Phuoc-Loc Nguyen
Research Subjects
Phuoc-Loc Nguyen has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Chanh-Nghiem Nguyen
Can Tho University
4 shared publications - Masayuki Fukuzawa
Kyoto Institute of Technology
4 shared publications - Nhut-Thanh Tran
Can Tho University
4 shared publications - Chi-Ngon Nguyen
Can Tho University
2 shared publications - Byung-Ryong Lee
University of Ulsan, School of Mechanical Engineering, Ulsan, Republic of Korea
1 shared publication - Chi-Linh Dam
Faculty of Automation Engineering, Can Tho University, Can Tho, Vietnam
1 shared publication
Latest Publications
- 30 December 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (1) , 015437
Design of a computer vision system for accurate measurement of mango skin defects by surface image slicing
External features such as color, size, weight, and defect area are among the critical parameters for grading mangoes for export purposes. This paper describes a novel computer vision system (CVS) for the accurate measurement of mango skin defects. A novel algorithm called mango skin image slicing (MSIS) was developed to generate mango slices, each of which includes points of pseudo-equidistance from the camera to accurately calculate the defect area. Based on images captured from 360-degree views, defects on the entire mango surface can be detected. For the first time, a strategy for preventing multiple considerations of the same defects from 360-degree images was introduced based on MSIS. The experimental results revealed that recalculations of the same defects were avoided, and negligible minor defects were excluded, complying with the guidance of the mango exporting firms. The measurement accuracy was evaluated with artificial defects of 100 mm2, yielding a mean error of 6.0 ± 1.4 mm2, which was suitable for defect area measurement considering the mango grading standard. The CVS throughput of approximately 644 mangoes per hour was also a reasonable trade-off for the achieved accuracy and great potential of extending the CVS for more sophisticated classification of non-negligible defects based on the advantages of mango images captured at closer camera–object distances.
- 30 December 2024
- Published by IOP Publishing in Measurement Science and Technology
- Vol. 36 (1) , 015437
Design of a computer vision system for accurate measurement of mango skin defects by surface image slicing
External features such as color, size, weight, and defect area are among the critical parameters for grading mangoes for export purposes. This paper describes a novel computer vision system (CVS) for the accurate measurement of mango skin defects. A novel algorithm called mango skin image slicing (MSIS) was developed to generate mango slices, each of which includes points of pseudo-equidistance from the camera to accurately calculate the defect area. Based on images captured from 360-degree views, defects on the entire mango surface can be detected. For the first time, a strategy for preventing multiple considerations of the same defects from 360-degree images was introduced based on MSIS. The experimental results revealed that recalculations of the same defects were avoided, and negligible minor defects were excluded, complying with the guidance of the mango exporting firms. The measurement accuracy was evaluated with artificial defects of 100 mm2, yielding a mean error of 6.0 ± 1.4 mm2, which was suitable for defect area measurement considering the mango grading standard. The CVS throughput of approximately 644 mangoes per hour was also a reasonable trade-off for the achieved accuracy and great potential of extending the CVS for more sophisticated classification of non-negligible defects based on the advantages of mango images captured at closer camera–object distances.
- Open Access
- 28 August 2024
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 12 (02) , 153-170
Towards Automatic Mango Grading: A Computer Vision System Design for Measuring a Mango’s Weight and Skin Defect Areas
Mangoes are among the tropical fruits that provide high export value. Therefore, grading them based on physical and external features is required to satisfy the exporting criteria. An image acquisition system has recently been developed to capture the mango’s 360∘ views. This study developed a computer vision system (CVS) to extend this system towards automatic grade classification of mango fruits based on the mango’s weight and imperfect skin area. The front-view images of four major faces could be identified with a higher accuracy of 97.98% by applying an average filter on the skin area. The mango region in these major-face images was then detected so that the skin defects could measured, and the mango’s 3D dimensions and area in pixel numbers could be calculated to estimate the mango’s weight with an average error of about 2.5% using a ridge regression model. Experimental results with 120 identified major-face images with artificial blemishes showed an average percentage error of 7.28%. At the controlled conveyor speed of 41[ ]mm/s for favorable image capture, the system could sequentially analyze about 1452 mangoes per hour for blemish area calculation. With such high throughput, the proposed CVS could be tailored to build an automatic mango grading system based on the mango’s weight and skin imperfections.
- 28 August 2024
- Published by World Scientific Pub Co Pte Ltd in Vietnam Journal of Computer Science
- Vol. 12 (02) , 153-170
Open AccessTowards Automatic Mango Grading: A Computer Vision System Design for Measuring a Mango’s Weight and Skin Defect Areas
Mangoes are among the tropical fruits that provide high export value. Therefore, grading them based on physical and external features is required to satisfy the exporting criteria. An image acquisition system has recently been developed to capture the mango’s 360∘ views. This study developed a computer vision system (CVS) to extend this system towards automatic grade classification of mango fruits based on the mango’s weight and imperfect skin area. The front-view images of four major faces could be identified with a higher accuracy of 97.98% by applying an average filter on the skin area. The mango region in these major-face images was then detected so that the skin defects could measured, and the mango’s 3D dimensions and area in pixel numbers could be calculated to estimate the mango’s weight with an average error of about 2.5% using a ridge regression model. Experimental results with 120 identified major-face images with artificial blemishes showed an average percentage error of 7.28%. At the controlled conveyor speed of 41[ ]mm/s for favorable image capture, the system could sequentially analyze about 1452 mangoes per hour for blemish area calculation. With such high throughput, the proposed CVS could be tailored to build an automatic mango grading system based on the mango’s weight and skin imperfections.
- Open Access
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 212371-212382
Precise Sweetness Grading of Mangoes (Mangifera indica L.) Based on Random Forest Technique With Low-Cost Multispectral Sensors
Before being exported, mangoes generally undergo rigorous external and internal quality inspection processes in which near-infrared (NIR) spectral approaches are favorable for grading purposes. A successful NIR-based grading system depends largely on high-quality spectral sensors and the reliability of the classifier. Motivated by the high economic impact of Cat Hoa Loc mangoes (Mangifera indica L.), we demonstrated that the sweetness of that mangoes could be precisely graded based on a random forest (RF) classifier in a three-phase approach with a low-cost Visible-Near infrared (VIS-NIR) multispectral sensor chipset. This approach is so-called RPR because RF, Partial Least Squares regression, and RF were respectively applied to consecutively determine the significant VIS-NIR responses, the good features as input variables, and the reliable RF classifier via our formulated discriminant index (DI). The experimental results confirmed that higher classification accuracy was achieved by using the extracted latent features rather than the raw VIS-NIR data. The DI was effectively used as a reliability measure to select the optimal classifier among those of identical training and testing accuracies of 100% and 82.1%, respectively. Performance comparison between the optimal RF classifier with a Support Vector Machines classifier and a multinomial logistic regression showed that the developed RF classifier was superior in various performance indices. Therefore, it is promising to extend the proposed approach to more complicated fruit grading problems with sufficient VIS-NIR datasets that are acquired from low-cost multispectral sensors.
- 24 November 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 212371-212382
Open AccessPrecise Sweetness Grading of Mangoes (Mangifera indica L.) Based on Random Forest Technique With Low-Cost Multispectral Sensors
Before being exported, mangoes generally undergo rigorous external and internal quality inspection processes in which near-infrared (NIR) spectral approaches are favorable for grading purposes. A successful NIR-based grading system depends largely on high-quality spectral sensors and the reliability of the classifier. Motivated by the high economic impact of Cat Hoa Loc mangoes (Mangifera indica L.), we demonstrated that the sweetness of that mangoes could be precisely graded based on a random forest (RF) classifier in a three-phase approach with a low-cost Visible-Near infrared (VIS-NIR) multispectral sensor chipset. This approach is so-called RPR because RF, Partial Least Squares regression, and RF were respectively applied to consecutively determine the significant VIS-NIR responses, the good features as input variables, and the reliable RF classifier via our formulated discriminant index (DI). The experimental results confirmed that higher classification accuracy was achieved by using the extracted latent features rather than the raw VIS-NIR data. The DI was effectively used as a reliability measure to select the optimal classifier among those of identical training and testing accuracies of 100% and 82.1%, respectively. Performance comparison between the optimal RF classifier with a Support Vector Machines classifier and a multinomial logistic regression showed that the developed RF classifier was superior in various performance indices. Therefore, it is promising to extend the proposed approach to more complicated fruit grading problems with sufficient VIS-NIR datasets that are acquired from low-cost multispectral sensors.