Model-based localization and measurement of miniature surface mount components
View Patent ↗A system and method for object inspection includes an object modeler; an iterative object segmentor in signal communication with the object modeler for receiving an input image and model parameters and producing a segmented image; a moment transformer in signal communication with the iterative object segmentor for receiving an input image, model parameters and a segmented image and producing estimates of object translation, rotation and scaling; an edge detector and interpolator in signal communication with the moment transformer for receiving an input image, model parameters and estimates and producing a set of line edges; and an iterative optimizer in signal communication with the edge detector and interpolator for receiving an input image, model parameters, estimates and line edges and producing refined estimates of object translation, rotation and scaling.
1. An object inspection method comprising:
offline modeling of an object type; and
runtime matching of an object corresponding to the object type;
wherein runtime matching comprises:
receiving an image having an object of the object type;
performing a coarse search for the object; and
performing a refined search for the object;
wherein performing a coarse search comprises localizing the object from the image in accordance with a model;
wherein performing a refined search comprises measuring the localized object;
wherein localizing comprises:
iteratively segmenting the object; and
applying a moment transformation to the segmented object; and
wherein iteratively segmenting the object comprises:
selecting an initial estimate of a threshold by using the average gray-level of the 2n brightest pixels in the image, where n is the size of the model;
segmenting the image into a background region and an object region in accordance with the threshold, with the pixels having a gray-level less than the threshold being assigned to the background region and all other pixels being assigned to the object region;
calculating the mean gray-levels within the background and object regions, respectively;
calculating a new threshold in accordance with the calculated mean gray-levels and the number of pixels in each region;
repeating the above steps of segmenting, calculating gray-levels and calculating new thresholds until-convergence is reached; and
obtaining the segmented object from the final pixels in the object region.
2. A method as defined in claim 1 wherein said object is a miniature surface mount component.
3. A method as defined in claim 1 wherein offline modeling comprises:
receiving reference data for objects corresponding to the object type; and
providing a model for the object type in correspondence with the received reference data.
4. A method as defined in claim 3 wherein the received reference data comprises computer aided design parameters for objects corresponding to the object type.
5. A method as defined in claim 3 wherein the provided model comprises a polygonal shape.
6. A method as defined in claim 1 wherein the received image comprises an object located on a simple image background.
7. A method as defined in claim 1 wherein localizing comprises estimating the pose of the object, and wherein measuring comprises estimating the dimension of the object.
8. A method as defined in claim 1 wherein measuring comprises:
detecting and interpolating edges of the object; and
iteratively optimizing measurement results.
9. An object inspection system comprising:
means for modeling an object type; and
means for matching an object corresponding to the object type;
wherein the means for matching comprises:
means for receiving an image having an object of the object type;
means for performing a coarse search for the object; and
means for performing a refined search for the object;
wherein the means for performing a coarse search comprises means for localizing the object from the image in accordance with a model;
wherein the means for performing a refined search comprises means for measuring the localized object;
wherein the means for localizing comprises:
means for iteratively segmenting the object; and
means for applying a moment transformation to the segmented object; and
wherein the means for iteratively segmenting the object comprises:
means for selecting an initial estimate of a threshold by using the average gray-level of the 2n brightest pixels in the image, where n is the size of the model;
means for segmenting the image into a background region and an object region in accordance with the threshold, with the pixels having a gray-level less than the threshold being assigned to the background region and all other pixels being assigned to the object region;
means for calculating the mean gray-levels within the background and object regions, respectively;
means for calculating a new threshold in accordance with the calculated mean gray-levels and the number of pixels in each region;
means for repeating the above steps of segmenting, calculating gray-levels and calculating new thresholds until convergence is reached; and
means for obtaining the segmented object from the final pixels in the object region.
10. A system as defined in claim 9 wherein said object is a miniature surface mount component.
11. A system as defined in claim 9 wherein the means for modeling comprises:
means for receiving reference data for objects corresponding to the object type; and
means for providing a model for the object type in correspondence with the received reference data.
12. A system as defined in claim 9 wherein the means for localizing comprises means for estimating the pose of the object, and wherein the means for measuring comprises means for estimating the dimension of the object.
13. A system as defined in claim 9 wherein the means for measuring comprises:
means for detecting and interpolating edges of the object; and
means for iteratively optimizing measurement results.