The dataset used for this project comprised of 11,600 grayscale images of handwritten Nepali characters. The characters are consonants, numerals, and vowels. Consonants: "क ख ग घ ङ च छ ज झ ञ ट ठ ड ढ ण त थ द ध न प फ ब भ म य र ल व श ष स ह क्ष त्र ज्ञ" Numerals: "० १ २ ३ ४ ५ ६ ७ ८ ९" Vowels: "अ आ इ ई उ ऊ ए ऐ ओ औ अं अः" The dataset comprised of 58 classes (36 consonants + 10 numerals + 12 vowels). Each class consists of 200 images split into a training set (160 images) and a test set (40 images). The model used for classification was TinyVGG. This model can classify the aforementioned 58 classes with 83.30% accuracy.
As it is said, “opinions” are core to almost all human activities and are key influences on our behaviors. Opinions can be analyzed for a person’s notion and sentiments. The key focus of the project is collaborative governance and data-powered collective intelligence using the huge amount of data made available by social media. In layman's terms, the project summarizes the acceptance of a given keyword (that might be positive, negative, or neutral) based on discussions on online forums.
This project was developed using AutoIt. It was for automation by generating source code based on GUI operations.