Skip to content

ruchi15/Auto-Vision-Scanner

Repository files navigation

Auto-Vision-Scanner

README: https://devpost.com/software/auto-vision-scanner

Idea/Mission:

Built an Auto Vision Scanner using the powerful Google Cloud Vision API that scans the image, analyses and converts the image into text. It locates any textual content in the image and extracts it. You’ll be amazed by the extent to which the powerful Google Cloud Vision API visualises and extracts the text from the image.

    ## Classes:
            - Detect_Image: The class for analyzing the image given by the user.

    ## Functions:
            - 'detect_image()': For Analyzing the image
            

    ## Variables.
            - 'content' : the image matrix
            - 'image' : The type of the image which will portray the content
            - 'text_response' : The text contained in the image with other features like location of the text
            - 'predictions' : prediction for the image type
            - 'face_response' : Respone of the face(features of the face) after detecting face
            - 'face_content': Face Annotations
            - 'conf': The confidence of the prediction of the emotions
            - 'face_content_result': The likelihoof of all the emotions

How we build it:

We used the Google Clould Vision API, Flask ,Python, HTML to host it on the web page page.

Running the Codes

Run command python main.py on Anaconda Prompt

The folder named "images" will contain the images which you will upload/import.

HACKERS - Ruchi Singh, Shivam Gupta, Harshita Rastogi

Tech Stack:

Google Cloud Vision API, Python, Flask, HTML, JavaScript, JSON.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

 
 
 

Contributors