Abstract
This paper presents an algorithmic model for automatic selection of keyframes for the classification of natural flower videos. For keyframe selection Scale Invariant Feature Transform and Discrete Cosine Transform are recommended. The selected keyframes are further used for classification process. To extract the features from the selected keyframs Deep Convolutional Neural Network (DCNN) is used as a feature extractor and for classification of flower videos Multiclass Support Vector Machine (MSVM) is applied. For experimentation, we have created dataset of natural flower videos consisting of 1825 flower videos of 20 different classes. Experimental results show that the proposed keyframe selection algorithm gives good compression ratio and the proposed classification system generates good classification accuracy.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Lin, H., Yang, X., Pei, J.: Key frame extraction based on multi scale phase based local features. In: ICSP2008 Proceedings. IEEE (2008). (978-1-4244-2179-4/08)
Guru, D.S., Sharath, Y.H., Manjunath, S.: Texture features and KNN in classification of flower images. In: IJCA Special Issue on “Recent Trends in Image Processing and Pattern Recognition", RTIPPR, pp. 21–29 (2010)
Guru, D.S., Sharath, Y.H., Manjunath, S.: Textural features in flower classification. Math. Comput. Model. 54, 1030–1036 (2011)
Das, M., Manmatha, R., Riseman, E.M.: Indexing flower patent images using domain knowledge. IEEE Intell. Syst. 14(5), 24–33 (1999)
Chatzigiorgaki, M., Skodras, A.N.: Real-time keyframe extraction towards video content identification. IEEE (2009). (978-1-4244-3298)
Pentland, A.: Video and image semantics, advanced tools for telecommunications. IEEE Multimedia Summer 1, 73–75 (1994)
Sheena, C.V., Narayanan, N.K.: Key-frame extraction by analysis of histograms of video frames using statistical methods. Procedia Comput. Sci. 70, 36–40 (2015)
Thakre, K.S., Rajurkar, A.M., Manthalkar, R.R.: Video partitioning and secured keyframe extraction of MPEG video. Procedia Comput. Sci. 78, 790–798 (2016)
Kumthekar, A.V., Patil, J.K.: Key frame extraction using color histogram method. IJSRET 2(4), 207–214 (2013)
Ferreira, L., Cruz, L., Assuncao, P.: A generic framework for optimal 2D/3D key-frame extraction driven by aggregated saliency maps
Naveed, E., Mehmood, I., Baik, S.W.: Efficient visual attention based framework for extracting key frames from videos. Sig. Process.: Image Commun. 28, 34–44 (2013)
Sreeraj, M., Asha, S.: Content based video retrieval using SURF descriptor, August. IEEE (2013)
Naveed, E., Tayyab, B.T., Sung, W.B.: Adaptive key frame extraction for video summarization using an aggregation mechanism. J. Vis. Commun. Image R.23, 1031–1040 (2012)
Joe, Y.-H.N., Matthew, H., Sudheendra, V., Oriol, V., Rajat, M., George, T.: Beyond short snippets: deep networks for video classification. In: CVPR2015, pp. 4694–4702. IEEE Xplore (2015)
Nanne, V.N., Eric, P.: Learning scale-variant and scale-invariant features for deep image classification. Pattern Recogn. 61, 583–592 (2017)
Cheng, M.-H., Hwang, K.S., Jeng, J.H., Lin, N.W.: Classification-based video super-resolution using artificial neural networks. Sig. Process. 93, 2612–2625 (2013)
Niu, Y., Zhao, Y., Ni, R.: Robust median filtering detection based on local difference descriptor. Sig. Process.: Image Commun. 53, 65–72 (2017)
Zeng, H., Liu, Y.Z., Fan, Y.M., Tang, X.: An improved algorithm for impulse noise by median filter. In: 2012 AASRI Conference on Computational Intelligence and Bioinformatics, AASRI Procedia, vol. 1, pp. 68–73 (2012)
Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60, 91–110 (2004)
Asnath, Y., Amutha, R.: Discrete cosine transform based fusion of multi-focus images for visual sensor networks. Sig. Process. 95, 161–170 (2014)
Haghighat, M.B.A., Aghagolzadeh, A., Seyedarabi, H.: Multi-focus image fusion for visual sensor networks in DCT domain. Comput. Electr. Eng. 37(5), 789–797 (2011)
Guo, Y., Liu, Y., Oerlemans, A., Lao, S., Wu, S., Lew, M.S.: Deep learning for visual understanding: a review. Neurocomputing 187, 27–48 (2016)
Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Proceedings of the 25th International Conference on Neural Information Processing Systems, vol. 1, pp. 1097–1105 (2012)
Iosifidis, A., Gabbouj, M.: Multi-class support vector machine classifiers using intrinsic and penalty graphs. Pattern Recogn. 55, 231–246 (2016)
Jyothi, V.K., Guru, D.S., Sharath Kumar, Y.H.: Deep learning for retrieval of natural flower videos. Procedia Comput. Sci. 132, 1533–1542 (2018)
Manjnath, S.: Video archival and retrieval system. Thesis, UOM (2012)
Gianluigiand, C., Raimondo, S.: An innovative algorithm for key frame extraction in video summarization. J. Real-Time Image Process. 1, 69–88 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jyothi, V.K., Guru, D.S., Kumar, Y.H.S. (2019). Classification of Natural Flower Videos Through Sequential Keyframe Selection Using SIFT and DCNN. In: Santosh, K., Hegadi, R. (eds) Recent Trends in Image Processing and Pattern Recognition. RTIP2R 2018. Communications in Computer and Information Science, vol 1035. Springer, Singapore. https://doi.org/10.1007/978-981-13-9181-1_27
Download citation
DOI: https://doi.org/10.1007/978-981-13-9181-1_27
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-13-9180-4
Online ISBN: 978-981-13-9181-1
eBook Packages: Computer ScienceComputer Science (R0)