Offline cursive Urdu-Nastaliq script recognition using multidimensional recurrent neural networks

Character recognition for cursive script like Arabic, handwritten English and French is a challenging task which becomes more complicated for Urdu Nasta'liq text due to complexity of this script over Arabic. Recurrent neural network (RNN) has proved excellent performance for English, French as well as cursive Arabic script due to sequence learning property. Most of the recent approaches perform segmentation-based character recognition, whereas, due to the complexity of the Nasta'liq script, segmentation error is quite high as compared to Arabic Naskh script. RNN has provided promising results in such scenarios. In this paper, we achieved high accuracy for Urdu Nasta'liq using statistical features and multi-dimensional long short-term memory. We present a robust feature extraction approach that extracts feature based on right-to-left sliding window. Results showed that selected features significantly reduce the label error. For evaluation purposes, we have used Urdu printed text images dataset and compared the proposed approach with the recent work. The system provided 94.97 % recognition accuracy for unconstrained printed Nasta'liq text lines and outperforms the state-of-the-art results.

Urdu Nasta'liq text recognition system based on multi-dimensional recurrent neural network and statistical features

In this paper, we studied the use of the foreground and background features and SVM classifier to improve the accuracy of offline handwritten numeral recognition. The foreground features are two directional features: directional gradient feature by Kirsch operators and directional stroke feature by local shrinking and expanding operations, and the background feature is concavity feature which is extracted from the convex hull of the numeral, where the concavity feature functions as complement to the directional features. During classification of the numeral, these three features are combined to obtain good discrimination power. The efficiency of our scheme is tested by recognition experiments on the handwritten numeral database CENPARMI, where SVM classifier with RBF kernel is used. The experimental results show the usefulness of our scheme and recognition rate of 99.10% is achieved.

/pdf/offline-handwritten-numeral-recognition-using-multiple-42htmetqds.pdf

Offline Handwritten Numeral Recognition Using Multiple Features and SVM classifier

Script identification especially for non-Latin script have gained the attention of researchers from both the academics and industry. There are lots of challenges associated with this since most of the existing research focuses on Latin scripts. Most of the researches in this field are working only with the latest or modern documents and font types. Historical and Degraded documents have not been given much importance in the OCR research. This paper provides the different stages required for the identification of the scripts. A brief overview of the different techniques for identifying and classifying the characters in Devanagari and Urdu Script. This has been performed especially for degraded and historical texts. The paper has been concluded with a strong future scope.

Degraded Script Identification of Urdu and Devanagari Document-A Survey

/pdf/offline-handwritten-devanagari-numerals-recognition-using-2ghd3f52be.pdf

Offline Handwritten Devanagari Numerals Recognition using GLCM Features & Neural Networks

Extraovarian granulosa cell tumors (GCTs) are rare neoplasms. They arise from the ectopic gonadal tissue along the embryonal route of genital ridge. We present a case of an extraovarian tumor in an elderly female who presented with lump in the abdomen occupying the pelvic region. She was operated and the mass was excised with intact capsule. Histopathology revealed the mass to be an adult granulosa cell tumor. Extraovarian granulosa cell tumors are very rare with only 13 such cases reported in literature to date. The present case is the largest primary retroperitoneal adult granulosa cell tumor reported till date.

Lisha Singla

Papers

Offline Handwritten Devanagari Numerals Recognition using GLCM Features & Neural Networks

A rare case of primary retroperitoneal extraovarian granulosa cell tumor