Abstract:
This paper offers an overview of target recognition through grouping of numerous images and
machine learning methods for the blind. Our system has been developed based on speech
recognition to allow blind people to learn about the various components of the Bangladesh
Liberation War Museum. The first poll reveals that most blind people are eager to see what is
inside the museum, but the museum has no electronic mechanism for identifying the item as
an excuse.
Different Machine Learning software (ML) such as Scikit-learn, Pandas, Matploatlib, Numpy,
TensorFlow have been used for the entire process. We also used Scikit-learn for applying
algorithms for pre-processing images and classification. We used five different K-Nearest
Neighbor(KNN), Support Vector Machine(SVM), Decision Tree Classifier, Random Forest,
Naive Baies and the most common Convolutional Neural Network(CNN) image processing
algorithm to test the validity of our work. The algorithm was the most accurate. Both algorithms
have been analyzed. Finally, this algorithm that provided the highest precision detects museum
displays.
