Belmont, CA, United States of America

Shubham Agarwal

This inventor holds 4 USPTO granted patents and 2 published patent applications. Top assignee: Konica Minolta Laboratory U.s.a., Inc.. Active years: 2019.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Shubham Agarwal. Retrieved from https://idiyas.com/inventor/shubham-agarwal-upjj34ao

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 4 

% Patents Active = 75.0

Average Co-Inventor Count = 2.4

ph-index = 3

Forward Citations = 13(Granted Patents)


Company Filing History:


Years Active: 2019

Loading Chart...
4 patents (USPTO):Explore Patents

Title: Shubham Agarwal: Innovator in Optical Character Recognition

Introduction

Shubham Agarwal is a notable inventor based in Belmont, CA (US). He has made significant contributions to the field of optical character recognition (OCR) through his innovative patents. With a total of 4 patents, Agarwal's work focuses on enhancing the accuracy and efficiency of text recognition technologies.

Latest Patents

One of Agarwal's latest patents is titled "Local connectivity feature transform of binary images containing text characters for optical character/word recognition." This invention applies a local connectivity feature transform (LCFT) to binary document images containing text characters. The transformed images are then input into a bi-directional Long Short Term Memory (LSTM) neural network for character and word recognition. The LCFT transformed image is a grayscale image where pixel values encode local pixel connectivity information from the original binary image. The transform provides a unique score for every possible shape represented as a 3×3 block.

Another significant patent is "Text image processing using stroke-aware max-min pooling for OCR system employing artificial neural network." This method digitizes printed text images using an LSTM network. Text images are pre-processed with a stroke-aware max-min pooling method before being fed into the network for both training and prediction. During training, an average stroke thickness is computed, and pooling is applied based on the stroke thickness of the text line images.

Career Highlights

Shubham Agarwal is currently employed at Konica Minolta Laboratory U.S.A., Inc. His work at this company has allowed him to develop and refine his innovative approaches to OCR technology. His contributions have been instrumental in advancing the capabilities of text recognition systems.

Collaborations

Agarwal has collaborated with notable coworkers, including Yongmian Zhang and Maral Mesmakhosroshahi. These collaborations have fostered a productive environment for innovation and development in the field of optical character recognition.

Conclusion

Shubham Agarwal's contributions to optical character recognition through his patents and work at Konica Minolta Laboratory U.S.A., Inc. highlight his role as a significant innovator in this field. His advancements in text recognition technology continue to influence the industry positively.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…