A Convolution Neural Network for Optical Character Recognition and Subsequent Machine Translation

Optical character recognition has been a longstanding challenging research topic in the broad area of machine learning and pattern recognition. In the present paper, we investigate the problem of textual image recognition and translation, which is among the most daunting challenges in image-based sequence recognition. A convolutional neural network (CNN) architecture, which integrates optical character recognition and natural language translation into a unified framework, is proposed. The accuracy of both OCR output and subsequent translation is moderate and satisfactory. The proposed system for OCR and subsequent translation is an effective, efficient and most promising one.

[1]  Goutam Sarker,et al.  A programming based handwritten text identification , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[2]  Goutam Sarker,et al.  A Heuristic based RBFN for Location and Rotation Invariant Clear and Occluded Face Identification , 2014 .

[3]  Goutam Sarker,et al.  A learning based handwritten text categorization , 2015, 2015 International Conference on Advances in Computer Engineering and Applications.

[4]  Xiaolin Hu,et al.  Gated Recurrent Convolution Neural Network for OCR , 2017, NIPS.

[5]  Goutam Sarker,et al.  A Modified SOM-Based RBFN for Rotation Invariant Clear and Occluded Fingerprint Recognition , 2015 .

[6]  Goutam Sarker,et al.  A modified RBFN based on heuristic based clustering for location invariant fingerprint recognition and localization with and without occlusion , 2014, International Conference for Convergence for Technology-2014.

[7]  Goutam Sarker,et al.  A Programming Based Boosting in Super-Classifier for Fingerprint Recognition , 2017 .

[8]  Goutam Sarker,et al.  A Multi-Level Integrator with Programming Based Boosting for Person Authentication Using Different Biometrics , 2018, J. Inf. Process. Syst..

[9]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[10]  Goutam Sarker,et al.  An optimal clustering for fuzzy categorization of cursive handwritten text with weight learning in textual attributes , 2015, 2015 IEEE 2nd International Conference on Recent Trends in Information Systems (ReTIS).

[11]  Goutam Sarker,et al.  An Efficient Multiple Classifier Based on Fast RBFN for Biometric Identification , 2014 .

[12]  Goutam Sarker,et al.  A modified BP network using malsburg learning for rotation and location invariant fingerprint recognition and localization with and without occlusion , 2014, 2014 Seventh International Conference on Contemporary Computing (IC3).

[13]  Dr.Goutam Sarker,et al.  A Mega Super Classifier with Fuzzy Categorization in Face and Facial Expression Identification , 2017 .

[14]  Goutam Sarker,et al.  An Efficient Integrator based on Template Matching Technique for Person Authentication using Different Biometrics , 2016 .

[15]  Dhananjoy Bhakta,et al.  A rotation and location invariant face identification and localization with or without occlusion using modified RBFN , 2013, 2013 IEEE Second International Conference on Image Information Processing (ICIIP-2013).

[16]  Dhananjoy Bhakta,et al.  An Unsupervised OCA-based RBFN for Clear and Occluded Face Identification , 2015 .

[17]  Xiang Bai,et al.  An End-to-End Trainable Neural Network for Image-Based Sequence Recognition and Its Application to Scene Text Recognition , 2015, IEEE Transactions on Pattern Analysis and Machine Intelligence.