Breast Cancer Detection Using K-Nearest Neighbors with 
Gray-Level Co-Occurrence Matrix and Histogram of 
Oriented Gradients Features

Suchismita Jena; Manas Ranjan Senapati

doi:https://doi.org/10.14445/22312803/IJCTT-V73I12P102

Research Article | Open Access | Download PDF

Volume 73 | Issue 12 | Year 2025 | Article Id. IJCTT-V73I12P102 | DOI : https://doi.org/10.14445/22312803/IJCTT-V73I12P102

Breast Cancer Detection Using K-Nearest Neighbors with Gray-Level Co-Occurrence Matrix and Histogram of Oriented Gradients Features

Suchismita Jena, Manas Ranjan Senapati

Received	Revised	Accepted	Published
17 Oct 2025	21 Nov 2025	04 Dec 2025	15 Dec 2025

Citation :

Suchismita Jena, Manas Ranjan Senapati, "Breast Cancer Detection Using K-Nearest Neighbors with Gray-Level Co-Occurrence Matrix and Histogram of Oriented Gradients Features," International Journal of Computer Trends and Technology (IJCTT), vol. 73, no. 12, pp. 5-12, 2025. Crossref, https://doi.org/10.14445/22312803/IJCTT-V73I12P102

Abstract

Improving treatment decisions and getting clinical outcomes is given much importance in the early detection of breast cancer from microscopic images. Textural descriptors obtained from the “Gray-Level Co-occurrence Matrix (GLCM)”, combined with structural representations derived from the “Histogram of Oriented Gradients (HOG)”, are presented in this work. To maintain consistent preprocessing, all microscopic images were resized, converted into grayscale, and normalized. Extraction of “Gray-Level Co-occurrence Matrix” features such as “contrast, correlation, energy, and homogeneity” was done. And “Histogram of Oriented Gradient” captured the edge orientation patterns. To train a Euclidean-distance “K-Nearest Neighbors (KNN)” classifier with a 70/30 train-test split, these feature sets were concatenated and used. An “accuracy” of 0.9167, “precision” of 0.8889, “sensitivity” of 0.9412, “specificity” of 0.8947, and an “F1-score” of 0.914 were produced by the GLCM+KNN model during evaluation. An “accuracy” of 0.8333, “precision” of 0.9231, “sensitivity” of 0.7059, “specificity” of 0.9474, and an “F1-score” of 0.8000 were achieved by the HOG+KNN model. These observations suggested that “Gray-Level Co-occurrence Matrix” features contributed more significantly to positive-class identification, whereas Histogram of Oriented Gradients features strengthened the discrimination of negative cases. Computationally efficient, interpretable, and suitable for diagnostic settings with limited resources are considered as some of the main characteristics of the proposed hybrid model.

Keywords

Breast cancer, Euclidean distance, “Gray-Level Co-occurrence Matrix (GLCM)”, “Histogram of Oriented Gradients (HOG)”, “K-Nearest Neighbors (KNN)”.

References

[1] Hyuna Sung et al., “Global Cancer Statistics 2020: GLOBOCAN Estimates of Incidence and Mortality,” CA: A Cancer Journal for Clinicians, vol. 71, no. 3, pp. 209-249, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[2] S. Karthik, R. Srinivasa Perumal, and P. V. S. S. R. Chandra Mouli, Breast Cancer Classification Using Deep Neural Networks,” Knowledge Computing and Its Applications, pp. 227-241, 2018.
[CrossRef] [Google Scholar] [Publisher Link]

[3] Li Shen et al., “Deep Learning to Improve Breast Cancer Detection on Screening Mammography,” Scientific Reports, pp. 1-12, 2019.
[CrossRef] [Google Scholar] [Publisher Link]

[4] Robert M. Haralick, K. Shanmugam, and Its'Hak Dinstein, “Textural Features for Image Classification,” IEEE Transactions on Systems, Man, and Cybernetics, vol. 3, no. 6, pp. 610-621, 1973.
[CrossRef] [Google Scholar] [Publisher Link]

[5] N. Dalal, and B. Triggs, “Histograms of Oriented Gradients for Human Detection,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition, San Diego, CA, USA, vol. 1, pp. 886-893, 2005.
[CrossRef] [Google Scholar] [Publisher Link]

[6] Faeze Kiani, “Texture Features in Medical Image Analysis: A Survey,” arXiv preprint, pp. 1-7, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[7] Yan Hao et al., “Breast Cancer Histopathological Images Recognition Based on Low Dimensional Three-Channel Features,” Frontiers in Oncology, vol. 11, pp. 1-15, 2021.
[CrossRef] [Google Scholar] [Publisher Link]

[8] Amjad Rehman Khan et al., “Identification of Anomalies in Mammograms through Internet of Medical Things Diagnosis System,” Computational Intelligence and Neuroscience, vol. 2022, no. 1, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[9] Yan Hao et al., “Breast Cancer Histopathological Images Classification Based on Deep Semantic Features and Gray Level Co-Occurrence Matrix (GLCM) Features,” PLOS ONE, vol. 17, no. 5, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[10] Shahadat Uddin et al., “Comparative Performance Analysis of K-Nearest Neighbour (KNN) Algorithm and Its Different Variants for Disease Prediction,” Scientific Reports, pp. 1-11, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[11] Breast Histopathology Images. [Online].
Available: https://www.kaggle.com/datasets/paultimothymooney/breast-histopathology-images

[12] Harmandeep Singh, Vipul Sharma, and Damanpreet Singh, “Comparative Analysis of Proficiencies of Various Textures and Geometric Features in Breast Mass Classification Using K-Nearest Neighbour,” Visual Computing for Industry, Biomedicine and Art, vol. 5, no. 3, pp. 1-19, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[13] Reem Jalloul, H.K. Chethan, and Ramez Alkhatib, “A Review of Machine Learning Techniques for the Classification and Detection of Breast Cancer from Medical Images,” Diagnostics, vol. 13, no. 14, pp. 1-24, 2023.
[CrossRef] [Google Scholar] [Publisher Link]

[14] Nada Mobark, Safwat Hamad, and S.Z. Rida, “CoroNet: Deep Neural Network-Based End-to-End Training for Breast Cancer Diagnosis,” Applied Sciences, vol. 12, no. 14, pp. 1-12, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[15] Madallah Alruwaili, and Walaa Gouda, “Automated Breast Cancer Detection Models Based on Transfer Learning,” Sensors, vol. 22, no. 3, pp. 1-16, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[16] Debendra Muduli, Ratnakar Dash, and Banshidhar Majhi, “Automated Diagnosis of Breast Cancer Using Multi-Modal Datasets: A Deep Convolutional Neural Network Based Approach,” Biomedical Signal Processing and Control, vol. 71, 2022.
[CrossRef] [Google Scholar] [Publisher Link]

[17] Chegini M. (Mohaddeseh Chegini) — “Uncertainty-Aware Deep Learning-Based CAD System for Breast Cancer Classification Using Ultrasound and Mammography Images,” Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, vol. 12, no. 1, pp. 1-17, 2023.
[CrossRef] [Google Scholar] [Publisher Link]