Text Area Identification For Recognizing Destination Places From Vehicles

K. S., SELVANAYAKI (2014) Text Area Identification For Recognizing Destination Places From Vehicles. In: International Conference on Advances In Engineering And Technology - ICAET 2014, 24 - 25 May, 2014, RIT, Roorkee, India.

[img]
Preview
Text
20140726_112455.pdf - Published Version

Download (1MB) | Preview
Official URL: https://www.seekdl.org/conferences/paper/details/3...

Abstract

Nowadays, automatic detection of text from the vehicles is an important problem in many applications. Text information present in an image can be easily understood by both human and computer. It has wide applications such as license plate reading, sign detection, identification of destination places, mobile text recognition and so on. This problem is challenging due to complex backgrounds, the non-uniform illuminations, variations of text font, size and line orientation. Once the text is identified, it can be analyzed, recognized and interpreted. Hence, there is a need for a better algorithm for detection and localization of text from vehicles. A method is proposed for detecting text from vehicles. The method makes use of features such as Histogram of oriented Gradients (HOG) and Local Binary Pattern (LBP). These features are stored which can be further used for feature matching at the time of classification. After the text region is being detected, it can be further subjected to character segmentation and recognition thereby identifying the destination places. The ability to recognize text area from the vehicles, especially buses has obvious applications like traffic management in the bus stands. The obtained results are verified and performance parameters like speed, precision and recall are determined.

Item Type: Conference or Workshop Item (Paper)
Uncontrolled Keywords: HOG, LBP, Profile based features, Skew detection and removal, Eigen value regularization
Depositing User: Mr. John Steve
Date Deposited: 27 May 2019 04:42
Last Modified: 27 May 2019 04:42
URI: http://publications.theired.org/id/eprint/2722

Actions (login required)

View Item View Item