Developing Wood Identification System by Local Binary Pattern and Hough Transform Method

Hadiwidjaja, M. Luthfi; Gunawan, P. H.; Prakasa, Esa; Rianto, Yan; Sugiarto, Bambang; Wardoyo, Riyo; Damayanti, Ratih; Sugiyanto, Krisdianto; Dewi, Listya Mustika; Astutiputri, Vidya Fatimah

doi:10.1088/1742-6596/1192/1/012053

Cited by 10 publications

(4 citation statements)

References 15 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%

See 1 more Smart Citation

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

Riana

Rahayu

Hasan

et al. 2021

Heliyon

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%

“…Timber identification systems can be an important system for minimizing fraud in the wood markets [1,7]. The inspection of visual defects being carried out manually in the wood industry is known to be unreliable due to its susceptibility to human error, for example, due to acute symptoms of headache and eye fatigue [8].…”

Section: Introductionmentioning

confidence: 99%

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

Riana

Rahayu

Hasan

et al. 2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…In the process of establishing features, the commonly used feature extraction methods for wood materials include the gray-level co-occurrence matrix [ 9 , 10 , 11 ], local binary pattern (LBP) [ 12 , 13 , 14 ], scale-invariant feature transform [ 15 , 16 ], and wavelet transform [ 17 , 18 ]. In addition, modified versions or other methods based on the above methods have emerged.…”

Section: Introductionmentioning

confidence: 99%

A Sawn Timber Tree Species Recognition Method Based on AM-SPPResNet

Ding

Liu

Zhuang

et al. 2021

Sensors

View full text Add to dashboard Cite

Sawn timber is an important component material in furniture manufacturing, decoration, construction and other industries. The mechanical properties, surface colors, textures, use and other properties of sawn timber possesed by different tree species are different. In order to meet the needs of reasonable timber use and product quality of sawn timber products, sawn timber must be identified according to tree species to ensure the best use of materials. In this study, an optimized convolution neural network was proposed to process sawn timber image data to identify the tree species of the sawn timber. The spatial pyramid pooling and attention mechanism were used to improve the convolution layer of ResNet101 to extract the feature vector of sawn timber images. The optimized ResNet (simply called “AM-SPPResNet”) was used to identify the sawn timber image, and the basic recognition model was obtained. Then, the weight parameters of the feature extraction layer of the basic model were frozen, the full connection layer was removed, and using support vector machine (SVM) and XGBoost classifier which were commonly used in machine learning to train and learn the 21 × 1024 dimension feature vectors extracted by feature extraction layer. Through a number of comparative experiments, it is found that the prediction model using linear function as the kernel function of support vector machine learning the feature vectors extracted from the improved convolution layer performed best, and the F1 score and overall accuracy of all kinds of samples were above 99%. Compared with the traditional methods, the accuracy was improved by up to 12%.

show abstract

“…This approach could help to reveal some new aspects of wood anatomy that might be difficult in conventional observation. The next reference is reported by Hadiwidjaja et al (2019). The Levi and Hassner (2015) proposed a simple convolutional net architecture that can be used even when the amount of learning data is limited.…”

Section: Introductionmentioning

confidence: 99%

Wood Classification of Japanese Fagaceae using Partial Sample Area and Convolutional Neural Networks

Fathurahman¹,

Gunawan²,

Prakasa³

et al. 2021

Journal of the Korean Wood Science and Technology

Self Cite

View full text Add to dashboard Cite

Wood identification is regularly performed by observing the wood anatomy, such as colour, texture, fibre direction, and other characteristics. The manual process, however, could be time consuming, especially when identification work is required at high quantity. Considering this condition, a convolutional neural networks (CNN)-based program is applied to improve the image classification results. The research focuses on the algorithm accuracy and efficiency in dealing with the dataset limitations. For this, it is proposed to do the sample selection process or only take a small portion of the existing image. Still, it can be expected to represent the overall picture to maintain and improve the generalisation capabilities of the CNN method in the classification stages. The experiments yielded an incredible F1 score average up to 93.4% for medium sample area sizes (200 × 200 pixels) on each CNN architecture (VGG16, ResNet50, MobileNet, DenseNet121, and Xception based). Whereas DenseNet121-based architecture was found to be the best architecture in maintaining the generalisation of its model for each sample area size (100, 200, and 300 pixels). The experimental results showed that the proposed algorithm can be an accurate and reliable solution.

show abstract

Developing Wood Identification System by Local Binary Pattern and Hough Transform Method

Cited by 10 publications

References 15 publications

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

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

A Sawn Timber Tree Species Recognition Method Based on AM-SPPResNet

Wood Classification of Japanese Fagaceae using Partial Sample Area and Convolutional Neural Networks

Contact Info

Product

Resources

About