Optimizing Color Detection in Digital Images: A Machine Learning Approach Using K-Nearest Neighbor

Most. Mazriha Akter Mohua¹

Section:Research Paper, Product Type: Journal-Paper
Vol.12 , Issue.6 , pp.56-60, Dec-2024

Online published on Dec 31, 2024

Copyright © Most. Mazriha Akter Mohua . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
Real-world problem-solving using machine learning algorithms, whether they are supervised or unsupervised, has become a significant issue. In this case, the system is trained with provided data to make predictions based on that data or previous experience. To recognize any object, color detection is necessary and machine learning has been proven benificial in this regard. However, color detection means identifying color name. This study utilizes the supervised ML algorithm K-Nearest Neighbor to optimize color detection in digital (RGB) images. This algorithm is used to separate different colors in the RGB images. This algorithm is beneficial for classification and regression (nonlinear) and provides advantages to some extent over other algorithms. A dataset containing 818 color names with their respective r, g, b values along with the intensity of each color has been trained with the KNN algorithm. By using the feature similarity of the nearest data points, it predicts the new data points` values. Initially, it calculates the distance between new and each training point, then selects the nearest points upon the value of K. The experimentation showed that a notable accuracy of 93.089% has been achieved with the optimal number of neighbors set at K=5. As computers can only track three basic colors (RGB), the OpenCV library is used to help detecting colors based on this fundamental color combination at different intensities.

Key-Words / Index Term :
Color detection, Machine learning, KNN, Digital image, RGB, OpenCV

References :
[1] R. Bayraktar, B. A. Akgul, and K. Bayram, “Colour recognition using colour histogram feature extraction and k-nearest neighbour classifier,” New Trends and Issues Proceedings on Advances in Pure and Applied Sciences, Vol.12, pp.08–14, 2020.
[2] N. Fatima, S. B. Reddy, K. S. Rani, S. Psalms, P. Nithin, S. Kudakala, P. Vaishnavi, G. R. NV, and G. Nijhawan, “Primary Colour Detection in An Image,” In 2024 MATEC Web of Conferences, EDP Sciences, Vol.392, 2024.
[3] P. Raguraman, A. Meghana, Y. Navya, S. Karishma, and S. Iswarya, “Color detection of rgb images using python and opencv,” International Journal of Scientific Research in Computer Science, Engineering and Information Technology, Vol.7, Issue.1, pp.109–112, 2021.
[4] R. Arali, V. Halawal, and A. Naik, “Colour detection from image,” International Journal of Advances in Engineering and Management (IJAEM), Vol.3, Issue.7, pp.2164–2171, 2021.
[5] K. Bhogal, N. Singla, and M. Kaur, “Color image segmentation using k-means clustering algorithm,” International Journal on Emerging Technologies, Vol.1, Issue.2, pp.18–20, 2010.
[6] J. B. Awotunde, S. Misra, D. Obagwu, and H. Florez, “Multiple colour detection of rgb images using machine learning algorithm,” In 2022 International Conference on Applied Informatics, Springer, pp.60–74, 2022.
[7] N. Kayhan and S. Fekri-Ershad, “Content based image retrieval based on weighted fusion of texture and color features derived from modified local binary patterns and local neighborhood difference patterns,” Multimedia Tools and Applications, Vol.80, Issue.21, pp.32763–32790, 2021.
[8] V. Jumb, M. Sohani, and A. Shrivas, “Color image segmentation using k-means clustering and otsu’s adaptive thresholding,” International Journal of Innovative Technology and Exploring Engineering (IJITEE), Vol.3, Issue.9, pp.72–76, 2014.
[9] N. Gulati and P. Panwar, “Genetic algorithms for image segmentation using active contours,” Journal of Global Research in Computer Science, Vol.4, Issue.1, pp.34–37, 2013.
[10] K. Pooja, R. Shreya, B. Yashika, M. R. BN et al., “Color recognition using k-nearest neighbors machine learning classification algorithm trained with color histogram features,” Int. Res. J. Eng. Technol.(IRJET), Vol.8, pp.1935–1936, 2021.
[11] S. R. Maniyath, R. Hebbar, K. Akshatha, L. Architha, and S. R. Subramoniam, “Soil color detection using knn classifier,” In 2018 International Conference on Design Innovations for 3Cs Compute Communicate Control (ICDI3C), IEEE, pp.52–55, 2018.
[12] P. S. Duth and M. M. Deepa, “Color detection in rgb-modeled images using matlab,” International Journal of Engineering & Technology, Vol.7, Issue.2.31, pp.29–33, 2018.
[13] H. J. Farooqi, A. A. Chauhan, and A. W. Siddiqui, “Naive Bayes Approached in Color Detection Using Pandas and OpenCV,” International Journal of Scientific & Engineering Research, Vol.11, Issue.12, pp.288-291, 2020.
[14] D. C. Gomathy, M. C. CHAITANYA, M. Anvitha, and M. C. JAHNAVI, “Color detection using pandas and opencv,” International Journal of Scientific Research in Engineering and Management (IJSREM), Vol.5, 2021.
[15] M. R. Mahajan, “Color classification using machine learning,” Ph.D. dissertation, Thesis, California State University, Sacramento, 2020.