An Efficient Flower Classification System using Feature Fusion

An Efficient Flower Classification System using Feature Fusion

© 2022 by IJETT Journal
Volume-70 Issue-11
Year of Publication : 2022
Authors : M. R. Banwaskar, A. M. Rajurkar
DOI : 10.14445/22315381/IJETT-V70I11P207

How to Cite?

M. R. Banwaskar, A. M. Rajurkar, "An Efficient Flower Classification System using Feature Fusion," International Journal of Engineering Trends and Technology, vol. 70, no. 11, pp. 70-80, 2022. Crossref,

Automatic classification of flowers is essential in research on flowers, medicinal use of flowers, flower patent analysis etc. Traditionally, flower classification is done using low-level features like color, shape, texture and geometry. There exist large intra-class variation and interclass similarity among flower classes. Search engine-based flower identification and classification system are not efficient and robust because they are based on visual search. The accuracy and robustness of flower classification depend highly on the feature descriptor. Deep features have shown excellent performance in the last few years on high-resolution images, but they cannot extract accurate global features from low-resolution images. Hence, an efficient flower classification system using a fusion of handcrafted features and in-depth features is proposed in this paper. Low-level features are extracted using Color Coherent Vector (CCV), Centre Symmetric Local Binary Pattern (CSLBP) and Edge Histogram Descriptor (EHD). Deep features are extracted from pre-trained networks: ResNet-50 and AlexNet. Further, a Multiclass Support Vector Machine (SVM) is used to yield high classification accuracy. Experiments are carried out on Oxford Flower 17, Flower102, Kaggle flower dataset and Corel-1K dataset. Classification accuracy of 100, 95.3, 94 and 92% is obtained on the Corel dataset, Oxford Flower 17, Kaggle flower dataset and flower 102 dataset, respectively, which is better than existing approaches. A remarkable achievement in classification accuracy of 86.4% is observed on the pooled dataset.

Deep Learning, Image descriptor, Convolutional Neural Networks, Image classification, Pooled dataset.

[1] Albadarneh and Ashraf Ahmad, "Automated Flower Species Detection and Recognition from Digital Images," International Journal of Computer Science and Network Security, vol. 17, no. 4, pp. 144-151, 2017.
[2] M. Tian, H. Chen, and Q. Wang, "Flower Identification Based on Deep Learning," Journal of Physics: Conference Series, vol. 1237, no. 2, 2019. Crossref,
[3] M. Mehdipour Ghazi, B. Yanikoglu, and E. Aptoula, "Plant Identification Using Deep Neural Networks via Optimization of Transfer Learning Parameters," Neurocomputing, vol. 235, pp. 228-235, 2017. Crossref,
[4] Kalyan Roy, and Joydeep Mukherjee, "Image Similarity Measure using Color Histogram, Color Coherence Vector, and Sobel Method," International Journal of Science and Research, vol. 2, no. 1, pp. 538-543, 2013.
[5] Heikkilä M, Pietikäinen M, and Schmid C, "Description of Interest Regions with Local Binary Patterns," Pattern Recognition, vol. 42, no. 3, pp. 425-436, 2009. Crossref,
[6] Chee Sun Won, Dong Kwon Park, and Soo-Jun Park, "Efficient Use of MPEG-7 Edge Histogram Descriptor," ETRI Journal, vol. 24, no. 1, pp. 23-30, 2002. Crossref,
[7] K. He, X. Zhang, S. Ren, and J. Sun, "Deep Residual Learning for Image Recognition," in the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016. Crossref,
[8] A. Krizhevsky, I. Sutskever, and G.E. Hinton, "ImageNet Classification with Deep Convolutional Neural Networks," Advances in Neural Information Processing Systems, pp. 1-9, 2012.
[9] Arun Kumar M, and Gopal M, "Ahybrid SVM based Decision Tree," Pattern Recognition, vol. 43, no. 12, pp. 3977–3987, 2010. Crossref,
[10] Visual Geometry Group, "Flower Datasets Home Page," 2009. [Online]. Available:
[11] Wang J.Z, Li J, and Wiederhold G, "SIMPLIcity: Semantics-Sensitive Integrated Matching for Picture Libraries," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 9, pp. 947-963, 2001. Crossref,
[12] Nilsback M, and Zisserman A, "Automated Flower Classification over a Large Number of Classes," 2008 Proceedings of Sixth Indian Conference, pp. 722-729, 2008. Crossref,
[13] Computer Vision, "Graphics & Image Processing," Bhubaneswar, India, pp. 722-729, 2008.
[14] Nilsback M,and Zisserman A, "A Visual Vocabulary for Flower Classification," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, New York, NY, vol. 2, pp. 1447-1454, 2006. Crossref,
[15] Zou J, and Nagy G, "Evaluation of Model-Based Interactive Flower Recognition," Proceedings - International Conference on Pattern Recognition, Cambridge, UK, vol. 2, pp. 311-314, 2004. Crossref,
[16] Meng Yang, Lei Zhang, Xiangchu Feng, and David Zhang, “Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification,” International Journal of Computer Vision, vol. 109, pp. 209-232, 2014. Crossref,
[17] M.E. Nilsback and A. Zisserman, "A Visual Vocabulary for Flower Classification," IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 1447 – 1454, 2006. Crossref,
[18] Guru D. S, Sharath Y. H, and Manjunath S, "Texture Features and KNN in Classification of Flower Images," International Journal of Computer Applications Special Issue on RTIPPR, no. 1, pp. 21–29, 2010.
[19] Riddhi H. Shaparia, Patel and Zankhana H. Shah, "Flower Classification using Texture and Color Features," International Conference on Research and Innovations in Science, Engineering & Technology, vol. 2, pp. 113-118, 2017. Crossref,
[20] Huthaifa Almogdady, Dr. Saher Manaseer, and Dr.Hazem Hiary, "A Flower Recognition System Based on Image Processing and Neural Networks," International Journal of Scientific and Technology Research, vol. 7, no. 11, pp. 166-173, 2018.
[21] Sarker I.H, "Deep Learning: A Comprehensive Overview on Techniques, Taxonomy, Applications and Research Directions," SN Computer Science, vol. 2, pp. 420, 2021. Crossref,
[22] Fei Hu, Fuguang Yao, and Changjiu Pu, "Learning Salient Features for Flower Classification Using Convolutional Neural Network," 2020 IEEE International Conference on Artificial Intelligence and Information Systems (ICAIIS), pp. 476-479,2020. Crossref,
[23] Mesut Tog˘açar a, Burhan Ergen, and Zafer Cömert, "Classification of Flower Species by using Features Extracted from the Intersection of Feature Selection Methods in Convolutional Neural Network Models," Measurement, vol. 158, 2020. Crossref,
[24] Farhana Sultana, Abu Sufian, and Paramartha Dutta, "Advancements in Image Classification using Convolutional Neural Network," Fourth IEEE International Conference on Research in Computational Intelligence and Communication Networks, pp. 122-129, 2018. Crossref,
[25] Giraddi, S. Seeri, P. S. Hiremath and J. G.N, "Flower Classification using Deep Learning Models," International Conference on Smart Technologies in Computing, Electrical and Electronics, pp. 130-133, 2020. Crossref,
[26] I. Gogul and V. S. Kumar, "Flower Species Recognition System using Convolution Neural Networks and Transfer Learning," IEEE Fourth International Conference on Signal Processing, Communication and Networking (ICSCN), pp. 1-6, 2017. Crossref,
[27] Sushma L, and K.P. Lakshmi, "An Analysis of Convolution Neural Network for Image Classification using Different Models," International Journal of Engineering Research & Technology (IJERT), vol. 9, no. 10, 2020. Crossref,
[28] G. Pass, R. Zabih, and J. Miller, "Comparing Images Using Color Coherence Vector," Proceedings of the Fourth ACM International Conference on Multimedia, pp. 65-73, 1997. Crossref,
[29] Ojala T, Pietikäinen M, and Harwood D, "A Comparative Study of Texture Measures with Classification Based on Featured Distributions," Pattern Recognition Journal, vol. 29, pp. 51-59, 1996. Crossref,
[30] [Online]. Available:
[31] M. Rajeshwari, and K. Rathika, "Palm Print Recognition Using Texture and Shape Features," SSRG International Journal of Computer Science and Engineering, vol. 9, no. 2, pp. 1-5, 2022. Crossref,
[32] Yan Yangyang, and Fu Xiang, "A Flower Image Classification Algorithm Based on Saliency Map and PCANet," Journal of Communication and Computer, vol. 15, pp. 1, 2019. Crossref,
[33] Prashengit Dhar, "A New Flower Classification System Using LBP and SURF Features," International Journal of Image, Graphics and Signal Processing, vol. 11, no. 5, pp. 13-20, 2019. Crossref,
[34] Rongxin Lv, Zhongzhi Li, Jiankai Zuo, and Jing Liu, "Flower Classification and Recognition Based on Significance Test and Transfer Learning," 2021 IEEE International Conference on Consumer Electronics and Computer Engineering, pp. 649-652, 2021. Crossref,
[35] M.V.D. Prasad , B. Jwala Lakshmamma, A. Hari Chandana, K. Komali, M.V.N. Manoja,P. Rajesh Kumar, Ch. Raghava Prasad, Syed Inthiyaz, P. Sasi Kiran, "An Efficient Classification of Flower Images with Convolutional Neural Networks," International Journal of Engineering & Technology, vol. 7, no. 1.1, pp. 384-391, 2018. Crossref,
[36] Chen, Liu, and Sun, "Flowers Classification via Deep Learning Models." [Online]. Available:
[37] Gadkari S, Mathias J, and Pansare A, "Analysis of Pre-Trained Convolutional Neural Networks to Build a Flower Classification System," International Journal for Research in Applied Science and Engineering Technology, vol. 7, no. 11, pp. 489-495, 2019. Crossref,
[38] Ferhat Bozkurt, "A Study on CNN Based Transfer Learning for Recognition of Flower Species," European Journal of Science and Technology, Special Issue 32, pp. 883-890, 2021. Crossref,