ercydann/Kenya-Sign-Language-FingerSpelling-Recognition

# KSL-FINGERSPELLING-RECOGNITION ## Table of contents - Business Understanding - Data preparation - Modeling - Evaluation --- ## 1. Business Understanding ### Overview Fingerspelling, a technique that utilizes hand formations to represent words and letters, plays a vital role in communication for individuals who are deaf or hard of hearing. However, merging this manual communication method with modern technology, such as smartphones, poses challenges as fingerspelling is typically faster than device recognition. Bridging this gap between fingerspelling and smartphone typing is crucial to improve communication accessibility. ### Problem Statement The deaf and hearing impaired community faces significant communication barriers with the rest of the society. This is because sign language is not widely understood by everyone else around them, and this can lead to difficulties in communication or communication breakdowns. To address this issue, this project aims to develop a Convolutional Neural Network (CNN) model specifically designed for fingerspelling recognition, allowing for accurate identification of individual letters and complete words in different sign languages. By improving the recognition of fingerspelling gestures, the model seeks to enhance communication accessibility for individuals who are deaf or hard of hearing, promoting inclusivity and fostering effective communication with the broader society. ### Objectives #### Main objective: * The main objective is to create an innovative machine learning model that acts as a vital bridge, connecting the deaf and mute community with the wider society by translating fingerspelling images to text. #### Specific objectives: * Develop a Convolutional Neural Network (CNN) model specifically designed for fingerspelling recognition in different sign languages. * Train the model using a large dataset of fingerspelling gestures in various sign languages, ensuring accuracy and reliability in recognizing individ …