The following operators can be used to better focus your queries.
( ) , AND, OR, NOT, W/#
? single char wildcard, not at start
* multi char wildcard, not at start
(Cat? OR feline) AND NOT dog?
Cat? W/5 behavior
(Cat? OR feline) AND traits
Cat AND charact*
This guide provides a more detailed description of the syntax that is supported along with examples.
This search box also supports the look-up of an IP.com Digital Signature (also referred to as Fingerprint); enter the 72-, 48-, or 32-character code to retrieve details of the associated file or submission.
Concept Search - What can I type?
For a concept search, you can enter phrases, sentences, or full paragraphs in English. For example, copy and paste the abstract of a patent application or paragraphs from an article.
Concept search eliminates the need for complex Boolean syntax to inform retrieval. Our Semantic Gist engine uses advanced cognitive semantic analysis to extract the meaning of data. This reduces the chances of missing valuable information, that may result from traditional keyword searching.
There is disclosed an interactive method for determining object recognition windows in vision assisted robotic applications.
English (United States)
This text was extracted from a PDF file.
100% of the total text.
Page 1 of 1
Statistical Determination of Recognition Windows
There is disclosed an interactive method for determining object recognition
windows in vision assisted robotic applications.
To enable automated distinction of one object from another, it is necessary to
describe parameters to the system particular to a given object. Typical
parameters include area perimeter as well as aspect ratio. These parameters
are easily obtainable for a particular picture of an object. As the object, however,
is moved within the field of view, recognition parameters undergo changes. Since
it is desired to recognize an object in any position and orientation, upper and
lower limits, windows, on each of these parameters are required.
The present method requires ten photographs of an object. Each photograph
is analyzed by the system to determine which of several objects in the
photographic image is the desired image. The system then displays a box
around the most likely object. If the system chosen object is incorrect, the user is
able to move the box. When this iterative process is complete, recognition
parameters for the object are recorded. Once recorded, the system performs
statistical calculations yielding a 99.9% confidence interval.
Use of this technique enables high quality inspection applications for
improperly installed assemblies or parts rejected for defects. This ability enables
system development for applications where minimum human intervention is