부산대학교 도서관

The proposed project is a comparative study of the accuracy of OCR-based image-to-speech conversion using novel FKM and FCM algorithms from low-resolution images that have high accuracy. Method and material: Two classes are contrasted, novel Fuzzy k-means clustering (FKM) (N=10) and Fuzzy c-means clustering (FCM) (N=10) with the G Power software, the total volume is determined with alpha equal to 0.05, the enrollment ratio is equal to 0.1, the confidence interval is 95%, and the power is 80%. SPSS' software was used to conduct an independent sample t-test to assess the accuracy rate. Conclusion: The results of the MATLAB simulation are 90 % accurate and have a precision of 84 % in the conversion of text to speech. In SPSS' statistical analysis, a significant degree of success (0.001) was achieved. Conclusion: A novel FKM classifier is demonstrated to be superior to the FCM Classifier for OCR-based images to speech. [ABSTRACT FROM AUTHOR]