원문정보
초록
영어
Effective identification of wood decay and crack defects by using support vector machine (SVM) theory. Extracting wood defect image through the image acquisition system, then processing the defect image by using gray level change, equalization, and median filtering et al. So as to achieve the purpose of improve the image quality and detection accuracy. Segment the target images, and then measures the area, perimeter, and diameter of the wood defects. Three eigenvalues, area and perimeter square ratio, length to diameter ratio and circumference and area ratio, which can be identified the wood defects was obtained. Separating these eigenvalues into training set and testing set. Training Support vector machine by using training set, establish a preliminary model of support vector machine. Using support vector machine model for accuracy test, if the test accuracy is low, repeatedly adjust the parameters of support vector machine for training and testing until reach the test accuracy. Making sure the kernel function and various parameters of support vector machine, constructing the support vector machine, which using for wood defect classification. The experimental results showed that this method has fast calculation speed, high precision, and helps to raise the utilization rate of wood.
목차
1. Introduction
2. Wood Defects Image Pre-Processing
2.1. Histogram Equalization
2.2. Median Filtering Process of Wood Defect Images
2.3. Wood Defect Image Segmentation
3. The Selection and Extraction of Wood Defect Characteristic Value
3.1. The Selection of Wood Defect Characteristic Value
3.2. The Extraction of Wood Defect Characteristic Value
4. Application of Support Vector Machine to Wood Defect Classification
4.1. The Support Vector Machine
4. 2. The Design of the Support Vector Machine
5. Results and Discussion
References