Enhanced the Accuracy in Handwritten Character Recognition Using Novel Open Scale-Invariant Feature Transform Algorithm Over Principal Component Analysis

Principal Component Analysis (PCA) and the Open Scale Invariant Feature Transform (SIFT) are being used to improve the accuracy of handwritten characters. Principal Component Analysis and Scale Invariant Feature Transform are the two groups that make up this study. The study parameters include alpha value 0.05, beta value 0.2, and power value 0.8, with a sample size of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{2 0}$</tex> per group. Additionally, utilizing various sample sizes, their accuracy comparisons are made with one another. In handwritten character recognition, the Scale Invariant Feature Transform outperforms the Principal Component Analysis, which yields an accuracy of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{8 5. 0 0 \%}$</tex>, by <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{9 6. 9 7 \%}$</tex>. For both performance and loss, the significance value is <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$0.165(\mathrm{p}&gt;0.01)$</tex>. When it comes to improving handwritten character accuracy, the SIFT model outperforms the PCA by a wide margin.