National Journal of System and Information Technology

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

Document Classification:A Technical Review


Affiliations
1 Babu Madhav Institute of Information Technology, Uka Tarsadia University, India
     

   Subscribe/Renew Journal


Document classification is used for identify the proprietary of complex document. Identify proprietary of any document is very difficult stuff in the area of image processing. There are various way to identify the proprietary of document like, based on signature, logo, seal and many more. We have searched for document classification based on logo and seal, and we surveyed literature related to our work. Majority authors used texture feature extraction author used Discrete Wavelet Transformation (DWT) and Fast Fourier Transform (FFT) for feature extraction and for classification they were used Know Nearest Neighbor (KNN), Neural Network (NN) and support vector machine (SVM).

Keywords

DWT, FFT KNN, NN, SVM.
Subscription Login to verify subscription
User
Notifications
Font Size


  • B.V.Dhandra, Mallikarjun Hangarge, “On Seperation of English Numerals from Multilingual Document Images”, International Journal of Multimedia (JM), Vol.2, No.6 Nov. 2007, Academy Publisher, Oulu, Finland, pp. 26-33, ISSN: 1796-2048.

  • B.V.Dhandra, Shashikala P, Gururaj M, “Kannada Handwritten Vowels Recognition Based on Normalized Chain Code and wavelet Filters”, National Conference on Recent Advances in Information Technology, 2014.

  • Shridevi Soma1, B.V Dhandra2, “Automatic Logo Recognition System from the Complex Document using Shape and Moment Invarient Features”, International Journal of Advances in Computer Science and Technology, Vol 4 No.2, Page: 06-13, 2015.

  • B.V. Dhandra, Shridevi Soma, Gururaj Mukarambi ” Identification of Institutional Logo based on Wavelet Features”, Dept. of Computer Science Central University of Karnataka Gulbarga International Journal of Computer Applications (0975 – 8887) Volume 107 – No 15, December 2014.

  • Shridevi Soma, B.V Dhandra, “A Shape feature based Identification of a Complex Document”, National Conference on Digital Image and Signal Processing (NCDISP – 2015), MAEER’s Arts, Commerce and Science College, Pune, India, 12th and 13th Feb 2015.

  • Sina Hassanzadeh and Hossein Pourghassem, "A Novel Logo Detection and Recognition Framework for Separated Part Logos in Document Images" Australian Journal of Basic and Applied Sciences, 5(9): 936-946, 2011 ISSN 1991-8178, Department of Electrical Engineering, Najafabad Branch, Islamic Azad University, Isfahan, Iran.

  • Raveendra. K, Dr. P V N Reddy and Dr. P V V Kishore, “A Review on Classification and Comparison of Automatic Logo Based Document Image Retrieval Methods and other Applications”. International Journal of Applied Engineering Research ISSN 0973-4562 Volume 12, Number 24 (2017).

  • Zhu, Guangyu, and David Doermann, "Automatic document logo detection." Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on. Vol. 2. IEEE, 2007.

  • Chen, Jingying, Maylor K. Leung, and Yongsheng Gao. "Noisy logo recognition using line segment Hausdorff distance." Pattern recognition 36.4 (2003): 943-955.

  • Sreelakshmi U.K, Akash V.G and N. Shobha Rani, "Detection of Variable Regions in Complex Document Images", International Conference on Communication and Signal Processing, April 6-8, 2017, India.

  • David S. Doermann, Ehud Rivlin and Isaac Weiss, “Logo Recognition Using Geometric Invariants”, 0-8186-4960-7/93 $3.00 0 1993 IEEE.

  • Alexandrina-Elena Pandelea*, Mihai Budescu and Gabriela Covatariu, “Image processing using artificial neural”, Buletinul Institutului politehnic din iaşi public at de universitatea tehnică, gheorghe asachi” din iaşi tomul lxi (lxv), fasc. 4, 2011


Abstract Views: 351

PDF Views: 4




  • Document Classification:A Technical Review

Abstract Views: 351  |  PDF Views: 4

Authors

Manish Vala
Babu Madhav Institute of Information Technology, Uka Tarsadia University, India

Abstract


Document classification is used for identify the proprietary of complex document. Identify proprietary of any document is very difficult stuff in the area of image processing. There are various way to identify the proprietary of document like, based on signature, logo, seal and many more. We have searched for document classification based on logo and seal, and we surveyed literature related to our work. Majority authors used texture feature extraction author used Discrete Wavelet Transformation (DWT) and Fast Fourier Transform (FFT) for feature extraction and for classification they were used Know Nearest Neighbor (KNN), Neural Network (NN) and support vector machine (SVM).

Keywords


DWT, FFT KNN, NN, SVM.

References