Cognex Corporation

Other

John P Petry, Iii

Juha Tapio Koljonen

Reto Wyss

David J Michael

Cyril C Marrion

Arman M Garakani

Len L Picard

This invention overcomes disadvantages of the prior art by providing a vision system and method of use, and graphical user interface (GUI), which employs a camera assembly having an on-board processor of low to modest processing power. At least one vision system tool analyzes image data, and generates results therefrom, based upon a deep learning process. A training process provides training image data to a processor (optionally) remote from the on-board processor to cause generation of the vision system tool therefrom, and provides a stored version of the vision system tool for runtime operation on the on-board processor. The GUI allows manipulation of thresholds applicable to the vision system tool and refinement of training of the vision system tool by the training process.

System and method for applying deep learning tools to machine vision and interface for the same

This invention overcomes disadvantages of the prior art by providing a vision system and method of use, and graphical user interface (GUI), which employs a camera assembly having an on-board processor of low to modest processing power. At least one vision system tool analyzes image data, and generates results therefrom, based upon a deep learning process. A training process provides training image data to a processor remote from the on-board processor to cause generation of the vision system tool therefrom, and provides a stored version of the vision system tool for runtime operation on the on-board processor. The GUI allows manipulation of thresholds applicable to the vision system tool and refinement of training of the vision system tool by the training process. A scoring process allows unlabeled images from a set of acquired and/or stored images to be selected automatically for labelling as training images using a computed confidence score.

A machine vision system located at a user site is programmed from a remote site using a program development system connected via a LAN, WAN, or the Internet. A user application program is developed and tested from the remote location and then downloaded through the network to the machine vision system. Libraries of common software module objects are stored at both locations and used during user program development and implementation in the machine vision system.

Remote machine vision application program development method

An apparatus and method are provided for automatic visual inspection of crescent-shaped wire bonds. The apparatus includes image acquisition means for acquiring an image of a wire and an image of a crescent-shaped wire bond. A search model is used that includes a crescent-modeling portion, and can also advantageously include a wire modeling portion. Search functionality is used to find an image of the crescent-shaped wire bond, using the search model, so as to provide location information regarding the location of the crescent base, and shape-match information regarding the reliability of the found location information. The invention is useful for verifying the correct position of the crescent bond to ensure good electrical contact. In addition, the invention greatly simplifies the task of two other important automated visual inspection steps: wire location and crescent shape determination. Presence/absence of the crescent bond can also be determined using this information.

Apparatus and method for inspecting wirebonds on leads

A machine vision system for inspection of a mark (such as a multi-character mark) on an IC device as shown. The system provides search and defect analysis for the mark, individual characters of the mark, and the foreground and the background of the mark. The system provides for search and defect analysis reports thereof. It includes components for operator training search and defect analysis models for the whole mark, and for automatic training of such models for individual characters of the mark.

Mark quality inspection apparatus and method

A method and apparatus for locating and measuring capillary indentation marks on wire bonded leads by creating a normalized, one-dimensional circumferential projection of a candidate center location in an image of a capillary indentation mark and detecting signals in the one-dimensional circumferential projection that correspond to a predefined pattern. The one-dimensional circumferential projection can be generated and evaluated for a full or a sub-sampled set of candidate center locations according to a number of different methods.

Method and apparatus to locate and measure capillary indentation marks

Method and apparatus for selecting a threshold for use by a boundary tracker to locate a crescent on a bonded lead involves creating a two-dimensional inspection window along the angle of the wire in a post-bond image of a bonded wire in order to generate a one-dimensional projection; generating a one-dimensional projection by summing each column of pixels in the inspection window in the direction of the wire angle and computing an average grey value for each column; and applying an edge-detection to the one-dimensional projection to locate the edges of the wire. If an edge point falls directly in the center of a pixel of the one-dimensional projection, the grey value for that edge point is considered to be the grey value of that pixel. If the edge falls between pixels, the edge's grey value is determined by the fractional pixel position of the edge point in the projection. The grey values of the left and right edge points are averaged and used as the threshold value. For more accurate threshold selection or if reflective stripes or confusing edges are likely to occur in the parts being inspected, the same steps are performed using a clipped difference image of the bonded wire instead of a post-bond image.

Method and apparatus for crescent boundary thresholding on wire-bonded

This invention provides a method and apparatus for automatically inspecting the connection of a wire to a lead on lead frame containing a semiconductor chip or similar device. Using an image processor to locate the general position of a soldered lead in a digitized image, the present invention creates a template of an idealized optical indentation left by a good bond; determines parameters such as wire angle, idealized position and shape thresholds for applying the template; conducts a normalized correlation search of the digitized image; compares the results returned to the parameters and reports the resulting signals generated by this comparison to a host controller or other control module.

Growing community of inventors

West Newton, MA, United States of America

John P Petry, Iii