Object identification and classification has been topic of interest for researchers in computer vision due to its numerous applications in various domains since decades. But object detection and classification faces certain issues and challenges like scaling variations, rotational variations, occlusion, noise etc. Hence, there is need to design descriptors which are robust, compact and efficient. The extraction of features and the classification process should be done with minimal compromises in the performances. This paper proposes an orientation and rotation invariant feature descriptor named as ORB (Oriented FAST and Rotated BRIEF). This feature vector computes scale, rotation and translation invariant features for the test and trainee images. For matching the computed feature sets we used supervised classification method i.e. K-Nearest Neighbors Algorithm (K-NN) and Support Vector Machine (SVM) for the classification of various object categories in the dataset. Comparative experimental results based on analysis of the SVM and KNN classifiers on the basis of recognition accuracy and execution time is given. Results show that SVM gives better matching score whereas KNN is time efficient in comparison to SVM.

ORB, K-Nearest Neighbour Classifier, SVM, Object Recognition and Classification

[1] Mikolajczyk, K.; Schmid, C., "A performance evaluation of local descriptors," in Computer Vision and Pattern Recognition, Proceedings. 2003 IEEE Computer Society Conference on , vol.2, 18-20 June 2003, pp.II-257-II-263 .
[2] Tinne Tuytelaars and Krystian Mikolajczyk,"Local Invariant Feature Detectors: A Survey", Foundations and Trends® in Computer Graphics and Vision: Vol. 3: No. 3, 2008, pp 177-280.
[3] C. Harris., M Stephens, “A combined corner and edge detector”, Alvey Vision Conf, pp. 147 – 151, 1988.
[4] E. Rosten, R. Porter and T. Drummond, FASTER and better:A machine learning approach to corner detection, IEEE Transaction on Pattern Analysis and Machine Intelligence, Vol. 32, pp.105-119, 2010.
[5] Lowe, D.G.: ‘Distinctive image features from scale-invariant keypoints’, International Journal of Computer Vision., 60, (2), pp. 91 – 110, 2004.
[6] Bay, H., Ess, A., Tuytelaars, T., Gool, L.V.: ‘Surf – speeded up robust features’, Computer Vision and Image Understanding, 110, (3), pp. 346 – 359, 2008.
[7] Ke, Y., and Sukthankar, R., "PCA-SIFT: A More Distinctive Representation for Local Image Descriptors", Computer Vision and Pattern Recognition, 2004.
[8] M. Calonder, V. Lepetit, M. Ozuysal, T. Trzcinski, C. Strecha, and P. Fua, "BRIEF: Computing a local binary descriptor very fast," Pattern Analysis and Machine Intelligence, IEEE Transactions on, vol. 34, no. 7, pp. 1281-1298, July 2012.
[9] S. Leutenegger, M. Chli, and R. Siegwart, "BRISK: Binary robust invariant scalable keypoints," in Computer Vision (ICCV), IEEE International Conference on, pp. 2548 -2555, Nov. 2011.
[10] S. Saha and V. Demoulin, "ALOHA: An efficient binary descriptor based on haar features," in Image Processing (ICIP), 2012 19th IEEE International Conference on, pp. 2345-2348, 2012.
[11] A. Alahi, R. Ortiz, and P. Vandergheynst, “FREAK: Fast Retina Keypoint”, In Proc. IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 510-517.
[12] E. Rublee, V. Rabaud, K. Konolige, and G. R. Bradski, “ORB: An efficient alternative to SIFT or SURF”, in Proc. ICCV, 2011, pp. 2564–2571.
[13] Bremner D, Demaine E, Erickson J, Iacono J,Langerman S, Morin P, Toussaint G, Outputsensitive algorithms for computing nearestneighbor decision boundaries, Discrete and Computational Geometry, 2005, pp. 593–604.
[14] Cover, T., Hart, P. , Nearest-neighbor pattern classification, Information Theory, IEEE Transactions on, Jan. 1967, pp. 21-27.
[15] LI LiLi, ZHANG YanXia and ZHAO YongHeng, “K-Nearest Neighbors for automated classification of celestial objects,” Science in China Series G-Phys Mech Astron, Vol.51, no.7, July 2008, pp. 916- 922.
[16] The PASCAL Visual Object Classes (VOC) Challenge Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J. and Zisserman,A. International Journal of Computer Vision, 88(2), 2010, pp. 303-338.
[17] Zhang, J., Marszałek, M., Lazebnik, S., & Schmid, C. (2007). Local features and kernels for classification of texture and object categories: A comprehensive study. International journal of computer vision, 73(2), 213-238.
[18] Maji, S., Berg, A. C., & Malik, J. (2008, June). Classification using intersection kernel support vector machines is efficient. In 2008 IEEE Conference on Computer Vision and Pattern Recognition (pp. 1-8). IEEE.
[19] Sun, Z., Bebis, G., & Miller, R. (2004). Object detection using feature subset selection. Pattern recognition, 37(11), 2165-2176.
[20] Lin, Y., Lv, F., Zhu, S., Yang, M., Cour, T., Yu, K., ... & Huang, T. (2011, June). Large-scale image classification: fast feature extraction and svm training. In CVPR 2011 (pp. 1689-1696). IEEE
[21] Rani, R., Kumar, R., & Singh, A. P. (2016, January). A Comparative Study of Object Recognition Techniques. In 2016 7th International Conference on Intelligent Systems, Modelling and Simulation (ISMS) (pp. 151-156). IEEE.Rani,
[22] R., Kumar, R., & Singh, A. P. (2018). An empirical evaluation of translational and rotational invariance of descriptors and the classification of flower dataset. Pattern Analysis and Applications, 21(1), 1-18.
[23] Rani, R., Kumar, R., & Singh, A. P. (2016, September). An empirical evaluation of local descriptors in object recognition. In 2016 international conference on advances in computing, communications and informatics (ICACCI) (pp. 1517-1521). IEEE.