Process of converting Handwritten Tamil letters into editable form for extracting the information present in documents, Invoices that in handwritten letters that are difficult to find out the word present in the document because of bad handwriting and poor quality of the picture, Social media comments for analyzing and extracting the sentiment behind the text. Nowadays people started to deliver their thoughts through their own language Native Tamil. People find it easy to post thighs in Tamil which also leads to false information, violated messages, and cyberbullying. To address this, the notion of deep learning algorithms is implemented to classify the letters in digital form and also to suggest that the combination of letters obtained from deep learning results in better performance and good accuracy as well. The method involves the identification of optical characters to obtain feedback for the model and the creation of a model using neural networks which include CNN, Yolo and ResNet. Existing works involves using a simple OCR system but it results in a low-level recognition rate it finds difficult blurred images, shaken images, slightly tilted image's, poor quality images to recognize the text and give it back as an editable form to overcome this above situation selecting these models for testing with the Tamil character's to choose upon the best fit model to proceed for the future work of increasing the dataset and to recognize all the combination of words given in the input source of Tamil letters. The dataset used here is from HP-Labs India, which provides a large dataset of around 60,000 samples of isolated Tamil letters collected from both male and female candidates with different age groups. Tamil text classification is generally used to classify particular letters from handwritten letters in the digital form of images.