Research on Character Segmentation Method in Image Text Recognition

2012 ◽  
Vol 546-547 ◽  
pp. 1345-1350
Author(s):  
Lian Huan Li
Keyword(s):  
Real Time ◽  
Projection Method ◽  
Segmentation Algorithm ◽  
Character Segmentation ◽  
Text Recognition ◽  
Segmentation Method ◽  
Correction Algorithm ◽  
Vertical Projection ◽  
Tilt Correction ◽  
Single Character

Character Segmentation is the key step for image text recognition. This paper presents a text tilt correction algorithm using tracked characteristics rectangle contour to extract angle, using line scan method based on the number of transitions to determine the character on the bottom. In order to meet the requirements of real-time and reliability, takes improved secondary single-character segmentation algorithm based on vertical projection method.

scholarly journals Character Segmentation in Asian Collector's Seal Imprints: An Attempt to Retrieval Based on Ancient Character Typeface

2021 ◽  
Vol HistoInformatics (HistoInformatics) ◽  
Author(s):  
Kangying Li ◽  
Biligsaikhan Batjargal ◽  
Akira Maeda
Keyword(s):  
User Interaction ◽  
Recognition System ◽  
Essential Elements ◽  
Character Segmentation ◽  
Training Data ◽  
Background Information ◽  
Segmentation Method ◽  
Single Character ◽  
Degraded Images ◽  
Standard Character

Collector's seals provide important clues about the ownership of a book. They contain much information pertaining to the essential elements of ancient materials and also show the details of possession, its relation to the book, the identity of the collectors and their social status and wealth, amongst others. Asian collectors have typically used artistic ancient characters rather than modern ones to make their seals. In addition to the owner's name, several other words are used to express more profound meanings. A system that automatically recognizes these characters can help enthusiasts and professionals better understand the background information of these seals. However, there is a lack of training data and labelled images, as samples of some seals are scarce and most of them are degraded images. It is necessary to find new ways to make full use of such scarce data. While these data are available online, they do not contain information on the characters' position. The goal of this research is to assist in obtaining more labelled data through user interaction and provide retrieval tools that use only standard character typefaces extracted from font files. In this paper, a character segmentation method is proposed to predict the candidate characters' area without any labelled training data that contain character coordinate information. A retrieval-based recognition system that focuses on a single character is also proposed to support seal retrieval and matching. The experimental results demonstrate that the proposed character segmentation method performs well on Asian collector's seals, with 85% of the test data being correctly segmented.

Research of the SMT Product Character Segmentation Based on Contour Feature

2011 ◽  
Vol 201-203 ◽  
pp. 2019-2022
Author(s):  
Hui Huang Zhao ◽  
De Jian Zhou ◽  
Yu Ming Xu
Keyword(s):  
Image Processing ◽  
Segmentation Algorithm ◽  
Character Segmentation ◽  
Surface Mount Technology ◽  
Binary Images ◽  
Image Sampling ◽  
The Third ◽  
Single Character ◽  
Contour Feature ◽  
Test Result

The principles of the Surface Mount Technology (SMT) product character segmentation and its technology could be described as following: SMT product character image is obtained by image sampling equipment and its ideal binary images is got after image processing. In order to segment the SMT product character effectively, a novel character segmentation algorithm is proposed based on contour feature. Three kinds of information are extracted, one is the up contour feature, another is the under contour feature, the third is the width and the height of the image. Then the position of character segmentation is determined according to the width and height of single character, and character segmentation can be accomplish according to its up contour feature and under contour feature. By analyzing the test result, the proposed approach has excellent properties in character segmentation.

Plate Character Segmentation Algorithm Based on Projection Feature and Prior Knowledge

2013 ◽  
Vol 790 ◽  
pp. 677-681
Author(s):  
Jun Liu ◽  
Jun Xiang ◽  
Chun Long Xu
Keyword(s):  
Prior Knowledge ◽  
High Efficiency ◽  
Segmentation Algorithm ◽  
Character Segmentation ◽  
Vertical Projection ◽  
Horizontal Projection ◽  
Local Projection

nfluenced by factors like mud, frame, rivet, space mark and plate slant, plate character segmentation tends to be inaccurate and even results in mistakes. In order to tackle these problems, this paper puts forward a plate character segmentation algorithm based on projection feature and prior knowledge. That is, firstly of all, to carry out horizontal coarse segmentation by horizontal projection, then use both vertical projection and prior knowledge to conduct vertical segmentation. At last, to carry out horizontal fine segmentation by local projection. The experiment demonstrates that such algorithm can solve the above mentioned problems accurately and practically with high-efficiency.

Tilt correction algorithm based on aggregation of grating projection sequences

2013 ◽  
Vol 33 (11) ◽  
pp. 3209-3212
Author(s):  
Xu LIU ◽  
Ling WU ◽  
Niannian CHEN ◽  
Yong FAN ◽  
Jingjing DUAN ◽  
...  
Keyword(s):  
Correction Algorithm ◽  
Tilt Correction

scholarly journals Real-Time Instance Segmentation of Traffic Videos for Embedded Devices

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 275
Author(s):  
Ruben Panero Martinez ◽  
Ionut Schiopu ◽  
Bruno Cornelis ◽  
Adrian Munteanu
Keyword(s):  
Real Time ◽  
Network Architecture ◽  
Training Procedure ◽  
Segmentation Method ◽  
Embedded Devices ◽  
Network Training ◽  
Assignment Algorithm ◽  
Ablation Study ◽  
Reduced Rate ◽  
Instance Segmentation

The paper proposes a novel instance segmentation method for traffic videos devised for deployment on real-time embedded devices. A novel neural network architecture is proposed using a multi-resolution feature extraction backbone and improved network designs for the object detection and instance segmentation branches. A novel post-processing method is introduced to ensure a reduced rate of false detection by evaluating the quality of the output masks. An improved network training procedure is proposed based on a novel label assignment algorithm. An ablation study on speed-vs.-performance trade-off further modifies the two branches and replaces the conventional ResNet-based performance-oriented backbone with a lightweight speed-oriented design. The proposed architectural variations achieve real-time performance when deployed on embedded devices. The experimental results demonstrate that the proposed instance segmentation method for traffic videos outperforms the you only look at coefficients algorithm, the state-of-the-art real-time instance segmentation method. The proposed architecture achieves qualitative results with 31.57 average precision on the COCO dataset, while its speed-oriented variations achieve speeds of up to 66.25 frames per second on the Jetson AGX Xavier module.

Neuro-inspired system for real-time vision sensor tilt correction

2010 ◽  
Author(s):  
A. Jimenez-Fernandez ◽  
J.L. Fuentes-del-Bosh ◽  
R. Paz-Vicente ◽  
A. Linares-Barranco ◽  
G. Jimenez
Keyword(s):  
Real Time ◽  
Vision Sensor ◽  
Tilt Correction

A character segmentation algorithm for mixed-mode communication

1985 ◽  
Vol 16 (4) ◽  
pp. 66-75 ◽  
Author(s):  
Osamu Nakamura ◽  
Makoto Ujiie ◽  
Noriyoshi Okamoto ◽  
Toshi Minami
Keyword(s):  
Mixed Mode ◽  
Segmentation Algorithm ◽  
Character Segmentation
Sign in / Sign up

Export Citation Format

Share Document