Lexical Error Compensation in Handwritten-Based Mathematical Information Retrieval
نویسندگان
چکیده
Entering mathematical queries, in general, can be a demanding task. Mathematical notation is twodimensional and cannot be easily typed with a standard QWERTY keyboard. Handwriting appears to be the most intuitive and promising method to express mathematical queries. Recognition technology for handwritten mathematical notation has never been applied in math search. Existing recognition techniques for handwritten mathematical notation are quite advanced but still produce misrecognized or completely unrecognized symbols. The objective of this research is to design and implement an automated symbol-recognition error compensation system for the handwritten-based query processing. To achieve this objective, we have designed and implemented a query processing algorithm which modifies and expands handwritten queries using different policies, in order to compensate for the symbol-recognition errors. Experiments have demonstrated that these policies substantially improve the performance of a handwritten‐based math IR system.
منابع مشابه
Application of information retrieval techniques to single writer documents
This work shows Information Retrieval experiments performed over handwritten documents produced by a single writer. The same retrieval task has been performed over both manual (no errors) and automatic (Word Error Rate around 45%) transcriptions of 200 handwritten texts. The results show that the performance loss due to recognition errors is acceptable and that Information Retrieval technologie...
متن کاملClosed-Loop Compensation of the Quadrature Error in MEMS Vibratory Gyroscopes
In this paper, a simple but effective method for compensation of the quadrature error in MEMS vibratory gyroscope is provided. The proposed method does not require any change in the sensor structure, or additional circuit in the feedback path. The mathematical relations of the proposed feedback readout system were analyzed and the proposed solution assures good rejection capabilities. Based on ...
متن کاملConnected Component Based Word Spotting on Persian Handwritten image documents
Word spotting is to make searchable unindexed image documents by locating word/words in a doc-ument image, given a query word. This problem is challenging, mainly due to the large numberof word classes with very small inter-class and substantial intra-class distances. In this paper, asegmentation-based word spotting method is presented for multi-writer Persian handwritten doc-...
متن کاملComparative Study of Degree of Bilingualism in Lexical Retrieval and Language Learning Strategies
This study compares lexical retrieval amongst monolinguals and intermediate bilinguals and advanced bilinguals. It also investigates the possible effects of their language learning strategies on their respective lexical retrieval advantage. The study used a mixed methods design and the groups consisted of 20 Persian near-monolinguals, 20 Persian-English intermediate level bilinguals, and 20 Per...
متن کاملUse of the Shearlet Transform and Transfer Learning in Offline Handwritten Signature Verification and Recognition
Despite the growing growth of technology, handwritten signature has been selected as the first option between biometrics by users. In this paper, a new methodology for offline handwritten signature verification and recognition based on the Shearlet transform and transfer learning is proposed. Since, a large percentage of handwritten signatures are composed of curves and the performance of a sig...
متن کامل