Leaf Identification Using SIFT Feature Extraction and SVM on PYNQZU

International Journal of VLSI & Signal Processing

© 2025 by SSRG - IJVSP Journal

Volume 12 Issue 2

Year of Publication : 2025

Authors : Mereddy Jahnavi, T. Satya Savithri

10.14445/23942584/IJVSP-V12I2P101

How to Cite?

Mereddy Jahnavi, T. Satya Savithri, "Leaf Identification Using SIFT Feature Extraction and SVM on PYNQZU," SSRG International Journal of VLSI & Signal Processing, vol. 12,  no. 2, pp. 1-5, 2025. Crossref, https://doi.org/10.14445/23942584/IJVSP-V12I2P101

Abstract:

This paper presents leaf identification utilizing an SVM classifier, based on features obtained through SIFT, VLAD, and PCA methodologies. The feature extraction process, referred to as the SVP technique, involves identifying key points using SIFT, converting these key points into a standardized feature vector with VLAD, and then reducing the dimensionality of this feature vector via PCA. A novel VLSI architecture for the SVM classifier is introduced in this paper and has been implemented on the PL portion of the PYQZU board, while the feature extraction methods are connected using the PS section of the board with a Python program. The suggested method has been evaluated using standard datasets of Apple and Cherry and custom datasets for Custard and Mango. The results obtained from the hardware implementation are comparable to those from the software, and the proposed approach yields effective outcomes even under acquisition disturbances, such as low lighting and rotation. The SVM classifier is employed for single-label classification and identification; however, there is a requirement for multilabel classification for images featuring multiple leaf types, which is addressed in this paper through the proposal of a Binary Relevance Strategy.

Keywords:

SIFT, VLAD and PCA methodologies, Leaf Identification, SVM classifier, Support Vector Machine.

References:

[1] David G. Lowe, “Distinctive Image Features from Scale-Invariant Keypoints,” International Journal of Computer Vision, vol. 60, no. 2, pp. 91-110, 2004.
[CrossRef] [Google Scholar] [Publisher Link]
[2] A. Ehsanirad, and S.K.Y.H, “Leaf Recognition for Plant Classification using GLCM and PCA Methods,” Oriental Journal of Computer Science & Technology, vol. 3, no. 1, pp. 31-36, 2010.
[Google Scholar]
[3] G.S. Sural, and S. Pramanik, “Segmentation and Histogram Generation using The HSV Color Space for Image Retrieval,” International Conference on Image Processing, Rochester, Rochester, NY, USA, 2002.
[CrossRef] [Google Scholar] [Publisher Link]
[4] Adil Salman et al., “Leaf Classification and Identification using Canny Edge Detector and SVM classifier,” 2017 International Conference on Inventive Systems and Control (ICISC), Coimbatore, India, pp. 1-4, 2017.
[CrossRef] [Google Scholar] [Publisher Link]
[5] Moulay Hafid Aabidi et al., “A New Approach of Leaf Disease Detection Using Bag of Visual Words,” Journal of Theoretical and Applied Information Technology, vol.101, no. 14, pp. 5645-5664, 2023.
[Google Scholar] [Publisher Link]
[6] Murad Qasaimeh, and Assim Sagahyroon, and Tamer Shanableh, “FPGA-Based Parallel Hardware Architecture for Real-Time Image Classification,” IEEE Transactions on Computational Imaging, vol. 1, no. 1, pp. 56-70, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[7] Qilong Li, and Xiaohong Wang, “Image Classification Based on SIFT and SVM,” IEEE/ACIS 17th International Conference on Computer and Information Science, Singapore, pp. 762-765, 2018.
[CrossRef] [Google Scholar] [Publisher Link]
[8] Di Fu, Bo Zhou, and Jinglu Hu, “Improving SVM based Multi-Label Classification by Using Label Relationship,” International Joint Conference on Neural Networks, Killarney, Ireland, pp. 1-6, 2015.
[CrossRef] [Google Scholar] [Publisher Link]
[9] Jesse Read et al., “Classifier Chains for Multi-Label Classification,” Machine Learning, vol. 85, pp. 333-359, 2011.
[CrossRef] [Google Scholar] [Publisher Link]
[10] Marta Ruiz-Llata, Guillermo Guarnizo, and Mar Yébenes-Calvino, “FPGA Implementation of a Support Vector Machine for Classification and Regression,” International Joint Conference on Neural Networks, Barcelona, Spain, pp. 1-5, 2010. [CrossRef] [Google Scholar] [Publisher Link]
[11] Shereen Afifi, Hamid Gholam Hosseini, and Roopak Sinha, “FPGA Implementations of SVM Classifiers: A Review,” SN Computer Science, vol. 1, 2020.
[CrossRef] [Google Scholar] [Publisher Link]
[12] C. Kyrkou and T. Theocharides, “A Parallel Hardware Architecture for Real-Time Object Detection with Support Vector Machines,” IEEE Transactions on Computers, vol. 61, no. 6, pp. 831-842, 2012.
[CrossRef] [Google Scholar] [Publisher Link]
[13] Davood Mahmoodi et al., “FPGA Simulation of Linear and Nonlinear Support Vector Machine,” Journal of Software Engineering and Applications, vol. 4, pp. 320-328, 2011.
[CrossRef] [Google Scholar] [Publisher Link]