Swietenia Mahagoni Wood Defects Segmentation Using YIQ Color Space and Thresholding

Rahayu, Sri; Qhomariyah, Nurul; Purnama, Jajang Jaya; Riana, Dwiza; Achyani, Yuni Eka; Ariani, Fattya

doi:10.1088/1742-6596/1641/1/012071

Cited by 1 publication

(1 citation statement)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tropical rainforests in Southeast Asia contain more than 15000 different plant species, consisting of 3000 categories of wood species. The largest income for Southeast Asian countries comes from the export activities of wood production [1,2]. Based on WITS (World Integrated Trade Solution) data in 2018, Indonesia's timber exports are spread across 191 partner countries.…”

Section: Introductionmentioning

confidence: 99%

Comparison of segmentation and identification of swietenia mahagoni wood defects with augmentation images

Riana

Rahayu

Hasan

et al. 2021

Heliyon

Self Cite

View full text Add to dashboard Cite

The largest income for Southeast Asian countries comes from the export activities of wood production. The potential for timber exports in Indonesia continues to increase each year. This soaring potential needs to be continually improved by maintaining quality so that trust and good cooperation can continue to be established with partner countries. Wood quality is closely related to wood defects. The faster the detection of wood defects is, the faster the quality of the wood will be determined. The wood industry which is still manual is also very susceptible to human eye fatigue. Technology is currently developing rapidly to help human productive activities and image processing is a breakthrough to detect wood defects. This study aims to identify swietenia mahagoni wood defects using the euclidean distance method from the extraction of 6 texture and shape features GLCM (Gray Level Co-Occurance Method) including metric, eccentricity, contrast, correlation, energy, and homogeneity, which was previously segmented with the best segmentation from the comparison results of thresholding and k-means segmentation and produced an average accuracy of 95.33% with an F1 score value of 0.95. The dataset used is the primary dataset with a total of 54 images on 3 types of wood defects, namely growing skin defects on wood ends, rotten wood eye on the body, and healthy wood eye on the body. Cross validation is also applied to test the reliability of the proposed model. By using 3-fold cross validation, the optimal average accuracy is 88.90%. Validation with other similar datasets was also carried out by identifying potato leaf defects resulting in an average accuracy of 92.86% with the most optimal 3-fold cross validation value achieved an average accuracy of 83.33%. Image augmentation is also carried out in order to reproduce the image so that the reliability test of the proposed method can be carried out, namely by rotating the image 45 degrees,90 degrees,120 degrees,180 degrees which produces 84 images of augmentation, so that the total image is 138 images and gets an average accuracy from the image augmentation is 80%.

show abstract

Section: Introductionmentioning

confidence: 99%