Impact Factor

7.883 Call For Paper

Share on

Author(s):

S. Murugesh | G.C. Lokeshwaran | G. Kannan | Mrs.M. Nithya
Keywords:

Archaeological Image Recognition, Convolutional Neural Network, Machine Learning, Artifact Classification, Deep Learning, Heritage Preservation, Computer Vision.
Abstract:
This Study Presents An Intelligent AI-based Image Recognition System Designed To Assist Archaeologists In The Identification And Classification Of Artifacts From Excavation Sites And Museum Archives. Traditional Archaeological Analysis Is Time-consuming And Prone To Subjective Interpretation, Limiting Scalability And Consistency. The Proposed System Leverages Deep Learning And Computer Vision—specifically Convolutional Neural Networks (CNN)—to Automate Artifact Recognition With High Accuracy. Through Systematic Preprocessing, Feature Extraction, And Classification, The Model Effectively Distinguishes Between Diverse Artifact Types Such As Tools, Sculptures, And Inscriptions. Experimental Evaluation Demonstrates That The CNN Model Achieves A Classification Accuracy Of 92% With An F1-score Of 0.91, Outperforming Traditional Machine Learning Methods Like SVM And KNN. Additionally, The System Is Deployed Through A Flask-based Web Interface That Enables Real-time Artifact Identification And Visualization. By Integrating AI-driven Image Recognition With Digital Archaeology, The System Enhances Research Efficiency, Promotes Cultural Heritage Preservation, And Contributes To The Digital Transformation Of Archaeological Studies.