Text and Facial Recognition

Project
features
number one
Pillow, OpenCV, and Tesseract

Demonstrating use of three Python libraries: Pillow, OpenCV, and Py Tesseract. I wrote a program that contains three main functions: (1) find a user-inputted word within an image, (2) crop faces out of a user-uploaded image, and (3) if word is in the image, faces from the image are displayed as a new image of cropped faces.

number one
Wired Script within Django Framework

I used Django models, views, and forms to execute the script. Through the forms view, the user can input the word and the image needed to execute the script. The input is stored in a MySQL database with the help of Django models. Using Django views, the script is imported and then executed with the output presented on a template page defined within the view.

number one
File Manipulation

The user is required to upload an image for the app to run. In order to create the output, images of faces found through the script are cropped, resized, and then saved using Python Pillow. Those cropped faces are then pasted onto a contact sheet which is saved as an image. This image is then displayed as the output through Django views and template.