Spectral Fluctuation Method : A Texture-Based Method to Extract Text Regions in General Scene Images
スポンサーリンク
概要
- 論文の詳細を見る
To obtain text information included in a scene image, we first need to extract text regions from the image before recognizing the text. In this paper, we examine human vision and propose a novel method to extract text regions by evaluating textural variation. Human beings are often attracted by textural variation in scenes, which causes foveation. We frame a hypothesis that texts also have similar property that distinguishes them from the natural background. In our method, we calculate spatial variation of texture to obtain the distribution of the degree of likelihood of text region. Here we evaluate the changes in local spatial spectrum as the textural variation. We investigate two options to evaluate the spectrum, that is, those based on one- and two-dimensional Fourier transforms. In particular, in this paper, we put emphasis on the one-dimensional transform, which functions like the Gabor filter. The proposal can be applied to a wide range of characters mainly because it employs neither templates nor heuristics concerning character size, aspect ratio, specific direction, alignment, and so on. We demonstrate that the method effectively extracts text regions contained in various general scene images. We present quantitative evaluation of the method by using databases open to the public.
- (社)電子情報通信学会の論文
- 2009-09-01
著者
-
Baba Yoichiro
Department Of Electronic Engineering The University Of Tokyo
-
Hirose Akira
Department Of Electronic Engineering The University Of Tokyo
-
Hirose Akira
Department Of Electrical Engineering The University Of Tokyo
関連論文
- Choroidal Vascular Lesions Identified by ICG Angiography in a Case of Familial Amyloidotic Polyneuropathy
- In early-stage diabetic retinopathy, risk of cardiac events after implantation of sirolimus-eluting stent is higher than after coronary artery bypass surgery
- Adaptive Plastic-Landmine Visualizing Radar System : Effects of Aperture Synthesis and Feature-Vector Dimension Reduction(Imaging, Wireless Technologies and Computational Electromagnetics)
- Ultrasonic Imaging for Boundary Shape Generation by Phase Unwrapping with Singular-Point Elimination Based on Complex-Valued Markov Random Field Model
- Spectral Fluctuation Method : A Texture-Based Method to Extract Text Regions in General Scene Images
- Improvement of Plastic Landmine Visualization Performance by Use of Ring-CSOM and Frequency-Domain Local Correlation
- Search Control Algorithm Based on Random Step Size Hill-Climbing Method for Adaptive PMD Compensation
- Plastic mine detecting radar system using complex-valued self-organizing map that deals with multiple-frequency interferometric images
- Risk of Retinal Detachment in Patients with Lattice Degeneration
- Phase Locking and Unlocking Associated with Transition to Quasi-Single Helicity State in the RELAX Reversed-Field Pinch
- Inhibitory effects of L-threo-DOPS, an L-noradrenaline precursor, on locus coeruleus-originating neurons in the caudate nucleus.
- Angiotensinogen gene haplotype is associated with the prevalence of Japanese non-alcoholic steatohepatitis
- Usefulness of Technetium-99 m-2-methoxy-isobutyl-isonitrile liver scintigraphy for evaluating disease activity of non-alcoholic fatty liver disease