Company Filing History:
Years Active: 1991-1992
Title: Innovations of Hin-Leong Tan
Introduction
Hin-Leong Tan is a notable inventor based in Rochester, NY (US). He has made significant contributions to the field of optical character recognition, holding a total of 5 patents. His work focuses on improving the efficiency and accuracy of character segmentation processes.
Latest Patents
One of his latest patents is titled "Fast character segmentation of skewed text lines for optical character." This invention presents a character segmentation process for skewed documents that divides the document bitmap into vertical blocks. Within each vertical block, it estimates the initial top and bottom bounds of each character in a character row from horizontal projections, effectively avoiding the effects of skew. The operations in the document bitmap to compute the exact boundaries of the character are confined within a narrow strip, which greatly reduces the amount of data fetched from memory and speeds up the segmentation process.
Another significant patent is "Row-by-row segmentation and thresholding for optical character." This invention predicts an optimal minimum gray level sensitivity threshold for the next character while scanning pixel rows between characters. It lowers the threshold unless noise in the image causes the scanner to detect too many 'ON' pixels between adjacent numerals. During subsequent attempts to recognize the segmented character, the invention computes a confidence score and adjusts the sensitivity threshold accordingly.
Career Highlights
Hin-Leong Tan is currently employed at Eastman Kodak Company, where he continues to innovate in the field of optical character recognition. His work has been instrumental in advancing the technology used in document processing and recognition.
Collaborations
He has collaborated with notable coworkers such as Lori L Barski and Roger S Gaborski, contributing to various projects and innovations within the company.
Conclusion
Hin-Leong Tan's contributions to optical character recognition through his patents demonstrate his commitment to innovation and technology advancement. His work continues to influence the field and improve the efficiency of character segmentation processes.