View source for 17960729. PATTERN RECOGNITION FOR IDENTIFYING INDISTINCT ENTITIES simplified abstract (INTERNATIONAL BUSINESS MACHINES CORPORATION)

=PATTERN RECOGNITION FOR IDENTIFYING INDISTINCT ENTITIES=


==Organization Name==

[[:Category:INTERNATIONAL BUSINESS MACHINES CORPORATION|INTERNATIONAL BUSINESS MACHINES CORPORATION]]


[[Category:INTERNATIONAL BUSINESS MACHINES CORPORATION]]

==Inventor(s)==

[[:Category:Rajesh Kumar Saxena of Thane East (IN)|Rajesh Kumar Saxena of Thane East (IN)]][[Category:Rajesh Kumar Saxena of Thane East (IN)]]

[[:Category:Harish Bharti of Pune (IN)|Harish Bharti of Pune (IN)]][[Category:Harish Bharti of Pune (IN)]]

[[:Category:Pinaki Bhattacharya of Pune (IN)|Pinaki Bhattacharya of Pune (IN)]][[Category:Pinaki Bhattacharya of Pune (IN)]]

[[:Category:Sandeep Sukhija of Rajasthan (IN)|Sandeep Sukhija of Rajasthan (IN)]][[Category:Sandeep Sukhija of Rajasthan (IN)]]

[[:Category:Dinesh Wadekar of Pune (IN)|Dinesh Wadekar of Pune (IN)]][[Category:Dinesh Wadekar of Pune (IN)]]

==PATTERN RECOGNITION FOR IDENTIFYING INDISTINCT ENTITIES - A simplified explanation of the abstract==


This abstract first appeared for US patent application 17960729 titled 'PATTERN RECOGNITION FOR IDENTIFYING INDISTINCT ENTITIES

==Simplified Explanation==

The patent application describes a method for identifying an indistinct entity within an image using image filters, gradients, and machine learning models.

* Image filters are used to generate multiple gradients corresponding to pixels in the image.
* A likely repeating pattern is searched for within the image based on the gradients.
* Data structures are created with probabilistically weighted feature vectors representing the repeating pattern.
* A machine learning model classifies the feature vectors to determine the identity of the repeating pattern.

== Potential Applications ==
This technology could be applied in various fields such as image recognition, pattern detection, and object identification in images.

== Problems Solved ==
This technology helps in identifying indistinct entities within images, which can be challenging for traditional image processing techniques.

== Benefits ==
The method provides a more accurate and efficient way to identify repeating patterns or entities within images.
It can improve the performance of image recognition systems and enhance the quality of image analysis.

== Potential Commercial Applications ==
Potential commercial applications of this technology include automated image analysis systems, security and surveillance systems, and medical imaging technologies.

== Possible Prior Art ==
One possible prior art could be the use of image filters and machine learning models in image recognition and pattern detection applications.

=== What are the specific types of image filters used in this method? ===

The specific types of image filters used in this method are not mentioned in the abstract. It would be helpful to know the exact filters used and how they contribute to generating the gradients for pattern detection.

=== How does the machine learning model classify the probabilistically weighted feature vectors? ===

The abstract does not provide details on how the machine learning model classifies the feature vectors. Understanding the classification process could shed light on the accuracy and reliability of the method.


==Original Abstract Submitted==

Identifying an indistinct entity within an image can include generating by an image filter multiple gradients, each of which corresponds to one of a plurality of pixels of an image captured by an imager. The image can be searched for a likely repeating pattern. Responsive to detecting, based on the multiple gradients, a likely repeating pattern within the image, data structures can be generated, the data structures comprising a set of probabilistically weighted feature vectors corresponding to the likely repeating pattern. A machine learning model can classify each of the set of probabilistically weighted feature vectors. An identity of the likely repeating pattern can be output, the identity based on the machine learning model classifications of the probabilistically weighted feature vectors.



[[Category:G06V10/764]]