International Journal of Computer and Information Technology

Open Access Open Access  Restricted Access Subscription Access

Feature Extraction using Histogram of Oriented Gradients for Image Classification in Maize Leaf Diseases


Affiliations
1 School of Computing and Information Technology Murang’a University of Technology Murang’a, Kenya
 

The paper presents feature extraction methods and classification algorithms used to classify maize leaf disease images. From maize disease images, features are extracted and passed to the machine learning classification algorithm to identify the possible disease based on the features detected using the feature extraction method. The maize disease images used include images of common rust, leaf spot, and northern leaf blight and healthy images. An evaluation was done for the feature extraction method to see which feature extraction method performs best with image classification algorithms. Based on the evaluation, the outcomes revealed Histogram of Oriented Gradients performed best with classifiers compared to KAZE and Oriented FAST and rotated BRIEF. The random forest classifier emerged the best in terms of image classification, based on four performance metrics which are accuracy, precision, recall, and F1-score. The experimental outcome indicated that the random forest had 0.74 accuracy, 0.77 precision, 0.77 recall, and 0.75 F1-score.

Keywords

Feature extraction, ORB, HOG, KAZE, Image classification, machine learning, and classifier.
User
Notifications
Font Size

  • Amato, G., & Falchi, F. (2017, September). kNN based image classification relying on local feature similarity. In Proceedings of the Third International Conference on SImilarity Search and APplications (pp. 101-108).

  • Bosch, A., Zisserman, A., & Munoz, X. (2018, October). Image classification using random forests and ferns. In 2017 IEEE 11th international conference on computer vision (pp. 1-8). Ieee.

  • Chen, P. Y., Huang, C. C., Lien, C. Y., & Tsai, Y. H. (2013). An efficient hardware implementation of HOG feature extraction for human detection. IEEE Transactions on Intelligent Transportation Systems, 15(2), 656-662.

  • Chen, Y. S., Chien, J. C., & Lee, J. D. (2016, September). KAZE-BOF-based large vehicles detection at night. In 2016 International Conference On Communication Problem-Solving (ICCP) (pp. 1-2). IEEE.

  • Foody, G. M., & Mathur, A. (2016). The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM. Remote Sensing of Environment, 103(2), 179-189.

  • Gan, G., & Cheng, J. (2018, December). Pedestrian detection based on HOG-LBP feature. In 2014 Seventh International Conference on Computational Intelligence and Security (pp. 1184-1187). IEEE.

  • Geismann, P., & Schneider, G. (2018, June). A two-staged approach to vision-based pedestrian recognition using Haar and HOG features. In 2011 IEEE Intelligent Vehicles Symposium (pp. 554-559). IEEE.

  • Goh, K. S., Chang, E., & Cheng, K. T. (2011, October). SVM binary classifier ensembles for image classification. In Proceedings of the tenth international conference on Information and knowledge management (pp. 395-402)

  • KIM¹, J. I. N. H. O., Kim, B. S., & Savarese, S. (2012). Comparing image classification methods: K-nearest-neighbor and support-vector-machines. In Proceedings of the 6th WSEAS international conference on Computer Engineering and Applications, and Proceedings of the 2012 American conference on Applied Mathematics (Vol. 1001, pp. 48109-2122).

  • Kobayashi, T. (2015). BFO meets HOG: feature extraction based on histograms of oriented pdf gradients for image classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (pp. 747-754).

  • K Song, Z liu, et al. A Research of maize disease image recognition of Corn Based on BP Networks. Measuring Technology and Mechatronics Automation China 2011: 246-249.

  • Li, W., Qian, Y., Loomes, M., & Gao, X. (2015, March). The application of KAZE features to the classification echocardiogram videos. In International Workshop on Multimodal Retrieval in the Medical Domain (pp. 61-72). Springer, Cham.

  • Li, Y., & Cheng, B. (2019, August). An improved k-nearest neighbor algorithm and its application to high resolution remote sensing image classification. In 2009 17th International Conference on Geoinformatics (pp. 1-4). Ieee.

  • Millard, K., & Richardson, M. (2015). On the importance of training data sample selection in random forest image classification: A case study in peatland ecosystem mapping. Remote sensing, 7(7), 8489-8515.

  • PD Jagadeesh, Y Rajesh, et al. Classification of Fungal Disease Symptoms affected on Cereals using Color Texture Features. International Journal of Signal Processing, Image Processing and Pattern Recognition 2013; 6: 321-330.

  • P Jagadeesh, R Yakkundimath, et al. SVM and ANN Based Classification of Plant Diseases Using Feature Reduction Technique. International Journal of Interactive Multimedia and Artificial Intelligence 2016; 3: 6-14.

  • Ramteke, R. J., & Monali, Y. K. (2018). Automatic medical image classification and abnormality detection using k-nearest neighbour. International Journal of Advanced Computer Research, 2(4), 190-196.

  • Sanchez-Morillo, D., González, J., García-Rojo, M., & Ortega, J. (2018, April). Classification of breast cancer histopathological images using KAZE features. In International Conference on Bioinformatics and Biomedical Engineering (pp. 276-286). Springer, Cham.

  • Spyrou, E., Le Borgne, H., Mailis, T., Cooke, E., Avrithis, Y., & O’Connor, N. (2015, September). Fusing MPEG-7 visual descriptors for image classification. In International Conference on Artificial Neural Networks (pp. 847-852). Springer, Berlin, Heidelberg.

  • Umbaugh, S. E., Wei, Y. S., & Zuke, M. (2017). Feature extraction in image analysis. A program for facilitating data reduction in medical image classification. IEEE engineering in medicine and biology magazine, 16(4), 62-73.

  • Xia, J., Ghamisi, P., Yokoya, N., & Iwasaki, A. (2018). Random forest ensembles and extended multiextinction profiles for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 56(1), 202-216.

  • Xu, B., Ye, Y., & Nie, L. (2012, June). An improved random forest classifier for image classification. In 2012 IEEE International Conference on Information and Automation (pp. 795-800). IEEE.

  • Z Zhiyong, H Xiaoyang, et al. Image recognition of maize leaf disease based on GA-SVM. Chemical Engineering Transactions 2015; 46:199-204.


Abstract Views: 221

PDF Views: 111




  • Feature Extraction using Histogram of Oriented Gradients for Image Classification in Maize Leaf Diseases

Abstract Views: 221  |  PDF Views: 111

Authors

Vincent Mbandu Ochango
School of Computing and Information Technology Murang’a University of Technology Murang’a, Kenya
John Gichuki Ndia
School of Computing and Information Technology Murang’a University of Technology Murang’a, Kenya
Geoffrey Mariga Wambugu
School of Computing and Information Technology Murang’a University of Technology Murang’a, Kenya

Abstract


The paper presents feature extraction methods and classification algorithms used to classify maize leaf disease images. From maize disease images, features are extracted and passed to the machine learning classification algorithm to identify the possible disease based on the features detected using the feature extraction method. The maize disease images used include images of common rust, leaf spot, and northern leaf blight and healthy images. An evaluation was done for the feature extraction method to see which feature extraction method performs best with image classification algorithms. Based on the evaluation, the outcomes revealed Histogram of Oriented Gradients performed best with classifiers compared to KAZE and Oriented FAST and rotated BRIEF. The random forest classifier emerged the best in terms of image classification, based on four performance metrics which are accuracy, precision, recall, and F1-score. The experimental outcome indicated that the random forest had 0.74 accuracy, 0.77 precision, 0.77 recall, and 0.75 F1-score.

Keywords


Feature extraction, ORB, HOG, KAZE, Image classification, machine learning, and classifier.

References