Title: Syntactic approach to reconstruct simple and complex medical images

Authors: Shilpa Rani; Kamlesh Lakhwani; Sandeep Kumar

Addresses: Department of CSE, Lovely Professional University, Punjab, 144411, India; Department of CSE, Neil Gogte Institute of Technology, Hyderabad, 500039, India ' Department of CSE, JECRC University, Jaipur, 303905, India ' Department of CSE, Koneru Lakshmaiah Education Foundation, Vaddeswaram, AP, 522302, India

Abstract: Most researchers find pattern recognition to be an interesting area to study. Objects that are different in shape, size, colour, and scale are easy to identify apart. Most of the available models for object recognition use a statistical approach, which works well if there is no noise in the image and the image is simple. However, this method fails if the pattern is more complicated, and there may be ambiguous results for complex pattern datasets. In that case, it would be better to use structural pattern recognition. We focused on the syntactic approach to describing the features as knowledge, which could make a big difference in theoretical computer science. Experiments have been performed on Brain MRI datasets and own dataset. To identify the performance of the reconstruction algorithm MAE, CPU time, and RMSE and iteration of the frame are calculated.

Keywords: pattern recognition; structural pattern recognition; picture description language; 2D images; knowledge vector; contour; syntactic pattern recognition.

DOI: 10.1504/IJSISE.2023.133654

International Journal of Signal and Imaging Systems Engineering, 2023 Vol.12 No.4, pp.127 - 136

Received: 13 Oct 2020
Accepted: 22 Dec 2021
Published online: 28 Sep 2023 *