch extraction, Local Steering Kernel, Principal Component Analysis.

 

چکیده    روش ارائه شده براي تشخيص اشیاء بر اساس استفاده از Local Steering Kernels (LSK) به عنوان توصیفگر تکه های تصویر مي باشد. به منظور نشان دادن خواص يك نقطه از تصاویر که در آن تغییرات رخ می دهد ، پچ مورد استفاده قرار مي گيرد. برای پیدا کردن نقطه مورد نظر، مبتنی بر آشکارساز موجي نقطه برجسته استفاده می شود. سپس، از روش (LSK) به منظور دست يابي به پیکسل مطلوب استفاده مي شود. ویژگی های استخراج شده بيش از حد كامل بوده؛ بنابراین، به منظور کاهش ابعاد، تجزیه و تحلیل اجزای اصلی، روش (PCA) اعمال می شود. علاوه بر این، نمایش طرز انتشار وفواصل وارتفاع سلول ها بیش از PCA خروجی، از هم پراکنده است. طبقه بندی مورد استفاده در اینجا ماشین بردار (SVM) طبقه بندی پشتیبانی است. علامت مشخصه پایگاه داده با استفاده از بانک اطلاعاتی خودرو UIUC است و نتایج به دست آمده رضایت بخش است. نتایج به دست آمده با استفاده از هسته LSK از لحاظ پارامترهای مختلف مانند اندازه پچ، تعدادی از نقاط برجسته به نسبت پچ ها، پارامترهاي وضوح و پارامتر هاي اندازه قابل مقايسه مي باشد.

References   

 

1.     Hegerath, A., Ney, I. H. and Seidl, T., "Patch-based object recognition", Diploma thesis, Human Language Technology and Pattern Recognition Group, RWTH Aachen University, Aachen, Germany, (2006)

2.     Opelt, A., Pinz, A., Fussenegger, M. and Auer, P., "Generic object recognition with boosting", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 28, No. 3, (2006), 416-431.

3.     Shapiro, R. H. L. and Haralick, R., "Computer and robot vision", Reading: Addison-Wesley, (1992).

4.     Harris, C. and Stephens, M., "A combined corner and edge detector", in Alvey vision conference, Manchester, UK. Vol. 15, (1988), 50-58.

5.     Loupias, E., Sebe, N., Bres, S. and Jolion, J.-M., "Wavelet-based salient points for image retrieval", in Image Processing, Proceedings. International Conference on, IEEE. Vol. 2, (2000), 518-521.

6.     Seo, H. J. and Milanfar, P., "Using local regression kernels for statistical object detection", in Image Processing, ICIP, 15th IEEE International Conference on, IEEE, (2008), 2380-2383.

7.     Seo, H. J. and Milanfar, P., "Training-free, generic object detection using locally adaptive regression kernels", Pattern Analysis and Machine Intelligence, IEEE Transactions on,  Vol. 32, No. 9, (2010), 1688-1704.

8.     Takeda, H., Farsiu, S. and Milanfar, P., "Kernel regression for image processing and reconstruction", Image Processing, IEEE Transactions on,  Vol. 16, No. 2, (2007), 349-366.

9.     Seo, H. J. and Milanfar, P., "Face verification using the lark representation", Information Forensics and Security, IEEE Transactions on,  Vol. 6, No. 4, (2011), 1275-1286.

10.   Seo, H. J. and Milanfar, P., "Nonparametric bottom-up saliency detection by self-resemblance", in Computer Vision and Pattern Recognition Workshops, CVPR Workshops, IEEE Computer Society Conference on, IEEE, (2009), 45-52.

11.   Deselaers, T., Heigold, G. and Ney, H., "Object classification by fusing svms and gaussian mixtures", Pattern Recognition,  Vol. 43, No. 7, (2010), 2476-2484.

12.   LeCun, Y., Huang, F. J. and Bottou, L., "Learning methods for generic object recognition with invariance to pose and lighting", in Computer Vision and Pattern Recognition, CVPR, Proceedings of the 2004 IEEE Computer Society Conference on, IEEE. Vol. 2, (2004), II-97-104.

13.   Shaeiri, Z. and Ghaderi, R., "Modification of the fast global k-means using a fuzzy relation with application in microarray data analysis", International Journal of Engineering-Transactions C: Aspects,  Vol. 25, No. 4, (2012), 283.

14.   Mutch, J. and Lowe, D. G., "Object class recognition and localization using sparse features with limited receptive fields", International Journal of Computer Vision,  Vol. 80, No. 1, (2008), 45-57.

15.   Deselaers, T., Hegerath, A., Keysers, D. and Ney, H., "Sparse patch-histograms for object classification in cluttered images", in Pattern recognition, Springer, (2006), 202-211.

16.   Sebe, N. and Lew, M. S., "Comparing salient point detectors", Pattern Recognition Letters,  Vol. 24, No. 1, (2003), 89-96.

17.   Duda, R. O., Hart, P. E. and Stork, D. G., "Pattern classification", John Wiley & Sons,  (2012).

18.   Ma, J., Zhao, Y. and Ahalt, S., "OSU SVM classifier matlab toolbox (ver 3.00)", Pulsed Neural Networks, (2002).

19.   Fergus, R., Perona, P. and Zisserman, A., "Object class recognition by unsupervised scale-invariant learning", in Computer Vision and Pattern Recognition, Proceedings. IEEE Computer Society Conference on, IEEE. Vol. 2, No., (2003), 264 -271

20.   Leibe, B., Leonardis, A. and Schiele, B., "Combined object categorization and segmentation with an implicit shape model", in Workshop on Statistical Learning in Computer Vision, ECCV. Vol. 2, No., (2004), 7-14.

21.           Opelt, A. and Pinz, A., Object localization with boosting and weak supervision for generic object recognition, in Image analysis., Springer, (2005), 862-871. 





International Journal of Engineering
E-mail: office@ije.ir
Web Site: http://www.ije.ir