English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Open

Presents the pdf analysis as premium feature

PDF Analysis

Insights

Presents the summarisation as premium feature

Summarisation

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Text recognition in scene image and video frames is difficult because of lowresolution, blur, background noise, etc. Since traditional OCRs do not performwell in such images, information retrieval using keywords could be analternative way to index/retrieve such text information. Date is a useful pieceof information which has various applications including date-wise videos/scenesearching, indexing or retrieval. This paper presents a date spotting basedinformation retrieval system for natural scene image and video frames wheretext appears with complex backgrounds. We propose a line based date spottingapproach using Hidden Markov Model (HMM) which is used to detect the dateinformation in a given text. Different date models are searched from a linewithout segmenting characters or words. Given a text line image in RGB, weapply an efficient gray image conversion to enhance the text information.Wavelet decomposition and gradient sub-bands are used to enhance textinformation in gray scale. Next, Pyramid Histogram of Oriented Gradient (PHOG)feature has been extracted from gray image and binary images for date-spottingframework. Binary and gray image features are combined by MLP based Tandemapproach. Finally, to boost the performance further, a shape coding basedscheme is used to combine the similar shape characters in same class duringword spotting. For our experiment, three different date models have beenconstructed to search similar date information having numeric dates thatcontains numeral values and punctuations and semi-numeric that contains dateswith numerals along with months in scene/video text. We have tested our systemon 1648 text lines and the results show the effectiveness of our proposed datespotting approach.

Date-Field Retrieval in Scene Image and Video Frames using Text Enhancement and Shape Coding