Abstract
In the paper, we proposed a coarse-to-fine scheme to automatically detect the regions of interest (ROIs) for digitized cadastral images in Taiwan. To consider some issues such as the skew effect, image quality, and noise in digitized cadastral images, the proposed scheme is composed of four parts: pre-processing, skew correction, noise reduction, and ROI localization. In the pre-processing, each cadastral image is normalized and the prior knowledge is used to find the candidate region of the ROI. To reduce the impact of noise and poor contrast on line detection, an adaptive thresholding is adopted. To decrease the skew effect, the detected horizontal and vertical lines are analyzed to estimate the skew angle. After skew correction, an adaptive noise reduction algorithm is devised to reduce the effect of marginal, artificial, and random noise. The coordinates of the candidate region in the de-skew image with high resolution can be found and then the ROI boundary can be located correctly in the fine detection. Experimental results demonstrate that the proposed scheme can effectively and correctly localize ROIs in digitized cadastral images.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alaei A, Nagabhushan P, Pal U, Kimura F (2016) An efficient skew estimation technique for scanned documents: an application of piece-wise painting algorithm. J Pattern Recognit Res 11(1):1–14
Chou CH, Chu SY, Chang F (2007) Estimation of skew angles for scanned documents based on piecewise covering by parallelograms. Pattern Recogn 40:443–455
Farahmand A, Sarrafzadeh A, Shanbehzadeh J (2013) Document image noises and removal methods. International MultiConference of Engineering and Computer Scientists 1:5
Hull JJ (1998) Document image skew detection: survey and annotated bibliography. Document Analysis Systems II 40–64. doi:10.1142/9789812797704_0003
Lin GS, Ji XW (2016) Video Quality Enhancement Based on Visual Attention Model and Multi-level Exposure Correction. Multimed Tools Appl 9903–9925
Lin H, Si J, Abousleman GP (2007) Region-of-interest detection and its application to image segmentation and compression. Proc. of International Conference on Integration of Knowledge Intensive Multi-Agent Systems, pp 306–311
Lin GS, Chang MK, Chiu ST (2009) A feature-based scheme for detecting and classifying video-shot transitions based on spatio-temporal analysis and fuzzy classification. Int J Pattern Recognit Artif Intell 23(6):1179–1200
Lin GS, Chang MK, Chen YL (2011) A passive-blind scheme for image forgery detection based on content-adaptive quantization table estimation. IEEE Trans Circuits Syst Video Technol 21(4):421–434
Lin GS, Chai SK, Yeh WC, Lin YC (2014) Suspicious region detection and identification based on intra−/inter-frame analyses and fuzzy classifier for breast magnetic resonance imaging. Int J Pattern Recognit Artif Intell 28(3):1–26
Rezaei SB, Sarrafzadeh A, Shanbehzadeh J (2013) Skew detection of scanned document images. Proc. of the International MultiConference of Engineers and Computer Scientists
Sonka M, Hlavac V, Boyle R (2008) Image processing, analysis, and machine vision. Toronto, Canada: Thomson
Zhou Q, Ma L, Celenk M, Chelberg D (2005) Content-based image retrieval based on ROI detection and relevance feedback. Multimedia Tools and Applications 27(2):251–281
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, GS., Tuan, NM. & Chen, WJ. Detecting region of interest for cadastral images in Taiwan. Multimed Tools Appl 76, 25369–25389 (2017). https://doi.org/10.1007/s11042-017-4504-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-017-4504-5