Detecting Shadows in Computer Vision: A MATLAB-Based Approach

Authors

  • Muhammad Hasan Irshad Department of Computer Science, Faculty of Engineering Science & Technology Iqra University Main Campus, Karachi, Pakistan
  • Mansoor Ebrahim Department of Engineering Science & Technology Iqra University Karachi, Pakistan.
  • Abdul Ahad Abro Department of Engineering Science & Technology Iqra University Karachi, Pakistan.
  • Kamran Raza Department of Engineering Science & Technology Iqra University Karachi, Pakistan.
  • Syed Hasan Adil Department of Engineering Science & Technology Iqra University Karachi, Pakistan.

DOI:

https://doi.org/10.62019/abbdm.v4i1.109

Abstract

The abstract outlines a novel MATLAB-based technique for enhancing shadow detection accuracy in computer vision applications. This MATLAB-based method uses thresholding and color analysis to improve the accuracy of shadow identification. Luminance (L*) is distinguished from chromaticity (a* and b*) in digital photographs by converting them into the Lab color space. This makes it easier to identify possible shadowed areas. The luminance channel's thresholding makes it possible to distinguish between regions that are well-lit and those that are shadowed. The computation of chromaticity distance also helps in detecting modest color changes that are suggestive of shadows. The culmination of the suggested technique is the creation of a binary shadow mask, which isolates the image's shaded regions. The research addresses limitations of existing approaches by maintaining robustness in diverse lighting conditions and complex scenarios, thereby enhancing image comprehension and the precision of shadow detection. The proposed technique holds promise for improving object recognition and scene analysis in computer vision applications, offering a robust and reliable solution for identifying and isolating shadows in digital images.

Downloads

Published

2024-02-29

How to Cite

Detecting Shadows in Computer Vision: A MATLAB-Based Approach. (2024). The Asian Bulletin of Big Data Management , 4(1), Data Science 4(1), 97-106. https://doi.org/10.62019/abbdm.v4i1.109