摘要
针对传统检测算法普遍存在检测精度低、耗时长的问题,提出了一种基于稀疏表示分类的检测识别算法。该算法通过引入了稀疏表示分类器,选取有效的子块高阶矩特征对图像子块进行分类,避免了对图像进行预处理,简化了检测步骤;然后根据子块分类结果的映射编码识别裂缝类型。在实际采集的高速公路路面图像数据库上进行测试,实验结果表明该算法相比传统算法具有更高的识别精度和执行效率。
Aiming at the problem ol low detection accuracy and time-consuming in traditional detectionalgorithms, a new detection and recognition algorithm based on sparse representation classification isproposed. By introducing a sparse representation-based classifier, a high order moment feature is selectedto classify the subblocks ol image in order to avoid the image preprocessing, simplify the detection steps ;and then, according to the results ol subblocks’ classification, the type of crack is mapped by encoding.the algorithm is tested on the actual database of highway pavement images. The experimental results showthat the algorithm has higher recognition accuracy and execution efficiency compared with the traditionalalgorithm.
作者
周舟
唐振民
吕建勇
钱彬
ZHOU Zhou TANG Zhen-min LV Jian-yong QIAN Bin(School of Computer Science and Engineering,Nanjing University of Science and Technology,Nanjing 2 1 0 0 9 4 ,China)
出处
《信息技术》
2016年第11期21-25,共5页
Information Technology
基金
国家自然科学基金(61473154)
