• Hitesh Choure
• Uday Parkar
• Rahul Langde
• Prof. Sunil R. Gupta

High accuracy character recognition techniques can provide useful information for segmentation-based word recognition systems. This research describes neural network-based techniques for segmented character recognition that may be applied to the segmentation and recognition components of an off-line word recognition system. Two neural architectures along with two different feature extraction techniques were investigated. A novel technique for character feature extraction is discussed and compared with others in the literature. Recognition results above 80% are reported using characters automatically segmented from the CEDAR benchmark database as well as standard CEDAR alphanumeric. Although a difficult problem, the accurate recognition of segmented characters is important in the context of segmentationbased,word recognition [4]. In this research, various neural architectures for character recognition are investigated. Two feature extraction techniques are tested including a novel technique that extracts features based on the direction of line segments within a character image.

"Novel Feature Extraction Technique for the Recognition of Segmented Character", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.5, Issue 8, page no.215-217, August-2018, Available :http://www.jetir.org/papers/JETIR18IC043.pdf

"Novel Feature Extraction Technique for the Recognition of Segmented Character", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.5, Issue 8, page no. pp215-217, August-2018, Available at : http://www.jetir.org/papers/JETIR18IC043.pdf