scispace - formally typeset
Search or ask a question
Author

M. P. S. Bisht

Bio: M. P. S. Bisht is an academic researcher. The author has contributed to research in topics: Artificial intelligence & Devanagari. The author has an hindex of 1, co-authored 1 publications receiving 1 citations.

Papers
More filters
Proceedings ArticleDOI
23 Mar 2023
TL;DR: In this paper , text detection and localization techniques are used for handwritten documents written in the Devanagari script, where image processing and an effective morphology-based technique for text detection are used.
Abstract: In text analysis systems, text detection and localization techniques are preliminary steps for further text recognition tasks. Finding the specific text information in the image is important as it has many significant real-time applications. The available techniques for text detection and localization work well for printed text, but their performance is not good for handwritten text present in an image. Also, the available modern deep learning techniques require large datasets for training. S0, if small handwritten data images are available, then image processing and an effective morphologybased technique for text detection and localization can be used. In this paper, these techniques are used for handwritten documents written in the Devanagari script.

Cited by
More filters
Journal ArticleDOI
16 Jul 2021-Science
TL;DR: In this paper, an analysis of satellite imagery, seismic records, numerical model results, and eyewitness videos reveals that ~27x106 m3 of rock and glacier ice collapsed from the steep north face of Ronti Peak.
Abstract: On 7 Feb 2021, a catastrophic mass flow descended the Ronti Gad, Rishiganga, and Dhauliganga valleys in Chamoli, Uttarakhand, India, causing widespread devastation and severely damaging two hydropower projects. Over 200 people were killed or are missing. Our analysis of satellite imagery, seismic records, numerical model results, and eyewitness videos reveals that ~27x106 m3 of rock and glacier ice collapsed from the steep north face of Ronti Peak. The rock and ice avalanche rapidly transformed into an extraordinarily large and mobile debris flow that transported boulders >20 m in diameter, and scoured the valley walls up to 220 m above the valley floor. The intersection of the hazard cascade with downvalley infrastructure resulted in a disaster, which highlights key questions about adequate monitoring and sustainable development in the Himalaya as well as other remote, high-mountain environments.

201 citations

Journal ArticleDOI
TL;DR: In this paper , a geospatial with field based study investigated the reasons behind the recent big disaster and this research finding will definitely assist to policy makers for sustainable planning and management.
Abstract: Most of the Greater Himalayan cities recurrently face multiple natural hazards or disasters such as earthquake, landslide, sinking, glacier busts and flash flood. So, Joshimath is no exception because it is situated on tectonically very active young fold Himalayan mountain chain. Previously, many incidents like landslides, subsidence or sinking and flash flood occurred in and around Joshimath city and multiple major and minor cracks also exposed on roads, walls and floors of houses. From 11 January 2023, major portion of Joshimath city is continuously started to sink and major and minor cracks have been developed on roads, floors, ceilings and walls of houses. Around 1000 people have been evacuated from the unsafe area and risky buildings. Here, schmidt hammer rebound test for rock strength, deep learning technique (landslide susceptibility) and geo-hydrological techniques have been applied. This geospatial with field based study investigated the reasons behind the recent big disaster and this research finding will definitely assist to policy makers for sustainable planning and management.
Proceedings ArticleDOI
17 Mar 2023
TL;DR: In this article , the authors proposed a novel framework that takes curvature into account when learning and employs CNN LSTM and Yolov5-OCR to extract information from printed and handwritten documents.
Abstract: The field of automated cheque collection has received a lot of attention recently due to the complexity and time-consuming nature of the manual process, which requires significant investment in technology, infrastructure, and staff training. However, some key areas such as Customer Experience and Interoperability with Image Processing and machine learning systems have not been explored. The challenge lies in the fact that handwritten characters are unique, and there is a lack of open-sourced foundation models. Furthermore, cheques and bank receipts contain both handwritten and non-handwritten text, making it difficult to extract information. The research proposes a novel framework that takes curvature into account when learning and employs CNN LSTM and Yolov5-OCR to extract information from printed and handwritten documents. The CTC-loss-function has limited application to processing bank cheques we had identified this gap and further improved overfitting which results due to CTC loss by combining CTC, curvature loss, and embedding loss, This research has further contributed to the development of an automated cheque collection framework that can extract information from both printed and handwritten texts, improving the overall efficiency of the cheque collection process and interoperability within various systems which is laborious in nature.
Proceedings ArticleDOI
17 Mar 2023
TL;DR: In this article , the authors proposed a novel framework that takes curvature into account when learning and employs CNN LSTM and Yolov5-OCR to extract information from printed and handwritten documents.
Abstract: The field of automated cheque collection has received a lot of attention recently due to the complexity and time-consuming nature of the manual process, which requires significant investment in technology, infrastructure, and staff training. However, some key areas such as Customer Experience and Interoperability with Image Processing and machine learning systems have not been explored. The challenge lies in the fact that handwritten characters are unique, and there is a lack of open-sourced foundation models. Furthermore, cheques and bank receipts contain both handwritten and non-handwritten text, making it difficult to extract information. The research proposes a novel framework that takes curvature into account when learning and employs CNN LSTM and Yolov5-OCR to extract information from printed and handwritten documents. The CTC-loss-function has limited application to processing bank cheques we had identified this gap and further improved overfitting which results due to CTC loss by combining CTC, curvature loss, and embedding loss, This research has further contributed to the development of an automated cheque collection framework that can extract information from both printed and handwritten texts, improving the overall efficiency of the cheque collection process and interoperability within various systems which is laborious in nature.