scholarly journals Improved Real time Signboard Detection and Translation Using FRCNN

2021 ◽  
Vol 10 (2) ◽  
pp. 1-5
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Mobile Application ◽  
Major Portion ◽  
Text Extraction

In India, majority of people are speaking the language Hindi, but a major portion of signboards are in English. On a business or pleasure trip, the travelers get confused by the various sign boards written in English. As smartphones becomes most popular inrecent years,they canrely on smartphone for the same. This paper explains the work intended to build a mobile application that can recognize the English content and sign present on the signboard image, detect and translate the content and symbols from English to Hindi and display the translated Hindi text back to the screen of the phone. The system uses pre-trained faster regional convolutional neural networkusing pre-trained CNN for object detection, tesseract OCR for text extraction and English-to-Hindi dictionary for translation.

scholarly journals AR Amenity Perceiver

2020 ◽  
Vol 8 (5) ◽  
pp. 2847-2850
Keyword(s):  
Augmented Reality ◽  
Object Detection ◽  
Real Time ◽  
User Experience ◽  
Mobile Application ◽  
Furniture Industry ◽  
Android Application

The major problem in the Furniture industry is choosing the appropriate furniture for the residence or office. The users are feeling difficult to visualize furniture from a catalog and so changing the furniture textures after purchase would be inconvenient. What: Our solution is a powerful mobile application to render 3D Furniture models into augmented reality. This application features AR experience of the Furniture in reality. The inspiration driving this investigation is to consider and develop an android application called 'AR Amenity Perceiver' with the usage of Augmented Reality advancement for structure and improvement that will help users with envisioning how furniture pieces will look and fit in their homes and besides can give nuances of things to help customer decision. How: The application supports plane and object detection to place and track Furniture in real time. Since the application is built with React Native, it is platform independent and supports real time stutter less object rendering. Why: The client can utilize View in Room 3D mode to envision the furnishings or stylistic theme components in the encompassing space with the assistance of AR. This allows users to check out the Furniture with available texture options and thus making the user experience more realistic before buying

scholarly journals Real Time Object Detection and Text Extraction

2019 ◽  
Vol 8 (11S) ◽  
pp. 33-37
Keyword(s):  
Object Detection ◽  
Real Time ◽  
Focal Points ◽  
Content Extraction ◽  
Text Extraction ◽  
Content Discovery ◽  
Content Identification ◽  
Different Content

—this paper distinguishes and analyzes diverse stages during the time spent content discovery and acknowledgment and investigations distinctive methodologies utilized for content extraction from real time pictures. Two generally utilized techniques for this issue are stepwise strategies and coordinated techniques, though this undertaking is additionally partitioned into content discovery and confinement, grouping, division and content acknowledgment. Imperative methodologies used to experience these stages and their comparing favorable circumstances, disservices and applications are exhibited in this paper. Different content related applications for symbolism are additionally introduced here. This survey performs a similar examination of crucial procedures in this field. This paper thinks about different stages in the procedure of content discovery and acknowledgment and examinations and analyzes distinctive methodologies used to experience these stages. It presents the significance of each handling stage and focal points, weaknesses, and utilization of methodologies utilized by different supporters of take care of these issues. Different uses of content identification and acknowledgment are additionally assessed in this paper. Content acknowledgment arranges changes over pictures of content into a series of characters or words. It is essential to change over pictures of content into words as a word is a rudimentary substance utilized by a human for his visual acknowledgment. Diverse methodologies of acknowledgment are character acknowledgment and word acknowledgment. Character acknowledgment techniques separate the content picture into numerous patterns of single characters. The partition between contiguous characters is imperative for these techniques.

Sign in / Sign up

Export Citation Format

Share Document