Title :
Symbol recognition via statistical integration of pixel-level constraint histograms: a new descriptor
Author_Institution :
Dept. of Comput. Sci. & Eng., Fudan Univ., Shanghai, China
Abstract :
A new descriptor for symbol recognition is proposed. 1) A histogram is constructed for every pixel to figure out the distribution of the constraints among the other pixels. 2) All the histograms are statistically integrated to form a feature vector with fixed dimension. The robustness and invariance were experimentally confirmed.
Keywords :
character recognition; constraint theory; feature extraction; image recognition; statistical analysis; feature vector; pixel level constraint histograms; statistical integration; symbol recognition; Character recognition; Circuits; Engineering drawings; Feature extraction; Graphics; Histograms; Optical distortion; Optical noise; Robustness; Shape; Index Terms- Symbol recognition; descriptor; feature extraction; feature representation.; graphics recognition; Algorithms; Artificial Intelligence; Cluster Analysis; Computer Simulation; Image Enhancement; Image Interpretation, Computer-Assisted; Information Storage and Retrieval; Models, Statistical; Numerical Analysis, Computer-Assisted; Patents as Topic; Pattern Recognition, Automated; Reproducibility of Results; Sensitivity and Specificity; Signal Processing, Computer-Assisted; Subtraction Technique;
Journal_Title :
Pattern Analysis and Machine Intelligence, IEEE Transactions on
DOI :
10.1109/TPAMI.2005.38
