Publication Date: 2023/07/25
Abstract: Biometric identification has emerged as a powerful tool for recognizing individuals in various applications, ranging from security systems to text analysis. This paper focuses on the application of biometric identification for recognizing text using a combination of one-hot encoding and convolutional neural networks (CNNs) through artificial intelligence (AI). The one-hot encoding technique is employed to represent textual data, where each word or character is converted into a binary vector of zeros and ones. This representation preserves the unique characteristics of the text and enables efficient processing by the CNN model. The CNN architecture is utilized to learn meaningful features from the encoded text, capturing important patterns and structures. The integration of AI techniques further enhances the accuracy and efficiency of the biometric identification system. AI algorithms allow for the automatic extraction of relevant features, reducing the need for manual feature engineering. The trained CNN model is capable of recognizing text patterns with a high degree of accuracy, enabling the identification of individuals based on their unique textual attributes. Experimental results demonstrate the effectiveness of the proposed approach. The combination of one-hot encoding and CNN via AI achieves notable improvements in text recognition performance, surpassing traditional methods. The system proves robust to variations in text content, font styles, and sizes, highlighting its potential for real-world applications.
Keywords: CNN, AI, ONE-HOT ENCODING.
DOI: https://doi.org/10.5281/zenodo.8181197
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23JUN2470.pdf
REFERENCES