Fast text line detection by finding linear connected components on Canny edge image

The traditional Canny edge detection algorithm is analyzed in this paper. To overcome the difficulty of threshold selecting in Canny algorithm, an improved method based on Otsu algorithm and mathematical morphology is proposed to choose the threshold adaptively and simultaneously. This method applies the improved Canny operator and the image morphology separately to image edge detection, and then performs image fusion of the two results using the wavelet fusion technology to obtain the final edge-image. Simulation results show that the proposed algorithm has better anti-noise ability and effectively enhances the accuracy of image edge detection.

Download Full-text

Reversible Data Hiding Scheme Using Adaptive Block Truncation Coding Based on an Edge-Based Quantization Approach

Symmetry ◽

10.3390/sym11060765 ◽

2019 ◽

Vol 11 (6) ◽

pp. 765 ◽

Cited By ~ 7

Author(s):

Chia-Chen Lin ◽

Ching-Chun Chang ◽

Zhi-Ming Wang

Keyword(s):

Data Hiding ◽

Reversible Data Hiding ◽

Zero Point ◽

Edge Image ◽

Block Truncation Coding ◽

Canny Edge ◽

High Embedding Capacity ◽

Processing Block ◽

And Performance ◽

Edge Based

In this paper, we provide a novel reversible data hiding method using adaptive block truncation coding based on an edge-based quantization (ABTC-EQ) approach. We exploit the characteristic not being used in ABTC-EQ. To accomplish this, we first utilized a Canny edge detector to obtain an edge image and classify each block in a cover image into two versions, edge-block and non-edge-block. Subsequently, k-means clustering was used to obtain three quantization levels and derive the corresponding bit map while the current processing block was the case of an edge-block. Then Zero-Point Fixed Histogram Shifting (ZPF-HS) was applied to embed the secret information into compressed code. The experimental results show that our method provides a high embedding capacity for each test image and performance is better than other methods.

Download Full-text

Fast and Lightweight Text Line Detection on Historical Documents

Document Analysis Systems - Lecture Notes in Computer Science ◽

10.1007/978-3-030-57058-3_31 ◽

2020 ◽

pp. 441-450

Author(s):

Aleksei Melnikov ◽

Ivan Zagaynov

Keyword(s):

Line Detection ◽

Historical Documents ◽

Text Line

Download Full-text

Text line detection based on cost optimized local text line direction estimation

10.1117/12.2083709 ◽

2015 ◽

Cited By ~ 1

Author(s):

Yandong Guo ◽

Yufang Sun ◽

Peter Bauer ◽

Jan P. Allebach ◽

Charles A. Bouman

Keyword(s):

Line Detection ◽

Text Line ◽

Direction Estimation ◽

Line Direction

Download Full-text

Polynomial Interpolation Sub-Pixel Edge Detection Method Based on Improved Canny Operator

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.563.203 ◽

2014 ◽

Vol 563 ◽

pp. 203-207

Author(s):

Kun Lin Yu ◽

Zhi Yu Xie

Keyword(s):

Edge Detection ◽

Detection Method ◽

Polynomial Interpolation ◽

Detection Algorithm ◽

Edge Image ◽

Canny Operator ◽

Edge Detection Algorithm ◽

Canny Edge ◽

Image Edge ◽

Edge Detection Method

According to the shortcoming of traditional Canny edge detection algorithm is sensitive to noise and low positioning accuracy, this paper proposes an algorithm of Polynomial interpolation Sub-pixel edge detection based on improved Canny operator: We first use improved Canny operator edge detection algorithm to extract rough image edge, then use the quadratic Polynomial interpolation to calculate on the rough extraction edge, finally refine the edge image. Experiments show that the improved method is better than the traditional detection method can accurately locate the image edge.

Download Full-text