基于DSP和图像分割的织物疵点实时检测方法
|
摘要
疵点自动检测是纺织品缺陷在线检测领域的一个研究热点;为满足高速实时疵点检测应用要求,构建了基于TMS320DM642的织物疵点检测硬件系统;该系统由光源与成像、图像采集与实时处理、结果显示与统计分析等部分组成,能充分利用数字信号处理器的高速运算能力,有效提高系统的检测速度;并提出一种基于自适应阈值分割的疵点检测算法,通过增强织物图像灰度直方图波谷对应阈值的检测概率,有效提高了疵点图像的分割准确性;最后,在所建硬件系统平台上利用该算法进行了棉坯布疵点检测实验,疵点检出率达到93.6%;结果表明,本系统可自动实时检测织物疵点,且检出效率高。
The automatic defect detection has been a research focus in the field of fabric defect detection on-line.To meet the application requirements for high-speed and real-time defect detection,a fabric defect detection hardware system based on TMS320DM642 is designed.The system is consisted of the following parts:illumination &imaging,image acquisition &real-time processing,result display &statistical analysis.It can take full advantage of the digital signal processors' high-speed operation ability and improves the speed of detection effectively.This paper proposes an algorithm based on adaptive threshold segmentation for defect detection.This algorithm enhances the detection probability of the threshold value corresponded to the fabric images' gray histogram troughs and improves the accuracy of detect images' segmentation.The defect detection rate reaches 93.6% through cambrayon detection experiment using the algorithm based on the hardware system platform.The result shows that the system can achieve the automatic and real-time fabric defect detection and has the high detection efficiency.
The automatic defect detection has been a research focus in the field of fabric defect detection on-line.To meet the application requirements for high-speed and real-time defect detection,a fabric defect detection hardware system based on TMS320DM642 is designed.The system is consisted of the following parts:illumination &imaging,image acquisition &real-time processing,result display &statistical analysis.It can take full advantage of the digital signal processors' high-speed operation ability and improves the speed of detection effectively.This paper proposes an algorithm based on adaptive threshold segmentation for defect detection.This algorithm enhances the detection probability of the threshold value corresponded to the fabric images' gray histogram troughs and improves the accuracy of detect images' segmentation.The defect detection rate reaches 93.6% through cambrayon detection experiment using the algorithm based on the hardware system platform.The result shows that the system can achieve the automatic and real-time fabric defect detection and has the high detection efficiency.
引文
[1]李文羽,程隆棣.基于机器视觉和图像处理的织物疵点检测研究新进展[J].纺织学报,2014,35(3):158-164.
[2]吴宁,管声启,徐帅华.基于纹理边缘周期性与局部方向性的织物疵点检测[J].计算机与现代化,2014(4):16-19.
[3]雷同飞.基于倾斜矫正算法的针织物图像研究[J].科学技术与工程,2013,13(19):5716-5718.
[4]刘哲.织物图像增强矩阵特征模型的建立[J].纺织学报,2011,32(8):142-146.
[5]王松伟,石美红,张正,等.基于熵和变异度的织物疵点图像分割方法[J].西安工程大学学报,2014,28(2):207-219.
[6]张素贞,叶建隆,邹采荣.织物图像增强技术的研究[J].电子器件,2011,34(4):473-476.
[7]曹文梁.基于改进差分盒算法的织物疵点自动检测方法[J].计算机测量与控制,2014,22(6):1676-1679.
[8]诸葛振容,徐敏,刘洋飞.基于Mean Shift的织物图像分割算法[J].纺织学报,2007,28(10):108-116.
[9]毕明德,孙志刚,李叶松.基于机器视觉的布匹疵点检测系统[J].仪表技术与传感器,2013(12):37-39.
[10]Latif-Amet L,Ertuzun A.An efficient method for texture defect detection:sub-band domain co-occurrence matrices[J].Image and vision Computing,2000,18(6):543-553.
[11]景军锋,张缓缓,李鹏飞,等.基于方法库的织物图像疵点检测[J].东华大学学报(自然科学版),2013,39(5):650-655.
[12]李春雷,张兆翔,刘洲峰,等.基于纹理差异视觉显著性的织物疵点检测算法[J].山东大学学报(工学版),2014,44(4):1-8.
[13]Liu Z,Wang Z,Zhao Q,et al.A fabric defect detection algorithm based on improved valley-emphasis method[J].Research Journal of Applied Sciences,Engineering and Technology,2014,7(12):2427-2431.
[14]刘洲峰,赵全军,李春雷,等.基于局部统计与整体显著性的织物疵点检测算法[J].纺织学报,2014,35(11):67-73.
[2]吴宁,管声启,徐帅华.基于纹理边缘周期性与局部方向性的织物疵点检测[J].计算机与现代化,2014(4):16-19.
[3]雷同飞.基于倾斜矫正算法的针织物图像研究[J].科学技术与工程,2013,13(19):5716-5718.
[4]刘哲.织物图像增强矩阵特征模型的建立[J].纺织学报,2011,32(8):142-146.
[5]王松伟,石美红,张正,等.基于熵和变异度的织物疵点图像分割方法[J].西安工程大学学报,2014,28(2):207-219.
[6]张素贞,叶建隆,邹采荣.织物图像增强技术的研究[J].电子器件,2011,34(4):473-476.
[7]曹文梁.基于改进差分盒算法的织物疵点自动检测方法[J].计算机测量与控制,2014,22(6):1676-1679.
[8]诸葛振容,徐敏,刘洋飞.基于Mean Shift的织物图像分割算法[J].纺织学报,2007,28(10):108-116.
[9]毕明德,孙志刚,李叶松.基于机器视觉的布匹疵点检测系统[J].仪表技术与传感器,2013(12):37-39.
[10]Latif-Amet L,Ertuzun A.An efficient method for texture defect detection:sub-band domain co-occurrence matrices[J].Image and vision Computing,2000,18(6):543-553.
[11]景军锋,张缓缓,李鹏飞,等.基于方法库的织物图像疵点检测[J].东华大学学报(自然科学版),2013,39(5):650-655.
[12]李春雷,张兆翔,刘洲峰,等.基于纹理差异视觉显著性的织物疵点检测算法[J].山东大学学报(工学版),2014,44(4):1-8.
[13]Liu Z,Wang Z,Zhao Q,et al.A fabric defect detection algorithm based on improved valley-emphasis method[J].Research Journal of Applied Sciences,Engineering and Technology,2014,7(12):2427-2431.
[14]刘洲峰,赵全军,李春雷,等.基于局部统计与整体显著性的织物疵点检测算法[J].纺织学报,2014,35(11):67-73.