激光与光电子学进展, 2018, 55 (5): 051501, 网络出版: 2018-09-11
木材节子缺陷检测与定位方法 下载: 1546次
Method for Wooden Knot Detection and Localization
机器视觉 图像识别 灰度直方图 最大熵 纹理特征 分块特征提取 支持向量机 machine vision image recognition gray histogram maximum entropy texture feature block feature extraction support vector machine
摘要
表面缺陷检测在木材的选择和利用中具有重要作用。提出了一种基于木材表面图像的灰度和纹理特征的木材节子缺陷检测与定位方法。首先,将图像分成相同大小的子图,计算每个子块图像的灰度直方图,以灰度最大熵作为判断依据对各子块图像进行初步识别;然后利用局部二值模式算法提取初步识别结果中各子块图像的纹理特征,并使用支持向量机分类算法进行节子图像的精确识别;最后将识别为节子图像的各子块图像拼接起来,得到最终识别结果。实验结果表明,所提方法能够得到较好的识别结果。采用混淆矩阵作为评价标准时,识别准确率可达到95%。
Abstract
Surface defect detection plays an important role in the selection and utilization of wood. A method is proposed for knot defect detection and localization based on the feature of gray and texture on the wood surface. First, the image is divided into blocks with equal sizes. The gray histogram of each subimage is calculated, and the gray maximum entropy is used as the criterion to achieve the preliminary recognition of the subimage. Second, the texture features of the preliminary result are extracted by local binary patterns algorithm. The support vector machine classification algorithm is utilized to precisely recognize the knot images. Finally, the subimages judged as knot images are joined together to obtain the final result. The experimental results show that the proposed method can obtain commendable recognition results. The knot recognition accuracy reaches 95% when confusion matrix is used as the evaluation criterion.
王泽润, 方益明, 冯海林, 杜晓晨, 夏凯. 木材节子缺陷检测与定位方法[J]. 激光与光电子学进展, 2018, 55(5): 051501. Zerun Wang, Yiming Fang, Hailin Feng, Xiaochen Du, Kai Xia. Method for Wooden Knot Detection and Localization[J]. Laser & Optoelectronics Progress, 2018, 55(5): 051501.