Perbandingan Metode InceptionResNetV2 dengan KNN Berbasis PCA dan KNN Berbasis LDA untuk Klasifikasi Telur Pecah Berdasarkan Citra Kulit Telur

Perbandingan Metode InceptionResNetV2 dengan KNN Berbasis PCA dan KNN Berbasis LDA untuk Klasifikasi Telur Pecah Berdasarkan Citra Kulit Telur

• By Wiguna, Bima Aviandi;
• Tesis
• 14

Penelitian ini membahas perbandingan performa metode InceptionResNetV2 dengan metode K-Nearest Neighbors (KNN) berbasis Principal Component Analysis (PCA) dan Linear Discriminant Analysis (LDA) dalam klasifikasi telur pecah berdasarkan citra kulit telur. Klasifikasi ini berperan penting dalam industri pangan, khususnya untuk proses sortir dan pengendalian mutu produk. Metode identifikasi manual yang digunakan secara konvensional cenderung tidak konsisten dan kurang akurat, sehingga dibutuhkan pendekatan otomatis berbasis citra untuk meningkatkan efisiensi dan keandalan. Pada studi ini, citra telur diproses melalui teknik praproses citra, dilanjutkan dengan reduksi dimensi menggunakan PCA dan LDA, lalu diklasifikasikan menggunakan KNN. Hasil eksperimen dibandingkan dengan pendekatan transfer learning menggunakan arsitektur InceptionResNetV2 dari TensorFlow Hub. Evaluasi performa menunjukkan bahwa InceptionResNetV2 memberikan akurasi tertinggi dalam mendeteksi telur pecah, namun metode KNN berbasis LDA juga menunjukkan performa kompetitif dengan keunggulan dalam hal efisiensi dan kompleksitas model yang lebih ringan. Temuan ini berkontribusi pada pengembangan sistem klasifikasi citra berbasis kecerdasan buatan yang efisien dan akurat, serta memiliki potensi untuk diterapkan pada berbagai aplikasi pengendalian mutu berbasis citra lainnya.

• Katakunci Klasifikasi Telur Pecah, Citra Kulit Telur, PCA, LDA, K-Nearest Neighbors, InceptionResNetV2, Transfer Learning.
• URL http://
• Penerbit Teknika Journal of Information and CommunicationTechnology, Surabaya Jawa Timur

REFERENSI

 

1. H. Rachmawanto et al., “Eggs classification based on egg shell image using K-Nearest Neighbors classifier,” in Proc. 2020 Int. Seminar on Application for Technology of Information and Communication (iSemantic), 2020, pp. 244–249, doi: 10.1109/iSemantic50169.2020.9234198.
2. F. M. Alavi, "Analysis of productivity improvement in manufacturing systems through simulation and optimization," CIRP Annals, vol. 70, no. 1, pp. 57-60, 2021. doi: 10.1016/j.cirp.2021.07.003.
3. S. N. Zulkifli, A. K. Shahriman, and I. H. A. Othman, "Automated sorting of eggs using image processing techniques: A review," Computers and Electronics in Agriculture, vol. 180, p. 105927, 2021. doi: 10.1016/j.compag.2021.07.003.
4. K. Manogaran and R. S. K. Saifullah, "Image analysis techniques for identifying and classifying chicken eggs: A comprehensive review," Computer Methods and Programs in Biomedicine, vol. 229, p. 107207, 2023. doi: 10.1016/j.cmpb.2023.107207.
5. B. Shahriman et al., "Using image processing for egg classification: A comparative study," Journal of Visual Communication and Image Representation, vol. 72, p. 102850, 2020. doi: 10.1007/s11042-020-09126-6.
6. A. Garcia et al., "Application of image processing techniques for the quality evaluation of eggs," Journal of Food Engineering, vol. 285, p. 110109, 2020. doi: 10.1016/j.jfoodeng.2020.109407.
7. C. D. W. de Souza et al., "Machine learning techniques for the classification of eggs using image processing," Artificial Intelligence Review, vol. 54, no. 1, pp. 97-126, 2021. doi: 10.1007/s10462-021-09956-6.
8. M. Raheja et al., "Signal processing techniques for the classification of poultry eggs using image data," Signal Processing, vol. 179, p. 107824, 2020. doi: 10.1016/j.sigpro.2020.107824.
9. Alhussein, A. H. Al-Harbi, and M. K. Shahbaz, "Image classification techniques: A comprehensive survey," IEEE Access, vol. 8, pp. 95066-95089, 2020. doi: 10.1109/ACCESS.2020.2990205.
10. Benzaoui et al., "A hybrid model for egg classification using deep learning and image processing," Soft Computing, vol. 25, no. 10, pp. 6747-6758, 2021. doi: 10.1007/s00500-021-05164-y.
11. B. Shahriman et al., "Comparative analysis of egg classification using different image processing techniques," Journal of Visual Communication and Image Representation, vol. 72, p. 102850, 2020. doi: 10.1007/s11042-020-09126-6.
12. Mallareddy, “Digital Image definition and sampling process,” Digital Image Processing Course Materials, Mallareddy College of Engineering and Technology, 2021.
13. Cuff, “Introduction to image processing: Two-dimensional data processing,” Digital Image Processing, Princeton University, 2022.
14. Narain, “Sampling and quantization of digital images,” Digital Image Analysis Course, Indian Institute of Technology Delhi, 2023.
15. Z. Husin, A. M. M. Osman, and H. N. E. Sheikh, “Methods for enhancing digital images quality,” IEEE Access, vol. 11, pp. 18142-18155, 2023.
16. Kumar and B. Rathi, “Principal Component Analysis for feature extraction in machine learning applications,” IEEE Access, vol. 9, pp. 12445-12459, 2021.
17. Liu, X. Zhang, and Y. Zhao, “Dimensionality reduction using PCA for image processing,” Journal of Image Processing, vol. 30, no. 3, pp. 231-245, 2022.
18. Verma, A. Pandey, and S. Sharma, “An overview of PCA and its application in machine learning,” Journal of Computational and Applied Mathematics, vol. 415, pp. 1-10, 2023.
19. G. Jung and P. Y. Lee, “PCA-based feature extraction for machine learning in high-dimensional data,” IEEE Transactions on Neural Networks and Learning Systems, vol. 32, no. 8, pp. 3541-3552, 2020.
20. Chen, Y. Zhang, and H. Zhang, “Enhancing feature selection with PCA and LDA for image recognition tasks,” Journal of Image and Graphics, vol. 15, no. 2, pp. 50-59, 2023.
21. Smith and T. Li, “A study on the application of Linear Discriminant Analysis for image classification,” IEEE Access, vol. 10, pp. 100-110, 2022.
22. Kumar, A. Gupta, and S. Agarwal, “Comparing LDA and PCA for dimensionality reduction in image processing,” Proceedings of the International Conference on Artificial Intelligence, pp. 240-247, 2021.
23. Shankar, M. Ravi, and S. Kumar, “Using LDA for effective face recognition in low-light conditions,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 45, no. 4, pp. 234-245, 2020.
24. Zhou, Q. Wang, and F. Liu, “Evaluating the performance of LDA for machine learning tasks,” Pattern Recognition Letters, vol. 141, pp. 50-57, 2021.
25. Wang and C. Ma, “Improving discriminant analysis for high-dimensional data,” Journal of Data Science, vol. 19, no. 2, pp. 110-123, 2023.
26. Silva, "The effectiveness of PCA-LDA and PLS-DA combinations for vibrational spectrum classification," Journal of Spectroscopy, 2021.
27. Swain, "Application of PCA for chronic disease classification: A study on kidney disease," International Journal of Health Sciences, 2023.
28. Islam, "Combining PCA and recursive feature elimination for chronic kidney disease classification," Journal of Biomedical Informatics, 2023.
29. Venkatesan, "PCA-LDA and XGBoost for medical dataset classification," Journal of Medical Data Science, 2023.
30. Jerop and A. Segera, "PCA-LDA dimensionality reduction for heart and kidney disease prediction with kernel SVM," Computational Health Journal, 2021.
31. Almustafa, "Effectiveness of PCA and LDA in chronic kidney disease classification," Healthcare Data Analysis Journal, 2021.
32. Zhu, "PCA-LDA method for hyperspectral image classification in remote sensing," Remote Sensing Journal, 2022.
33. Zhang, "Dimension reduction with PCA and classification with LDA for infrared spectrum detection," Spectral Analysis and Imaging, 2023.
34. Ayu, "Plant leaf disease classification based on PCA-LDA," Agricultural Informatics Journal, 2022.
35. Ishaq, "Application of PCA-LDA in medical image classification for health condition identification," Journal of Medical Imaging and Data Analysis, 2023.
36. Huang, Y. Wang, dan Q. Liu, "Crack detection of unwashed eggs using YOLOv5 and ByteTrack from production line videos, " in Proc. 2023 Int. Conf. on Smart Agriculture Technologies, 2023.
37. Setiadi, A. S. Nugroho, dan T. Utami, "Static image-based classification of hatching eggs using SVM and morphological analysis, " J. Agric. Inform., vol. 12, no. 2, pp. 110–118, 2021.
38. Turkoglu dan B. Gokmen, "Defect detection in eggs using deep learning with CNN and BiLSTM architecture," Comput. Electron. Agric., vol. 188, p. 106333, 2021.
39. Alvarado, M. Cardenas, dan L. Rivera, "Real-time egg counting and sorting using conveyor camera system," J. Food Eng., vol. 305, p. 110651, 2022.
40. Zhou, Y. Zhang, dan X. Liu, "Graphite grade classification using improved Inception-ResNet-v2, " Minerals Engineering, vol. 198, p. 107051, 2023.
41. Nugroho, T. Supriyanto, dan M. Kurniawan, "Chest X-ray pneumonia detection using fine-tuned Inception-ResNet-v2, " Health Inf. Sci. Syst., vol. 11, no. 1, pp. 22–30, 2023.
42. Day, "Broken Eggs: CNN & VGG16," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/alexday11/broken-eggs-cnn-vgg16
43. Marconato, "Broken Eggs - Image Classification (85.18%)," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/raphaelmarconato/broken-eggs-image-classification-85-18
44. Ghareeb, "Eggs Classification with 89% Accuracy," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/mahmoudghareeb/eggs-classification-with-89-accuracy
45. Dutta, "ResNet-50 V2: Broken Eggs," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/gauravduttakiit/broken-eggs-resnet-50-v2
46. Orcun, "InceptionResNetV2 Broken Egg Prediction," Kaggle, 2023. [Online]. Available: https://www.kaggle.com/code/ardaorcun/inceptionresnetv2-broken-egg-prediction