International Journal of Advanced Research and Publications (2456-9992)

High Quality Publications & World Wide Indexing!

Arabica Coffee Bean Quality Identification Using Support Vector Machine-Based Digital Image Processing

Volume 6 - Issue 6, June 2023 Edition
[Download Full Paper]

Judy Ann T. Nasuli, Joben P. Lumbis, Edwin R. Arboleda
Arabica Coffee Bean, Convolutional Neural Networks, Image Processing, Originality Certification, Support Vector Machine,
Existing institutions already began performing actions regarding the originality certification of coffee bean varieties and their quality. The purpose of this research paper was to investigate how technology can assist in performing evaluations through image analysis. Specifically, the study focused on developing a system to classify the quality and size of Arabica coffee beans. The system utilized image processing to analyze morphological features of coffee bean images, including area and perimeter. By combining these features and using a support vector machine (SVM) classifier, the system achieved an accuracy rate of 95% in identifying coffee bean quality and size. These findings suggest that technology-based tools can effectively assist with object evaluation, particularly in the context of coffee bean classification.
[1]. C. A. Lujan, F. J. Mora, & J. R. Atoche, (2008). Comparative Analysis in the Implementation of Subtraction and Thresholding for Digital Image Processing (Cce), 465–469.

[2]. C. Banica,, S. V. Paturca,, S. D. Grigorescu,, & A. M Stefan, (2017). Data Acquisition and Image Processing System for Surface Inspection, 28–33.

[3]. D.D Burdescu, L. Stanescu, M. Brezovan, C.S. Spahiu & F. Slabu (n.d.). Algorithms for Image Processing in Graph-based Volumetric Segmentation.

[4]. D. Makowski A. Mielczarek P. Perek, G. Jab?o, Orlikowski, M., Napieralski, A., … Martin, V. (2014). High-Performance Image Acquisition and Processing System with MTCA . 4, 4–5.

[5]. D. Makowski, A. Mielczarek, P. Perek, G. Jab?o?ski, M. Orlikowski, B. Sakowicz, V. Martin, (2015). High-Performance Image Acquisition and Processing System with MTCA . 4, 62(3), 925–931.

[6]. D. Talukdar & R. Sridhar (1993). Adaptive Thresholding ASIC for Image Processing Application, 104–107.

[7]. D. R. Arellano-baez, E. N. Sanchez, F. A. Prietc-ortiz, Guadalajara, U., Luna, P. La, S. Manizales & N. Campus (n.d.). [ I ], 1280–1283. dqg 6hjphqwdwlrq ri 0dpprjudp ,pdjhv, 187–190. Click or tap here to enter text.

[8]. E. Faculty (2015). Digital Image Based Identification of Rice Variety Using Image Processing and Neural Network, 16(1), pp.182–190. https://doi.org/10.11591/telkomnika.v16i1.8686

[9]. E. R. Arboleda, A. C. Fajardo, and R. P. Medina, “An image processing technique for coffee black beans identification,” in 2018 IEEE International Conference on Innovative Research and Development, ICIRD 2018, Institute of Electrical and Electronics Engineers Inc., Jun. 2018, pp. 1–5. doi: 10.1109/ICIRD.2018.8376325.

[10]. G. O. F. Parikesit (2011). Coffee Bean Grade Determination Based on Image Parameter, 9(3), 547– 554.

[11]. F. Wang, D. Hu, & J.Fan (2017). Multi-Feature Fusion with SVM Classification for Crime Scene Investigation Image Retrieval, 0–5.

[12]. H.K. Tu, L. T. Thuong, H. Viet, U. Synh, & H. Khoa, (2017). Develop an algorithm for image forensics using feature comparison and sharpness estimation, 82–87.

[13]. J. Kuruvilla (n.d.). A Review on Image Processing and Image Segmentation.

[14]. K. Anuar, M. Said, & A. B. Jambek (2016). A Study on Image Processing Using Mathematical Morphological, 507–512.

[15]. M. Barstu, 2017). A Discriminative Dictionary Learning-AdaBoost- SVM Classification Method on Imbalanced Datasets.

[16]. M. Automation (2015). 2015 Seventh International Conference on Measuring Technology and Mechatronics Automation Introduction to digital image pre-processing and segmentation. https://doi.org/10.1109/ICMTMA.2015.148

[17]. M. Weingart & O. Vascan, (2013). Image Segmentation Processing - some techniques and experimental results, pp.0–5.

[18]. N. Taujuddin, R. Ibrahim& S. Sari (2016). Reconstruction of “ Phi ” in Thresholding Process for a Better Compressed Image Quality.

[19]. N. S. A. Ibrahim, N.F Soliman, N. F., Abdallah, M., & El- samie, F. E. A. (2016). $q $ojrulwkp iru 3uh surfhvvlqj

[20]. R. Hariprasad , S. Muthuraja, (2016). An Image Processing Technique combined with Real Time Data Acquisition to Identify the Posture, 3–5.

[21]. S. Ghosh & S. Shit (2014). [ I, 1065–1068].

[22]. W. Henning (n.d.). A Two-Sample Test for Statistical Comparisons of Shape Populations.
[23]. Z. Y. Lv, P. Zhang, J. A. Benediktsson, & W. Z. Shi (2014). Morphological Pro fi les Based on Differently Shaped Structuring Elements for Classi fi cation of Images with Very High Spatial Resolution, 1–9.

[24]. L. Demidova (2017). Two-Level Intellectual Classifier Based on the SVM Algorithm, (June), 0–3.