Görüntüdeki Farklı Nesneyi Renk ve Şekil Özelliklerini Kullanarak Tespit Etme

Yıl 2021, Cilt: 11 Sayı: 2, 1 - 7, 26.07.2021

Şafak Altay Açar

https://doi.org/10.35354/tbed.815317

Öz

Bu çalışmada bir görüntü üzerindeki nesnelerden farklı olanı tespit eden iki farklı yöntem sunulmaktadır. İlk yöntemde görüntüdeki nesnelerin renk özellikleri kullanılmaktadır. İkinci yöntemde ise şekil özellikleri kullanılmaktadır. Öncelikle görüntü üzerindeki nesneler 2 girişli ve 6 çıkışlı bir yarışmacı öğrenme ağı ile kümelendirilerek belirlenmektedir. Sonra da sunulan yöntemlerden biri kullanılarak nesnelerden farklı olan tespit edilmektedir. Deneysel çalışmalarda 80 farklı nesne ve 160 farklı görüntü kullanılmıştır. Renk özelliklerini kullanan yöntem %90 başarı elde etmiştir. Şekil özelliklerini kullanan yöntem %73.75 başarı elde etmiştir. Elde edilen sonuçlar birbirleriyle karşılaştırılarak değerlendirilmiştir. Ayrıca yarışmacı öğrenme ağının kümelendirme performansı da ayrıyeten incelenmiştir. Gelecek çalışmalar hakkında öneriler sunulmuştur.

Anahtar Kelimeler

Nesne tespiti, Yarışmacı öğrenme ağı, Kümeleme

Detection Different Object in Image Using Colour and Shape Properties

Öz

In this study, two different methods which detect different one from objects in an image are presented. In the first method, colour properties of object in image are used. In the second method, shape properties of object in image are used. Firstly, objects in image are determined by clustering using a competitive learning network with 2 inputs and 6 outputs. Then, different one from objects is detected by using one of proposed methods. 80 different objects and 160 different images are used in experimental studies. The method using the colour properties achieved 90% success. The method using the shape properties achieved 73.75% success. Obtained results were evaluated by comparing each other. Also, clustering performance of competitive learning network was examined separately. Suggestions about future studies are presented.

Anahtar Kelimeler

Object detection, Competitive learning network, Clustering

Kaynakça

• Chen, Y., Zhu, L., Yuille, A., Zhang, H. 2009. Unsupervised Learning of Probabilistic Object Models (POMs) for Object Classification, Segmentation, and Recognition Using Knowledge Propagation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(10), 1747-1761.
• Proß, W., Quint, F., Otesteanu, M. 2010. Using PEG-LDPC Codes for Object Identification. 9th International Symposium on Electronics and Telecommunications, 11-12 Nov., Timisoara, Romania, 361-364.
• Sahbi, H., Audibert, J., Keriven, R. 2011. Context-Dependent Kernels for Object Classification. IEEE Transactions on Pattern Analysis and Machine Intelligence, 33(4), 699-708.
• Islam, M. K., Jahan, F., Min, J., Baek, J. 2011. Object Classification Based on Visual and Extended Features for Video Surveillance Application. 8th Asian Control Conference, 15-18 May, Kaohsiung, Taiwan, 1398-1401.
• Quang, V. D., Ban, D. V., Ha, H. C. 2012. A Method of Object Identification Based on Fuzzy Object Functional Dependencies in Fuzzy Object-Oriented Databases. Fourth International Conference on Knowledge and Systems Engineering, 17-19 Aug., Danang, Vietnam, 46-53.
• Kim, K., Kim, J., Kang, S., Kim, J., Lee, J. 2012. Object Recognition for Cell Manufacturing System. 9th International Conference on Ubiquitous Robots and Ambient Intelligent, 26-28 Nov., Dajeon, Korea, 512-514.
• Chen, J., Hu, C., Yuan, X., Feng, Z., Miao, H. 2013. An Identification and Classification Method for Circular Object Based on Rotating Image Template Matching. IEEE International Conference on Mechatronics and Automation, 4-7 Aug., Takamatsu, Japan, 1338- 1343.
• Kim, K., Kang, S., Kim, J., Lee, J., Kim, J., Kim, J. 2013. Multiple Objects Recognition for Industrial Robot Applications. 10th International Conference on Ubiquitous Robots and Ambient Intelligence, 30 Oct.-2 Nov., Jeju, Korea, 257-259.
• Higa, K., Iwamoto, K., Nomura, T. 2013. Multiple Object Identification Using Grid Voting of Object Center Estimated from Keypoint Matches. IEEE International Conference on Image Processing, 15-18 Sept., Melbourne, Australia, 2973-2977.
• Peng, L., Yang, Y., Qi, X., Wang, H. 2014. Highly Accurate Video Object Identification Utilizing Hint Information. International Conference on Computing, Networking and Communications, 3-6 Feb., Honolulu, USA, 317-321.
• Jang, H., Yang, H., Jeong, D., Lee, H. 2015. Object Classification using CNN for Video Traffic Detection System. 21st Korea-Japan Joint Workshop on Frontiers of Computer Vision, 28-30 Jan., Mokpo, South Korea.
• Liang, C., Juang, C. 2015. Moving Object Classification Using a Combination of Static Appearance Features and Spatial and Temporal Entropy Values of Optical Flows. IEEE Transactions on Intelligent Transportation Systems, 16(6), 3453-3464.
• Oka, T., Morimoto, M. 2015. An Extraction and Recognition Method for Partially Hidden Objects. International Conference on Informatics, Electronics & Vision, 15-18 June, Fukuoka, Japan.
• Shehnaz, M., Naveen, N. 2015. An Object Recognition Algorithm with Structure-Guided Saliency Detection and SVM Classifier. International Conference on Power, Instrumentation, Control and Computing, 9-11 Dec., Thrissur, India.
• Horiguchi, H., Ikeshiro, K., Imamura, H. 2016. Recognition for Objects by Relationship Between Attributes. Third International Conference on Digital Information Processing, Data Mining, and Wireless Communications, 6-8 July, Moscow, Russia, 307-312.
• Dai, C. 2016. Online Surveillance Object Classification With Training Data Updating. International Conference on Audio, Language and Image Processing, 11-12 July, Shanghai, China, 733-737.
• Reddy, A. V. N., Phanikrishna, Ch. 2016. Contour Tracking Based Knowledge Extraction And Object Recognition Using Deep Learning Neural Networks. 2nd International Conference on Next Generation Computing Technologies, 14-16 Oct., Dehradun, India, 352-354.
• Zhang, H., Zhuang, B., Liu, Y. 2017. Object Classification Based on 3D Point Clouds Covariance Descriptor. IEEE International Conference on Computational Science and Engineering and IEEE International Conference on Embedded and Ubiquitous Computing, 21-24 July, Guangzhou, China, 234-237.
• Yan, L., Wang, Y., Song, T., Yin, Z. 2017. An Incremental Intelligent Object Recognition System Based on Deep Learning. Chinese Automation Congress, 20-22 Oct., Jinan, China, 7135-7138.
• Sujana, S. R., Abisheck, S. S., Ahmed, A. T., Chandran, K. R. S. 2017. Real Time Object Identification Using Deep Convolutional Neural Networks. International Conference on Communication and Signal Processing, 6-8 April, Chennai, India, 1801-1805.
• Bychkov, I. V., Rugnikov, G. M., Fedorov, R. K., Avramenko, Y.V. 2018. Object Identification on Raster Images by User Query. 3rd Russian-Pacific Conference on Computer Technology and Applications, 18-25 Aug., Vladivostok, Russia.
• Hayat, S., Kun, S., Tengtao, Z., Yu, Y., Tu, T., Du, Y. 2018. A Deep Learning Framework Using Convolutional Neural Network for Multi-class Object Recognition. IEEE 3rd International Conference on Image, Vision and Computing, 27-29 June, Chongqing, China, 194-198.
• Sonoda, J., Kimoto, T. 2018. Object Identification form GPR Images by Deep Learning. Asia-Pacific Microwave Conference, Kyoto, Japan, 1298-1300.
• Liu, J., Gao, M. 2008. Unsupervised Classification Algorithm for Intrusion Detection based on Competitive Learning Network. International Symposium on Information Science and Engieering, 20-22 Dec., Shanghai, China, 519-523.
• Theodoris, S., Koutroumbas, K. 2003. Pattern Recognition. 2nd edn, USA, Academic Press, chapter 15, 552-555.
• Kumar, G., Bhatia, P. K. 2014. A Detailed Review of Feature Extraction in Image Processing Systems. Fourth International Conference on Advanced Computing & Communication Technologies, 8-9 Feb., Rohtak, India, 5-12.
• Geusebroek, J. M., Burghouts, G. J., Smeulders, A. W. M. 2005. The Amsterdam Library of Object Images. Int. J. Comput. Vision, 61(1), 103-112.
• Davies, D. L., Bouldin, D. W. 1979. A Cluster Separation Measure. IEEE Transactions on Pattern Analysis and Machine Intelligence, PAMI-1(2), 224-227.