A Unified Framework for Multioriented Text Detection and Recognition
Top Cited Papers
- 4 September 2014
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 23 (11), 4737-4749
- https://doi.org/10.1109/tip.2014.2353813
Abstract
High level semantics embodied in scene texts are both rich and clear and thus can serve as important cues for a wide range of vision applications, for instance, image understanding, image indexing, video search, geolocation, and automatic navigation. In this paper, we present a unified framework for text detection and recognition in natural images. The contributions of this paper are threefold: 1) text detection and recognition are accomplished concurrently using exactly the same features and classification scheme; 2) in contrast to methods in the literature, which mainly focus on horizontal or near-horizontal texts, the proposed system is capable of localizing and reading texts of varying orientations; and 3) a new dictionary search method is proposed, to correct the recognition errors usually caused by confusions among similar yet different characters. As an additional contribution, a novel image database with texts of different scales, colors, fonts, and orientations in diverse real-world scenarios, is generated and released. Extensive experiments on standard benchmarks as well as the proposed database demonstrate that the proposed system achieves highly competitive performance, especially on multioriented texts.Keywords
Funding Information
- National Natural Science Foundation of China (61222308, 61173120)
- Program for New Century Excellent Talents in University (NCET-12-0217)
- Fundamental Research Funds for the Central Universities (HUST 2013TS115)
- CCF-Tencent Project (AGR2014)
This publication has 56 references indexed in Scilit:
- Robust Subspace Discovery via Relaxed Rank MinimizationNeural Computation, 2014
- Human Detection Using Learned Part Alphabet and Pose DictionaryLecture Notes in Computer Science, 2014
- Scene Text Localization and Recognition with Oriented Stroke DetectionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- On Combining Multiple Segmentations in Scene Text RecognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Image Binarization for End-to-End Text Understanding in Natural ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Scene Text Detection via Connected Component Clustering and Nontext FilteringIEEE Transactions on Image Processing, 2013
- Scene text detection using graph model built upon maximally stable extremal regionsPattern Recognition Letters, 2013
- Text Detection in Natural Scene Images by Stroke Gabor WordsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2011
- Textfinder: an automatic system to detect and recognize text in imagesIEEE Transactions on Pattern Analysis and Machine Intelligence, 1999
- AUTOMATIC TEXT LOCATION IN IMAGES AND VIDEO FRAMESPattern Recognition, 1998