scispace - formally typeset
Book ChapterDOI

Real-Time Prototype of Driver Assistance System for Indian Road Signs

Karattupalayam Chidambaram Saranya, +1 more
- pp 147-155
Reads0
Chats0
TLDR
A system for the detection and recognition of road signs in real time (tested for Indian road signs) that is invariant to scale, angle, blur extent, and variation in lighting condition.
Abstract: 
The paper presents a system for the detection and recognition of road signs in real time (tested for Indian road signs). The detection and recognition algorithm used is invariant to scale, angle, blur extent, and variation in lighting condition. Shape classification of road signs using Hu moments is done in order to categorize signs as either warning, mandatory, prohibitory or informational. Classified road signs are then matched to ideal road signs using feature extraction, and the matching is done with the help of Oriented FAST and Rotated BRIEF (ORB) descriptors. After recognition, the driver is given a feedback.

read more

Citations
More filters
Journal ArticleDOI

Recognition of cursive video text using a deep learning framework

Ali Mirza, +1 more
- 01 Dec 2020 - 
TL;DR: In this article, the authors presented an analytical technique for recognition of cursive caption text that relies on a combination of convolutional and recurrent neural networks trained in an end-to-end framework.
Book ChapterDOI

Impact of Pre-Processing on Recognition of Cursive Video Text

Ali Mirza, +3 more
TL;DR: Experimental study on a dataset of 12,000 text lines in cursive Urdu text reveals that appropriately pre-processing the text line images significantly improves the recognition rates.
Journal ArticleDOI

Detection and recognition of cursive text from video frames

Ali Mirza, +3 more
- 01 Dec 2020 - 
TL;DR: This paper presents a comprehensive framework for detection and recognition of textual content in video frames, and proposes a UrduNet, a combination of CNNs and long short- term memory (LSTM) networks.
Book ChapterDOI

Extracting Multi-Language Text from Video into Editable Form

Stephen Platten
TL;DR: In this paper , a case study about all types of the framework for text recognition and segmentation in video frames is presented, focusing on cursive scripts, in particular, using English text as an example.
References
More filters
Proceedings ArticleDOI

Object recognition from local scale-invariant features

David G. Lowe
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Book ChapterDOI

SURF: speeded up robust features

Herbert Bay, +2 more
TL;DR: A novel scale- and rotation-invariant interest point detector and descriptor, coined SURF (Speeded Up Robust Features), which approximates or even outperforms previously proposed schemes with respect to repeatability, distinctiveness, and robustness, yet can be computed and compared much faster.
Proceedings ArticleDOI

ORB: An efficient alternative to SIFT or SURF

Ethan Rublee, +3 more
TL;DR: This paper proposes a very fast binary descriptor based on BRIEF, called ORB, which is rotation invariant and resistant to noise, and demonstrates through experiments how ORB is at two orders of magnitude faster than SIFT, while performing as well in many situations.
Journal ArticleDOI

Visual pattern recognition by moment invariants

Ming-Kuei Hu
- 01 Feb 1962 - 
TL;DR: It is shown that recognition of geometrical patterns and alphabetical characters independently of position, size and orientation can be accomplished and it is indicated that generalization is possible to include invariance with parallel projection.
Proceedings ArticleDOI

A non-local algorithm for image denoising

Antoni Buades, +2 more
TL;DR: A new measure, the method noise, is proposed, to evaluate and compare the performance of digital image denoising methods, and a new algorithm, the nonlocal means (NL-means), based on a nonlocal averaging of all pixels in the image is proposed.