Lucent Technologies Inc.

Other

Muid Ur-Rehman Mufti

Andrei Csipkes

John Mark Palmquist

George J Vachtsevanos

J Lewis Dorrity

A segment detection system automatically, contactlessly, rapidly, and precisely detects a segment along an edge, such as a boundary, of an object in a digitized image. The segment detection system includes an imager for capturing an image of an object and converting the image into an electrical signal. A computer is connected to the camera for receiving the electrical signal. A machine vision system is associated with the computer and is adapted to analyze the image. A segment detection program is disposed in the computer for driving the computer and the machine vision system in accordance with the present invention. The segment detection program includes an initialization subroutine and a matching subroutine. The initialization subroutine configures the program to search for a particular target polynomial equation. The matching subroutine derives a test polynomial equation that represents a test segment from a test edge of the object based upon an analysis of the image. Further, the matching subroutine determines whether the test segment matches the target segment by comparing corresponding coefficients of the test polynomial equation and the target polynomial equation.

Segment detection system and method

The Invention includes a method and apparatus which analyzes an image of an object to detect and identify defects in the object. The present invention utilizes a scanning technique which converts a 2-D image of the object into a 1-D image, a transformation technique which extracts relevant features from the image, and a fuzzy inferencing technique which utilizes the features generated by the transformation technique to detect and identify defects. The present invention preferably includes an off-line learning process which selects the optimum transform coefficients for a given set of defects and stores the corresponding features in a rulebase. Preferably, the wavelet transform is used as the transformation technique to provide an analysis of the image which is localized in the frequency and time domains. The present invention may also include an on-line learning process when the present invention is incorporated into a manufacturing process for real time inspection of the object being manufactured. The on-line learning process attempts to nullify the effects of noise which may be associated with the image sensors being used to read the image by using a similarity function to maintain a predetermined level of fuzziness of the inference engine of the present invention.

Method and apparatus for analyzing an image to detect and identify

A surface analysis system can contactlessly, automatically, and rapidly detect, classify, and evaluate a surface of an object, particularly, an optical fiber end face, for discontinuities to derive a single pass/fail conclusion regarding the surface. The surface analysis system has a scope for capturing an image of the end face. A computer is connected to the scope. A machine vision system is associated with the computer for receiving the image. A surface analysis program is associated with the computer for driving the machine vision system. The program searches for any discontinuities in the image by analyzing each pixel and a corresponding pixel structure of pixels to determine whether a discontinuity resides at each pixel. Discontinuities are classified as one of the following: binary thresholds, local gradients, and directional gradients. The pixel structure includes a plurality of pixels that were previously analyzed. The program determines whether the surface is continuous based upon any discovered discontinuities.

Growing community of inventors

Atlanta, GA, United States of America

Muid Ur-Rehman Mufti