检索结果-内蒙古大学图书馆

text detection and localization in scene images: a broad review

ARTIFICIAL INTELLIGENCE REVIEW 2021年第6期54卷 4317-4377页

作者： Mahajan, Shilpa Rani, Rajneesh Natl Inst Technol Jalandhar 144011 Punjab India

Nowadays, text detection and localization have gained much popularity in the field of text analysis systems as they pave the way for the number of real-time based applications like mobile transliteration technologies, assistive methods for visually impaired persons, etc. text detection and localization techniques are used to find the position of text area in the *** paper intends to present a broad review in this field as five-fold: (1) comparison of document images with scene images and applications of natural scene images, (2) significant and up-to-date traditional machine learning and deep learning-based approaches for the text detection and localization for different languages, (3) various publicly available benchmarked datasets, (4) comparative analysis for other benchmarked datasets and, (5) related challenges and future scope on the field. The paper summarises some of the potential ways in this field, which can serve as a useful reference for the researchers for future exploration of the area.

关键词： Natural scene images text detection Machine learning Deep learning text localization Benchmarked dataset

来源：评论

学校读者我要写书评

暂无评论

text detection and Recognition in Imagery: A Survey

引用

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE 2015年第7期37卷 1480-1500页

作者： Ye, Qixiang Doermann, David Univ Chinese Acad & Sci Dept Elect Elect & Commun Engn Beijing Peoples R China Univ Maryland Inst Adv Comp Studies College Pk MD 20742 USA

This paper analyzes, compares, and contrasts technical challenges, methods, and the performance of text detection and recognition research in color imagery. It summarizes the fundamental problems and enumerates factors that should be considered when addressing these problems. Existing techniques are categorized as either stepwise or integrated and sub-problems are highlighted including text localization, verification, segmentation and recognition. Special issues associated with the enhancement of degraded text and the processing of video text, multi-oriented, perspectively distorted and multilingual text are also addressed. The categories and sub-categories of text are illustrated, benchmark datasets are enumerated, and the performance of the most representative approaches is compared. This review provides a fundamental comparison and analysis of the remaining problems in the field.

关键词： text detection text localization text recognition survey

来源：评论

学校读者我要写书评

暂无评论

text detection in images using sparse representation with discriminative dictionaries

引用

IMAGE AND VISION COMPUTING 2010年第12期28卷 1590-1599页

作者： Zhao, Ming Li, Shutao Kwok, James Hunan Univ Coll Elect & Informat Engn Changsha 410082 Hunan Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Hong Kong Peoples R China

text detection is important in the retrieval of texts from digital pictures, video databases and webpages. However, it can be very challenging since the text is often embedded in a complex background. In this paper, we propose a classification-based algorithm for text detection using a sparse representation with discriminative dictionaries. First, the edges are detected by the wavelet transform and scanned into patches by a sliding window. Then, candidate text areas are obtained by applying a simple classification procedure using two learned discriminative dictionaries. Finally, the adaptive run-length smoothing algorithm and projection profile analysis are used to further refine the candidate text areas. The proposed method is evaluated on the Microsoft common test set, the ICDAR 2003 text locating set, and an image set collected from the web. Extensive experiments show that the proposed method can effectively detect texts of various sizes, fonts and colors from images and videos. (c) 2010 Elsevier B.V. All rights reserved.

关键词： text detection Sparse representation Discriminative dictionary

来源：评论

学校读者我要写书评

暂无评论

text detection, localization, and tracking in compressed video

引用

SIGNAL PROCESSING-IMAGE COMMUNICATION 2007年第9期22卷 752-768页

作者： Qian, Xueming Liu, Guizhong Wang, Huan Su, Rui Xi An Jiao Tong Univ Sch Elect & Informat Engn Xian 710049 Peoples R China

Video text information plays an important role in semantic-based video analysis, indexing and retrieval. Video texts are closely related to the content of a video. Usually, the fundamental steps of text-based video analysis, browsing and retrieval consist of video text detection, localization, tracking, segmentation and recognition. Video sequences are commonly stored in compressed formats where MPEG coding techniques are often adopted. In this paper, a unified framework for text detection, localization, and tracking in compressed videos using the discrete cosines transform (DCT) coefficients is proposed. A coarse to fine text detection method is used to find text blocks in terms of the block DCT texture intensity information. The DCT texture intensity of an 8 x 8 block of an intra-frame is approximately represented by seven AC coefficients. The candidate text block regions are further verified and refined. The text block region localization and tracking are carried out by virtue of the horizontal and vertical block texture intensity projection profiles. The appearing and disappearing frames of each text line are determined by the text tracking. The final experimental results show the effectiveness of the proposed methods. (c) 2007 Elsevier B.V. All rights reserved.

关键词： text detection DCT coefficient text tracking compressed video text line text localization MPEG

来源：评论

学校读者我要写书评

暂无评论

text detection with Deep Neural Network System Based on Overlapped Labels and a Hierarchical Segmentation of Feature Maps

引用

INTERNATIONAL JOURNAL OF CONTROL AUTOMATION AND SYSTEMS 2019年第6期17卷 1599-1610页

作者： Kim, Hong-Hyun Jo, Jea-Ho Teng, Zhu Kang, Dong-Joong Pusan Natl Univ Sch Mech Engn 2 Busandaehak Ro 63Beon Gil Busan 46241 South Korea Beijing Jiaotong Univ Sch Comp & Informat Technol 3 Shangyuancun Beijing 100044 Peoples R China

This paper proposes a three-level framework to detect texts in a single image. First, a salient feature map of text is extracted using a Fully Convolutional Network (FCN) that achieves good performance in semantic segmentation. Label combination using both boxes of word and characters level is proposed to improve the detection of uneven boundaries of text regions. Second, in the feature map of FCN, the text region has a higher probability value than the background region, and the coordinates in the character area are very close to each other. We segment the text area and the background area by using the characteristics of text feature map with Hierarchical Cluster Analysis (HCA). Finally, we applied a Convolutional Neural Networks (CNN) to classify the candidate text area into text and non-text. In this paper, we used CNN which can classify 4 classes in total by separating the background area and three text classes (one character, two characters, three characters or more). The text detection framework proposed in this paper have shown good performance with ICDAR 2015, and high performance especially in Recall criterion, finding more texts than other algorithms.

关键词： Deep neural netwrok detection framework text detection text localization

来源：评论

学校读者我要写书评

暂无评论

text detection on Natural Images Using Mnemonic Cellular Automata

引用

JOURNAL OF CELLULAR AUTOMATA 2014年第2-3期9卷 183-194页

作者： Zagoris, Konstantinos Pratikakis, Ioannis Democritus Univ Thrace Dept Elect & Comp Engn Visual Comp Grp GR-67100 Xanthi Greece

textual information that resides in natural images is an important knowledge for indexing and retrieval purposes. In this paper, a new approach is proposed using Mnemonic Cellular Automata (m-CA) which strives towards detecting scene text on natural images. Initially, an edge map is calculated and consequently binarized. Then, taking advantage of the Hybrid Cellular Automata (CA) flexibility, the transition rules are changed and are applied in different consecutive steps. Initially, its rules partially depend on Coordinating Logic Filters (CLF) and the majority state. Moreover, in the final steps of the m-CA evolution the update rules are modified as the history of past evolution steps is incorporated into each cell. Experimental work on the ICDAR 2011 Robust Reading Competition dataset shows improved performance.

关键词： Mnemonic cellular automata text detection images

来源：评论

学校读者我要写书评

暂无评论

text detection in natural scene images based on color prior guided MSER

引用

NEUROCOMPUTING 2018年 307卷 61-71页

作者： Zhang, Xiangnan Gao, Xinbo Tian, Chunna Xidian Univ Sch Elect Engn Xian 710071 Shaanxi Peoples R China

In this paper, we focus on text detection in natural scene images which is conducive to content-based wild image analysis and understanding. This task is still an open problem and usually includes two key issues: text candidate extraction and verification. For text candidate extraction, we introduce a color prior to guide the character candidate extraction by Maximally Stable Extremal Region (MSER). The principle of color prior acquirement is to obtain stroke-like textures with modified Stroke Width Transform (SWT), which is based on segmented edges. For text verification, the ideology of deep learning is adopted to distinguish text/non-text candidates. To improve classification accuracy, the results of specific task CNNs are fused. The proposed framework is evaluated on the ICDAR 2013 Robust Reading Competition database. It achieves F-score at 85.87%, which are superior over several state-of-the-art text detection methods. (C) 2018 Elsevier B.V. All rights reserved.

关键词： text detection text candidate extraction Maximally stable extremal region Stroke width transform text verification Deep learning

来源：评论

学校读者我要写书评

暂无评论

text detection, recognition, and script identification in natural scene images: a Review

引用

INTERNATIONAL JOURNAL OF MULTIMEDIA INFORMATION RETRIEVAL 2022年第3期11卷 291-314页

作者： Naosekpam, Veronica Sahu, Nilkanta Indian Inst Informat Technol Guwahati Dept Comp Sci & Engn Gauhati Assam India

text in natural scene images plays a vital role in scene understanding. It contains a rich and abundant amount of valuable semantic information useful in many applications such as analysis of products' labels, autonomous driving, and blind navigation. Consequently, detection, recognition, and identification of scripts of texts present in scene images have recently received massive attention. This paper intends to walk through the advances on the mentioned topics, mainly focusing on the approaches proposed in the last 8-10 years. As per our knowledge, this paper is the first to provide a review on the scene text script identification. We also provide a clear and precise classification between conventional-, deep learning-, and hybrid-based methods, including their advantages and disadvantages. State-of-the-art evaluation metrics, benchmark datasets' characteristics, and performances of the existing methods are also analyzed and discussed. Lastly, we present an insight into potential research directions to complete the review. We hope this review will provide a brief insight for the researchers into scene text understanding.

关键词： text detection text recognition Script identification Scene understanding

来源：评论

学校读者我要写书评

暂无评论

text detection in street level images

引用

PATTERN ANALYSIS AND APPLICATIONS 2013年第4期16卷 519-533页

作者： Fabrizio, Jonathan Marcotegui, Beatriz Cord, Matthieu LRDE EPITA Lab F-94276 Le Kremlin Bicetre France Mines ParisTech CMM Ctr Morphol Math Math & Syst F-77305 Fontainebleau France UPMC Sorbonne Univ Lab LIP6 F-75005 Paris France

text detection system for natural images is a very challenging task in Computer Vision. Image acquisition introduces distortion in terms of perspective, blurring, illumination, and characters which may have very different shape, size, and color. We introduce in this article a full text detection scheme. Our architecture is based on a new process to combine a hypothesis generation step to get potential boxes of text and a hypothesis validation step to filter false detections. The hypothesis generation process relies on a new efficient segmentation method based on a morphological operator. Regions are then filtered and classified using shape descriptors based on Fourier, Pseudo Zernike moments and an original polar descriptor, which is invariant to rotation. Classification process relies on three SVM classifiers combined in a late fusion scheme. Detected characters are finally grouped to generate our text box hypotheses. Validation step is based on a global SVM classification of the box content using dedicated descriptors adapted from the HOG approach. Results on the well-known ICDAR database are reported showing that our method is competitive. Evaluation protocol and metrics are deeply discussed and results on a very challenging street-level database are also proposed.

关键词： text detection text segmentation TMMS Toggle mapping Image classification

来源：评论

学校读者我要写书评

暂无评论

text detection in Scene Images Based on Interest Points

引用

JOURNAL OF INFORMATION PROCESSING SYSTEMS 2015年第4期11卷 528-537页

作者： Minh Hieu Nguyen Lee, Gueesang FTP Univ Software Engn Hanoi Vietnam Chonnam Natl Univ Dept Elect & Comp Engn Gwangju South Korea

text in images is one of the most important cues for understanding a scene. In this paper, we propose a novel approach based on interest points to localize text in natural scene images. The main ideas of this approach are as follows: first we used interest point detection techniques, which extract the corner points of characters and center points of edge connected components, to select candidate regions. Second, these candidate regions were verified by using tensor voting, which is capable of extracting perceptual structures from noisy data. Finally, area, orientation, and aspect ratio were used to filter out non-text regions. The proposed method was tested on the ICDAR 2003 dataset and images of wine labels. The experiment results show the validity of this approach.

关键词： Connected Component Interest Point Tensor Voting text detection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：