Abstract-Recurrent neural networks (RNN) have been successfully applied for recognition of cursive handwritten documents, both in English and Arabic scripts. Ability of RNNs to model context in sequence data like speech and text makes them a suitable candidate to develop OCR systems for printed Nabataean scripts (including Nastaleeq for which no OCR system is available to date). In this work, we have presented the results of applying RNN to printed Urdu text in Nastaleeq script. Bidirectional Long Short Term Memory (BLSTM) architecture with Connectionist Temporal Classification (CTC) output layer was employed to recognize printed Urdu text. We evaluated BLSTM networks for two cases: one ignoring the character's shape variations and the second is considering them. The recognition error rate at character level for first case is 5.15% and for the second is 13.6%. These results were obtained on synthetically generated UPTI dataset containing artificially degraded images to reflect some real-world scanning artefacts along with clean images. Comparison with shape-matching based method is also presented.
Documents are routinely captured by digital cameras in today's age owing to the availability of high quality cameras in smart phones. However, recognition of camera-captured documents is substantially more challenging as compared to traditional flat bed scanned documents due to the distortions introduced by the cameras. One of the major performancelimiting artifacts is the motion and out-of-focus blur that is often induced in the document during the capturing process. Existing approaches try to detect presence of blur in the document to inform the user for re-capturing the image. This paper reports, for the first time, an Optical Character Recognition (OCR) system that can directly recognize blurred documents on which the stateof-the-art OCR systems are unable to provide usable results. Our presented system is based on the Long Short-Term Memory (LSTM) networks and has shown promising character recognition results on both the motion-blurred and out-of-focus blurred images. One important feature of this work is that the LSTM networks have been applied directly to the gray-scale document images to avoid error-prone binarization of blurred documents. Experiments are conducted on publicly available SmartDoc-QA dataset that contains a wide variety of image blur degradations. Our presented system achieves 12.3% character error rate on the test documents, which is an over three-fold reduction in the error rate (38.9%) of the best-performing contemporary OCR system (ABBYY Fine Reader) on the same data.
Finding products and items in large online space that meet the user needs is difficult. Users may spend a considerable amount of time before finding item relevant to their needs. Like many other economic branches, growing Internet usage also change user behavior in the real-estate market. Advancement in virtual reality offers a virtual tour, interactive maps, floor plans that make an online rental website popular among users. With an abundance of information, recommender systems become more than ever important to suggest the user with relevant property and reduce search time. A sophisticated recommender in this domain can assist the need of a real-estate agent. Session-based user behavior, lack of user profile leads to the use of traditional recommendation methods. In this research, we proposed an approach for real-estate recommendation based on Gated Orthogonal Recurrent Unit (GORU) and Weighted Cosine Similarity. GORU captures the user searching context and weighted cosine similarity improves the rank of pertinent property. To conduct this research, we have used the data of an online public real estate web portal 4. The factual data represents the original behavior of the user on an online portal. We have used Recall, User coverage and Mean Reciprocal Rank (MRR) metric for the evaluation of our system against other state-of-the-art techniques. Proposed solution outperforms various baselines and state-of-the-art RNN based solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.