Edge Detection of Degraded Stone Inscription Kannada Characters Using Fuzzy Logic Algorithm
Digital India is an initiative by the Government of India. This initiative encourages digitization and analysis in all walks of life. Digitization will preserve any historical document and that information can access by any individuals by his finger tip f
- PDF / 427,891 Bytes
- 10 Pages / 439.37 x 666.142 pts Page_size
- 72 Downloads / 191 Views
Abstract Digital India is an initiative by the Government of India. This initiative encourages digitization and analysis in all walks of life. Digitization will preserve any historical document and that information can access by any individuals by his finger tip from any place. Stone inscriptions are one of the key historical evidences of literature and culture of that region in the passage of time. Recognition and analysis of stone inscriptions play a pivotal role in deciding the era/age it belongs ad to understand the content. A proper digitization and recognition technique is prerequisite and desired. Here, in this work digitization of characters has been done by using ordinary digital camera. Further, the captured images are pre-processed in order to extract features. In this proposed algorithm, gradient analysis is carried out at every pixel in the x and y directions, based on the result it defines an edge using Fuzzy Inference System. The experiment was conducted on twenty set of analogous degraded stone inscriptions Kannada characters and result obtained was magnificent with better time efficiency compared to prior methods. Keywords Digitalization
⋅
Edge detection
⋅
Fuzzy inference system
B.K. RajithKumar (✉) ⋅ B.V. Uma Department of Electronics and Communication Engineering, RV College of Engineering, Bengaluru, India e-mail: [email protected] B.V. Uma e-mail: [email protected] H.S. Mohana Department of Electronics and Instrumentation Engineering, Malnad College of Engineering, Hassan, India e-mail: [email protected] J. Uday Department of Electronics and Communication Engineering, Srinivas Institute of Technology, Mangaluru, India e-mail: [email protected] © Springer Nature Singapore Pte Ltd. 2018 S.C. Satapathy et al. (eds.), Data Engineering and Intelligent Computing, Advances in Intelligent Systems and Computing 542, DOI 10.1007/978-981-10-3223-3_2
11
12
B.K. RajithKumar et al.
1 Introduction Feature extraction plays a vital role in stone inscription character recognition, for better feature extraction an enhanced pre-processing is required. Comprehensible feature extraction for any Kannada stone inscriptions is challengeable, especially in the stone inscriptions each character are not uniformly inscripted and some characters are degraded due to some natural calamities. Edge detection is imperative step in preprocessing; the prior methods like Sobel, Canny are deficient to find the edges of old stone inscription characters so new-fangled edge detection technique is required for better feature extraction. In this present work, the captured image is converted into gray scale and Fuzzy algorithm works only on double precision data so the gray scale image was again converted into double-precision. To determine image gradient in x-axis and y-axis, we define Fuzzy Inference System (FIS) using triangular membership function and defined rule such that, any pixel belongs to a uniform region is make it as white else make same pixel as black. Finally we compared the recognition results of proposed method with Sob
Data Loading...
