Efficient LBP-GLCM texture analysis for asphalt pavement raveling detection using eXtreme Gradient Boost

Daneshvari, Mohammad Hassan; Nourmohammadi, Ebrahim; Ameri, Mahmoud; Mojaradi, Barat

doi:10.1016/j.conbuildmat.2023.132731

Cited by 10 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is calculated by counting the number of times a pair of pixels with a particular spatial relationship occurs in an image with a specific combination of grayish levels. GLCM is used to extract texture features such as contrast, correlation, energy, and homogeneity, which can be used for image classification and segmentation [34]- [36].…”

Section: ) Gray Level Co-occurrence Matrix (Glcm)mentioning

confidence: 99%

Wood Type Identification System using Naive Bayes Classification

Yulianto,

Fadlil

2023

Control Syst. Optim. Lett.

View full text Add to dashboard Cite

Wood, a forest product and natural resource, is a raw material used to make household goods. Some types of wood have almost the same pattern or structure. Wood quality varies greatly depending on the tree species and the environmental conditions in which it grows. This makes it challenging to identify the type of wood, especially for wooden furniture users. Therefore, wood classification is essential to ensure that the wood used meets the required quality standards and requirements. Automatic classification of wood using image processing has several advantages and can make it easier for humans. One of the image processing methods for wood classification is the Naïve Bayes method. Feature extraction technique using GLCM using contrast, correlation, energy, and homogeneity attributes. The GLCM methods can be combined to create a system design to distinguish five wood species using an image-based wood type identification system. The study results have successfully designed a system to determine five types of wood using the framework of an image-based wood type identification system. An application system has been produced to distinguish five types of wood using the framework of an image-based wood type identification system with the GLCM feature extraction method and the Naive Bayes classification method. The application system successfully identified wood species with a test accuracy rate of 88%.

show abstract

Section: ) Gray Level Co-occurrence Matrix (Glcm)mentioning

confidence: 99%

Wood Type Identification System using Naive Bayes Classification

Yulianto,

Fadlil

2023

Control Syst. Optim. Lett.

View full text Add to dashboard Cite

show abstract

“…Integrating GLCM and LBP features can produce comprehensive feature vectors for object detection, especially objects experiencing rotation and displaying complex texture variations. The proposes to combine these two methods not only increases the robustness to texture variations and rotation but also provides a deeper understanding of the texture characteristics of objects in 2D digital images [9]. Model test using 4,437 2D objects, machine learning classification using k-nearest neighbors (KNN) and random forest (RF) [10]- [13].…”

mentioning

confidence: 99%

The object detection model uses combined extraction with KNN and RF classification

Kurniati,

Manongga,

Sembiring

et al. 2024

IJEECS

View full text Add to dashboard Cite

Object detection plays an important role in various fields. Developing detection models for 2D objects that experience rotation and texture variations is a challenge. In this research, the initial stage of the proposed model integrates the gray-level co-occurrence matrix (GLCM) and local binary patterns (LBP) texture feature extraction to obtain feature vectors. The next stage is classifying features using k-nearest neighbors (KNN) and random forest (RF), as well as voting ensemble (VE). System testing used a dataset of 4,437 2D images, the results for KNN accuracy were 92.7% and F1-score 92.5%, while RF performance was lower. Although GLCM features improve performance on both algorithms, KNN is more consistent. The VE approach provides the best performance with an accuracy of 93.9% and an F1-score of 93.8%, this shows the effectiveness of the ensemble technique in increasing object detection accuracy. This study contributes to the field of object detection with a new approach combining GLCM and LBP as feature vectors as well as VE for classification.

show abstract