-
公开(公告)号：US20230334651A1
公开(公告)日：2023-10-19
申请号：US18020826
申请日：2021-08-05
Applicant: CORNING INCORPORATED
Inventor： Jacob George , Byoungseon Jeon , Seth Thomas Nickerson , Hak Chuah Sim
IPC: G06T7/00
CPC classification number: G06T7/001 , G06T2207/30108 , G06T2207/20084
Abstract: A method and system for inspecting a honeycomb body. The method includes capturing a first image. Instances of at least one feature in the first image that correlates to a structural characteristic of the honeycomb body are detected. One or more detected instances of the at least one feature identified in the first image are abstracted by creating a graphical representation of each of the one or more detected instances of the at least one feature. A second image is generated by augmenting the first image with the graphical representation in place of or in addition to each of the one or more detected instances of the at least one feature identified in the first image. The second image is analyzed using a machine learning algorithm to classify the honeycomb body with respect to the structural characteristic of the honeycomb body.
-
2.发明授权公开(公告)号：US09996766B2
公开(公告)日：2018-06-12
申请号：US15139931
申请日：2016-04-27
Applicant: CORNING INCORPORATED
Inventor： DiRisio Carlo Richard , Frey Julie Charmaine , Gehl Kristine Sluder , Russell Wayne Madara , Hak Chuah Sim , Yeqing Zhang
CPC classification number: G06K9/4661 , G06K9/4604 , G06K9/52 , G06K9/6215 , G06T7/0006 , G06T2207/30164
Abstract: Imaging-based methods for detecting defects in an extruded cellular ceramic article having a web array are disclosed. The methods may include capturing a digital image of the web array to establish an intensity-based initial web array representation. The methods also may include performing an intensity threshold process on the initial web array representation to define an intensity-based high-resolution web array representation having sub-pixel resolution, and performing piecewise cubic spline fits to define corresponding web skeletons. The method may also include comparing intensities of the high-resolution web array representation along the web skeletons to a threshold intensity to determine the defect locations and sizes. The methods can be applied to determining the size and location of skin defects as well.
-
3.发明申请IMAGING-BASED METHODS FOR DETECTING AND MEASURING DEFECTS IN EXTRUDED CELLULAR CERAMIC ARTICLES 有权基于成像的检测和测量超微细陶瓷制品缺陷的方法公开(公告)号：US20160321797A1
公开(公告)日：2016-11-03
申请号：US15139931
申请日：2016-04-27
Applicant: CORNING INCORPORATED
Inventor： DiRisio Carlo Richard , Frey Julie Charmaine , Gehl Kristine Sluder , Russell Wayne Madara , Hak Chuah Sim , Yeqing Zhang
CPC classification number: G06K9/4661 , G06K9/4604 , G06K9/52 , G06K9/6215 , G06T7/0006 , G06T2207/30164
Abstract: Imaging-based methods for detecting defects in an extruded cellular ceramic article having a web array are disclosed. The methods may include capturing a digital image of the web array to establish an intensity-based initial web array representation. The methods also may include performing an intensity threshold process on the initial web array representation to define an intensity-based high-resolution web array representation having sub-pixel resolution, and performing piecewise cubic spline fits to define corresponding web skeletons. The method may also include comparing intensities of the high-resolution web array representation along the web skeletons to a threshold intensity to determine the defect locations and sizes. The methods can be applied to determining the size and location of skin defects as well.
Abstract translation: 公开了一种用于检测具有卷筒纸阵列的挤出的蜂窝状陶瓷制品中的缺陷的基于成像的方法。 该方法可以包括捕获网络阵列的数字图像以建立基于强度的初始网络阵列表示。 所述方法还可以包括对初始web阵列表示执行强度阈值处理以定义具有子像素分辨率的基于强度的高分辨率网络阵列表示，以及执行分段三次样条拟合以定义相应的网络骨架。 该方法还可以包括将沿着web骨架的高分辨率网格数组表示的强度与阈值强度进行比较，以确定缺陷位置和大小。 该方法也可用于确定皮肤缺陷的大小和位置。
-
-
Search Results
3
records
(took 0.01 seconds)
