External Defects and Soil Deposits Identification on Potato Tubers using 2CCD Camera and Principal Component Images

Dimas Firmanda Al Riza, Tetsuhito Suzuki, Yuichi Ogawa, Naoshi Kondo

Abstract


Abstract

Precise recognition of potato external defects and the ability to identify defects and non-defect areas are in demand. Common scab represents a significant issue that requires detection, yet identifying the extent of common scab infection remains challenging when using a standard RGB camera. In this research, a 2CCD camera system that could obtain a set of RGB and near-infrared images, which could enhance defect detection, has been used. Image segmentation strategies based on a single principal component image and the principal component pseudo-colored image have been proposed to identify external potato defects while excluding soil deposits on the potato surface, often recognized as defects by the normal color machine vision system. Performance metrics calculation results show relatively good results, with segmentation true accuracy around 64% for both methods. Principal component pseudo-colored images were able to discriminate defects area and soil deposits in a single image. The methods presented in this paper could be used as the basis to develop further classification and grading algorithms.

Keywords: image processing, multispectral, PCA, surface defects

 

Abstrak

Pengenalan yang tepat terhadap cacat eksternal kentang dan kemampuan untuk mengidentifikasi area cacat dan non-cacat sangat dibutuhkan. Keropeng yang umum merupakan masalah signifikan yang memerlukan deteksi, namun mengidentifikasi tingkat infeksi keropeng yang umum tetap menjadi tantangan saat menggunakan kamera RGB standar. Penelitian ini menggunakan sistem kamera 2CCD yang dapat memperoleh serangkaian gambar RGB dan inframerah dekat yang dapat meningkatkan deteksi cacat. Strategi segmentasi gambar berdasarkan gambar komponen utama tunggal dan gambar berwarna semu komponen utama diusulkan untuk mengidentifikasi cacat eksternal kentang dengan mengecualikan endapan tanah pada permukaan kentang yang sering dikenali sebagai cacat oleh sistem penglihatan mesin warna normal. Hasil penghitungan metrik kinerja menunjukkan hasil yang relatif baik, dengan akurasi segmentasi sebenarnya sekitar 64% untuk kedua metode. Komponen utama gambar berwarna semu mampu membedakan area cacat dan endapan tanah dalam satu gambar. Metode yang disajikan dalam penelitian ini dapat digunakan sebagai dasar untuk mengembangkan algoritma klasifikasi dan penilaian lebih lanjut.

Kata Kunci: cacat permukaan, multispektral, PCA, pengolahan citra

 


Keywords


image processing; multispectral; PCA; surface defects; cacat permukaan; multispektral; PCA; pengolahan citra

Full Text:

PDF

References


Al Riza, D. F. (2019). Potato Surface Defect Detection Using Machine Vision Systems Based on Spectral Reflection and Fluorescence Characteristics in the UV-NIR Region [Kyoto University]. https://doi.org/10.14989/doctor.k22075

Al Riza, D. F., Suzuki, T., Ogawa, Y., & Kondo, N. (2017). Diffuse reflectance characteristic of potato surface for external defects discrimination. Postharvest Biology and Technology, 133, 12–19. https://doi.org/10.1016/j.postharvbio.2017.07.006

Al Riza, D. F., Widodo, S., Yamamoto, K., Ninomiya, K., Suzuki, T., Ogawa, Y., & Kondo, N. (2022). External defects and severity level evaluation of potato using single and multispectral imaging in near infrared region. Information Processing in Agriculture. https://doi.org/10.1016/j.inpa.2022.09.001

López-Maestresalas, A., Lopez-Molina, C., Oliva-Lobo, G. A., Jarén, C., Ruiz de Galarreta, J. I., Peraza-Alemán, C. M., & Arazuri, S. (2022). Evaluation of near-infrared hyperspectral imaging for the assessment of potato processing aptitude. Frontiers in Nutrition, 9, 999877. https://doi.org/10.3389/fnut.2022.999877

Moallem, P., Razmjooy, N., & Ashourian, M. (2013). Computer vision -based potato defect detection using neural networks and support vector machine. International Journal of Robotics and Automation, 28(2), 137–145. https://doi.org/10.2316/Journal.206.2013.2.206-3746

Momin, A., Kondo, N., Al Riza, D. F., Ogawa, Y., & Obenland, D. (2023). A methodological review of fluorescence imaging for quality assessment of agricultural products. Agriculture, 13(7), 1433. https://doi.org/10.3390/agriculture13071433

Pandey, N., Kumar, S., & Pandey, R. (2019). Grading and Defect Detection in Potatoes Using Deep Learning. In Communication, Networks and Computing (pp. 329–339). https://doi.org/10.1007/978-981-13-2372-0_29

Su, W.-H., & Sun, D.-W. (2019). Advanced Analysis of Roots and Tubers by Hyperspectral Techniques. In Advances in Food and Nutrition Research (Vol. 87, pp. 255–303). Academic Press. https://doi.org/10.1016/bs.afnr.2018.07.003

Su, W.-H., & Xue, H. (2021). Imaging spectroscopy and machine learning for intelligent determination of potato and sweet potato quality. Foods, 10(9), 2146. https://doi.org/10.3390/foods10092146

Sun, D.-W. (2016). Computer Vision Technology for Food Quality Evaluation. Elsevier. https://doi.org/10.1016/C2014-0-01718-2

Valindria, V. V., Lavdas, I., Bai, W., Kamnitsas, K., Aboagye, E. O., Rockall, A. G., Rueckert, D., & Glocker, B. (2017). Reverse classification accuracy: Predicting segmentation performance in the absence of ground truth. IEEE Transactions on Medical Imaging, 36(8), 1597–1606. https://doi.org/10.1109/TMI.2017.2665165

Wang, C., Huang, W., Zhang, B., Yang, J., Qian, M., Fan, S., & Chen, L. (2016). Design and Implementation of an Automatic Grading System of Diced Potatoes Based on Machine Vision (pp. 202–216). https://doi.org/10.1007/978-3-319-48354-2_22




https://doi.org/10.21776/ub.industria.2023.012.02.4

Refbacks

  • There are currently no refbacks.