Colour, Texture, and Shape Features based Object Recognition Using Distance Measures

Full Text (PDF, 919KB), PP.42-50

Views: 0 Downloads: 0

Author(s)

S.M. Mohidul Islam 1,* Farhana Tazmim Pinki 1

1. Computer Science and Engineering Discipline, Khulna University, Khulna, Bangladesh

* Corresponding author.

DOI: https://doi.org/10.5815/ijem.2021.04.05

Received: 22 Jun. 2021 / Revised: 2 Jul. 2021 / Accepted: 25 Jul. 2021 / Published: 8 Aug. 2021

Index Terms

Color Histogram, Gabor Wavelet, Hough Transform, Nearest Neighbor, Ensemble of Distance Measures.

Abstract

Object recognition is the recognizing process of objects into semantically expressive classes using its visual insides. Classification of objects becomes complex and challenging task because of its size, poor image quality, occlusion, scaling, geometric distortion, lightening, etc. In this paper, global descriptors that means Color, Texture, and Shape features are used to recognize object. Color histogram is used to obtain the color content, texture content is obtained using Gabor wavelet, and shape content is extracted using Hough transform. These low level or global features are used for creating feature vector. Distance measure is used to find the 1-Nearest Neighbor from the training images i.e. object with minimum distance or maximum similarity with visual contents of the query image. The class of that training image is the predicted label of the query image. We have used twelve different distance measures: some are metrics, some are non-metrics and finally, their recognition accuracy is compared. Ensemble of these distance measures is also used for object recognition in the image. We evaluate this method on a publicly available object-recognition dataset: Columbia Object Image Library (COIL-100) dataset. The experiments show that the recognized results outperform many state-of-the-art methods.

Cite This Paper

S.M. Mohidul Islam, Farhana Tazmim Pinki, " Colour, Texture, and Shape Features based Object Recognition Using Distance Measures", International Journal of Engineering and Manufacturing (IJEM), Vol.11, No.4, pp. 42-50, 2021. DOI: 10.5815/ijem.2021.04.05

Reference

[1]Najva, N., K. Edet Bijoy. SIFT and tensor based object detection and classification in videos using deep neural networks. Procedia Computer Science 2016; 93: 351-358.

[2]Hussin, R., Juhari, M. R., Kang, N. W., Ismail, R. C., Kamarudin, A. Digital image processing techniques for object detection from complex background image. Procedia Engineering 2012; 41: 340-344.

[3]Peter, K., Rota Bulò, S., Antonio, C., Pushmeet, K., Marcello, P., Horst, B. Context-Sensitive Decision Forests for Object Detection 2012; 440-448.

[4]Marée, R., Geurts, P., Piater, J., Wehenkel, L. Decision trees and random subwindows for object recognition. In ICML workshop on Machine Learning Techniques for Processing Multimedia Content (MLMM2005), 2005.

[5]Muralidharan, R., Chandrasekar, C. Object recognition using SVM-KNN based on geometric moment invariant. International Journal of Computer Trends and Technology. 2011 Aug; 1(1):215-20.

[6]Blackwell, P., Austin, D. Appearance Based Object Recognition with a Large Dataset using Decision Trees. In Proceedings of the Australasian Conference on Robotics and Automation, 2004.

[7]Opelt, A., Pinz, A., Fussenegger, M., Auer, P. Generic object recognition with boosting. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2006 Jan 23; 28(3):416-31.

[8]RGB color model. https://en.wikipedia.org/wiki/RGB_color_model. Last accessed date: 23 March, 2021.

[9]Color histogram. https://en.wikipedia.org/wiki/Color_histogram. Last accessed date: 23 March, 2021.

[10]Lee TS. Image representation using 2D Gabor wavelets. IEEE Transactions on pattern analysis and machine intelligence. 1996 Oct;18(10):959-71.  

[11]Daugman, John. Computer Vision Lecture Series. University of Cambridge.

[12]Daugman, John. Information Theory Lecture Series. University of Cambridge.

[13]Kuse, Manohar, Yi-Fang Wang, Vinay Kalasannavar, Michael Khan, and Nasir Rajpoot. "Local isotropic phase symmetry measure for detection of beta cells and lymphocytes." Journal of Pathology Informatics 2, 2011.

[14]Edge. https://www.mathworks.com/help/images/ref/edge.html. Accessed date: 30 March, 2021.

[15]Hough. https://www.mathworks.com/help/images/ref/hough.html. Accessed date: 30 March, 2021.

[16]Rgb2gray. https://www.mathworks.com/help/matlab/ref/rgb2gray.html. Accessed date: 30 March, 2021.

[17]Cai, Fei, Honghui Chen, and Jianwei Ma. "Man-made object detection based on texture visual perception." International Journal of Engineering and Manufacturing (IJEM), MECS, Vol. 2, no. 3, pp. 1-8, 2012.

[18]Mani, M. Radhika, G. P. S. Varma, D. M. Potukuchi, and Ch Satyanarayana. "Design of a novel shape signature by farthest point angle for object recognition." I.J. Image, Graphics and Signal Processing (IJIGSP), MECS,  Vol. 7, no. 1, pp. 35-46, 2015.

[19]Mishra, P.K. and Saroha, G.P., A study on classification for static and moving object in video surveillance system. International Journal of Image, Graphics and Signal Processing (IJIGSP), MECS, Vol. 8, No. 5, pp.76-82, 2016.

[20]Jain, S.K. and Rajankar, S.O., Real-Time Object Detection and Recognition Using Internet of Things Paradigm. International Journal of Image, Graphics and Signal Processing, (IJIGSP), MECS, Vol. 9, No. 1, pp.18-26, 2017.

[21]Khalifa, F.A., Semary, N.A., El-Sayed, H.M. and Hadhoud, M.M.. Local detectors and descriptors for object class recognition. International Journal of Intelligent Systems and Applications (IJISA), MECS, Vol. 7, No. 10, pp.12-18, 2015.

[22]Ma, L., Liu, Y., Jiang, H., Wang, Z. and Zhou, H. An improved method of geometric hashing pattern recognition. International Journal of Modern Education and Computer Science (IJMECS), MECS, Vol. 3, No. 3, pp.1-7, 2011.

[23]https://en.wikipedia.org/wiki/Gabor_wavelet. Accessed date: 31 March, 2021.

[24]https://en.wikipedia.org/wiki/Hough_transform. Accessed date: 31 March, 2021.