Implementation of K-Nearest Neighbours for Automotive  Body Surface Defect Detection

Ninuk Wiliani; Nabeel Fathurrahman; Herry  Wahyono

doi:10.47794/jesica.v2i2.30

Ninuk Wiliani Universitas Pancasila
Nabeel Fathurrahman Universitas Krisnadwipayana
Herry Wahyono Universitas Krisnadwipayana

DOI: https://doi.org/10.47794/jesica.v2i2.30

Keywords: Body repair, gray level co-occurrence matrix (GLCM), k-nearest neighbours (KNN)

Abstract

A body repair shop company that handles surface damage to vehicles is very necessary because the exterior appearance of the vehicle plays an important role in creating a good and attractive impression to others. Therefore, body repair companies must be able to adapt and keep up with the times. By combining advanced technology solutions, such as image processing, companies can streamline the identification phase, reduce human error, and optimize the allocation of repair resources. The problem discussed in this study is how to classify the surface of the vehicle body so that the classification model built can increase the accuracy in classifying the surface of the vehicle body. The steps taken in this study are to collect images of the surface of the vehicle body, and then the image data goes through a preprocessing process using median filtering to remove noise and segmentation techniques to improve image results. After preprocessing, the next step is to extract features based on texture using the Gray Level Co-occurrence Matrix (GLCM) and Statistical methods. Next, the images will be classified using the K-Nearest Neighbors (KNN) method, and the accuracy obtained is 56.80% for k = 3. After that, the classification model will be evaluated using the Area Under the Curve (AUC), and the AUC value obtained is 68.75%. With this approach, body repair workshop companies can improve the efficiency and accuracy in classifying vehicle body surfaces by utilizing image processing technology and techniques, allowing for better resource allocation and more reliable repair results

Downloads

Download data is not yet available.

References

M. H. Prova and Y. Liu, “Understanding cross-functional collaboration in quality work: A case study of hood production at Volvo Cars Body Components,” to be published, 2025.

S. Bakheet and A. Al-Hamadi, “Automatic detection of COVID-19 using pruned GLCM-based texture features and LDCRF classification,” Comput. Biol. Med., vol. 137, p. 104781, Oct. 2021.

S. Barburiceanu, R. Terebes, and S. Meza, “3D texture feature extraction and classification using GLCM and LBP-based descriptors,” Appl. Sci., vol. 11, no. 5, p. 2332, 2021.

M. K. Ghalati et al., “Texture analysis and its applications in biomedical imaging: A survey,” IEEE Rev. Biomed. Eng., vol. 15, pp. 222–246, 2021.

S. S. Priscila, S. S. Rajest, R. Regin, and T. Shynu, “Classification of satellite photographs utilizing the K-nearest neighbor algorithm,” Cent. Asian J. Math. Theory Comput. Sci., vol. 4, no. 6, pp. 53–71, 2023.

P. Cunningham and S. J. Delany, “K-nearest neighbour classifiers—A tutorial,” ACM Comput. Surv., vol. 54, no. 6, pp. 1–25, 2021.

L. Le, Y. Xie, and V. V. Raghavan, “KNN loss and deep KNN,” Fundam. Inform., vol. 182, no. 2, pp. 95–110, 2021.

M. Auleria, A. I. Arrahmah, and D. E. Saputra, “A review on k-nearest neighbour based classification for object recognition,” in Proc. 2021 Int. Conf. Data Sci. Appl. (ICoDSA), Bandung, Indonesia, 2021, pp. 1–6.

H. Singh, V. Sharma, and D. Singh, “Comparative analysis of proficiencies of various textures and geometric features in breast mass classification using k-nearest neighbor,” Vis. Comput. Ind. Biomed. Art, vol. 5, no. 1, p. 3, 2022.

S. Walters, “Area under the curve (AUC),” in Encyclopedia of Quality of Life and Well-Being Research. Cham, Switzerland: Springer, 2024, pp. 252–254.

S. C. Leong, Y. M. Tang, C. H. Lai, and C. K. M. Lee, “Facial expression and body gesture emotion recognition: A systematic review on the use of visual data in affective computing,” Comput. Sci. Rev., vol. 48, p. 100545, 2023.

M. Merino et al., “Body perceptions and psychological well-being: A review of the impact of social media and physical measurements on self-esteem and mental health with a focus on body image satisfaction and its relationship with cultural and gender factors,” Healthcare, vol. 12, no. 12, p. 1396, 2024.

Y. Liu, T. Zhang, M. Liang, and E. Wang, “Segmentation of lung nodules in CT images using weighted average-based threshold and maximized variance,” AIP Adv., vol. 14, no. 9, p. 095031, 2024.

T. B. Sasongko, H. Haryoko, and A. Amrullah, “Analisis efek augmentasi dataset dan fine tune pada algoritma pre-trained convolutional neural network (CNN),” J. Teknol. Inf. Ilmu Komput. (JTIIK), vol. 10, no. 4, pp. 763–768, 2024.

N. Wiliani, T. Khawa, and S. Ramli, “Peningkatan kontras pada preprocessing gambar permukaan solar panel dengan histogram,” Innovation and Technology, vol. 2, no. 1, 2025.

N. Wiliani, T. Rahman, S. Ramli, and A. Sani, “Statistical characteristics for identification defect of solar panel with Naive Bayes,” in Proc. 2nd Int. Conf. Electr., Telecommun. Comput. Eng. (ELTICOM), Medan, Indonesia, 2019, pp. 2–8, doi: 10.4108/eai.27-4-2019.2286885.

O. Rainio, J. Teuho, and R. Klén, “Evaluation metrics and statistical tests for machine learning,” Sci. Rep., vol. 14, no. 1, p. 6086, 2024.