A Hybrid Approach for Complex Layout Detection of Newspapers in Gurumukhi Script Using Deep Learning
Journal Title: International Journal of Experimental Research and Review - Year 2023, Vol 35, Issue 6
Abstract
Layout analysis is the crucial stage in the recognition system of newspapers. A good layout analysis results in better recognition results. The complexity of newspaper layout structures poses a formidable challenge in digitization. The intricate arrangement of text, images, and various sections within a newspaper demands sophisticated algorithms and techniques for accurate layout detection. The paper introduces a diverse set of methodologies from existing literature, highlighting the evolution of techniques for newspaper layout analysis. In this paper, we present a novel method to detect the complex layout of newspapers in the Gurumukhi script by using a hybrid approach. The method developed consists of two parts. In the first part, we proposed an algorithm to remove pictures and graphics from Punjabi newspaper images that involve various image preprocessing tasks based on binarization, finding contours, and erosion on the image to remove the graphics from the image. This method removes pictures from complex non-Manhattan layouts. We have tested this algorithm on 100 newspaper images, giving an accuracy of 96.22%. In the second part, a dataset of 500 newspapers was created with images labeled with five classes on which the model was trained. Finally, we have trained the deep-leaning model based on a convolutional network to detect the columns of text in newspapers. We have used four different architectures of CNN and compared their performance based on different metrics such as precision, recall, and F1 score. We have tested this method on a number of newspapers in the Gurumukhi script. We have achieved an accuracy of 95.53% with this approach.
Authors and Affiliations
Atul Kumar, Gurpreet Singh Lehal
Keywords
Related Articles
- EP ID EP724725
- DOI 10.52756/ijerr.2023.v35spl.004
- Views 61
- Downloads 0
Safety evaluation of a polyherbal formulation: Acute and sub-acute toxicity study using Wistar Albino rats
Vatrog Nashak Churna (VNC) is a traditional polyherbal formulation for musculoskeletal diseases. Although the safety and mechanism of toxicity of the individual herbs have been explored, the formulation remains undocumen...
Anonymity in decentralized apps: Study of implications for cybercrime investigations
In the digital age, cybercrime facilitated by anonymous communication apps raises significant concerns. Criminals exploit the anonymity provided by these apps, creating challenges for law enforcement and cybersecurity pr...
Isozyme profiling of Antioxidant Enzyme in Macrotyloma uniflorum
The current climate change and pollution scenario has invariably increased the abiotic stress of salinity, heavy metals, and temperature on plants. Abiotic stress impacts the plant's defense system, impacting the crop's...
Zooplankton Bio-indicators Against Changing Hydrological Parameters at Bidyadhari River of Indian Sundarbans
Sundarban Estuarine System is influenced by periodic tidal input and fresh water inflow. It is surrounded by world’s largest mangrove ecosystem and harbour naturally grown fishery. The total system is intersected by a ne...
Relationship of State anxiety and trait anxiety between Physical education students and general degree college students
Mental disorders appear to be on the rise among college students and are having a significant effect on their attrition, with anxiety identified as one of the most common presenting issues. Anxiety is a state of tension;...