Vol 5, No 1 (2010)
Pattern Recognition Theory
A Probabilistic Tri-Class Support Vector Machine 1-9
Luis Gonzalez-Abril, Cecilio Angulo, Francisco Velasco, Juan Antonio Ortega
A probabilistic interpretation for the output obtained from a tri-class Support Vector Machine into a multi-classification problem is presented in this paper.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.237
In-Place Algorithm for Connected Components Labeling 10-22
Tetsuo Asano, Hiroshi Tanaka
Connected components labeling of a binary image is one of the most fundamental operations in image processing. This paper presents two linear-time algorithms on this topics, one for just reporting the number of connected components and the other for labeling every element of value 1 (or white pixel) by its component index.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.218
A Least Square Kernel Machine With Box Constraints 38-51
Jayanta Basak
Principle of parsimony (Occam’s razor) is a key principle where the unnecessary complexity of a classifier is regulated to improve the generalization performance in pattern classification.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.181
Optimal Parameter Selection Technique for a Neural Network Based Local Thresholding Method 69-94
Mohammed Jahirul Islam, Majid Ahmadi, Maher A Sid-Ahmed, Yasser M Alginahi
Thresholding of a given image into binary image is a necessary step for most image analysis and recognition techniques. In document recognition application, success of OCR mostly depends on the quality of the thresholded image.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.146
Example Based Single-Frame Image Super-Resolution by Support Vector Regression 104-118
Dalong Li, Steven Simske
As many other inverse problems, single-frame image super-resolution is an ill-posed problem. The problem has been approached in the context of machine learning.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.253
Applications
Recognition of on-Line Arabic Handwritten Characters Using Structural Features 23-37
Ahmad Tawfiq Al-Taani, Saeed Al-Haj
In this study, an efficient approach for the recognition of on-line Arabic handwritten characters is presented. The approach is based on structural features and decision tree learning techniques.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.217
Shape Feature and Fuzzy Logic Based Offline Devnagari Handwritten Optical Character Recognition 52-68
Prachi Mukherji, Priti P. Rege
Devnagari script is the major script of India and is widely used for various languages. In this work we propose a new shape based technique for recognition of isolated handwritten Devnagari characters.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.48
Face Verification in Videos: Set Estimation and Class Specific Thresholds 95-103
Madhura Datta, C.A Murthy
In conventional still face recognition techniques, any query image is always classified to one of the face classes irrespective of whether the query image is a face or not.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.145
Segmentation of Remotely Sensed Images Using Resampling Based Bayesian Learning 119-130
Abhishek Singh, Padmini Jaikumar, Suman Mitra
This paper presents a technique for performing unsupervised segmentation of satellite images using a `sampling-resampling' based Bayesian learning method.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.176
Rotation and Scale-Invariant Texture Classification Using Log-Polar and Ridgelet Transform 131-139
Selvaraj Arivazhagan, Kumar Gowri, Lakshmanan Ganesan
In Texture analysis, the rotation and scale invariant texture classification is one of the challenging problems. This paper provides a new method for rotation and scale invariant texture classification using log-polar and ridgelet transform.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.205
A Novel LBP Based Methods for Pavement Crack Detection 140-147
Yong Hu, Chun-xia Zhao
The local binary pattern (LBP) is a gray-scale and rotation invariant operator, and has been proved to be theoretically very simple, yet computational efficient approach for texture classification.
JPRR Vol 5, No 1 (2010); doi:10.13176/11.167