/Feature-Extraction-from-Images-for-Poetry-Assistance

In this project Object-based, scene-based and emotion-based features were extracted from a given image and these features were used to generate a poem.

Primary LanguageJupyter Notebook

Feature-Extraction-from-Images-for-Poetry-Assistance

In this project Object-based, scene-based and emotion-based features were extracted from a given image and these features were used to generate a poem.

The primary goals of this project were following:

  1. Research Part: To provide motivation to artists for creation of poetry based on images and scenes.
  2. Development Part: To provide a user interface where artists can insert images and obtain computer generated poetic hints.

The Research Part was broken down into a sequence of steps as described below. The success of each step was highly dependent on the working of the previous steps:

  1. Image Classification
  2. Image Captioning
  3. Tagging
  4. Emotion Extraction
  5. Poetry Generation
  6. Development

WhatsApp Image 2022-01-22 at 12 46 31 PM