Image Recogniser

Image Recogniser

The project uses convolutional neural networks (CNNs) for image processing and recurrent neural networks (RNNs) for language modeling. I have implemented search algorithms such as?Beam search and Greedy search?to generate the most likely descriptions for input images.?


This model is trained on the?Flickr 30k Dataset?which has a wide range of images with their descriptions. The model is built using the powerful?Inception architecture developed by Google, which allows the network to capture features of different sizes in the input image.


Furthermore, I have added modules for image classification to?classify images as potentially abusive or restricted content.?This feature is essential for platforms that want to ensure that user-generated content is safe and appropriate. I've also added a module that allows users to?input image URLs, so they can directly work with images from the web.

No alt text provided for this image
No alt text provided for this image


No alt text provided for this image

Source Code

Vikram Mohanty

Aspiring Data Analyst| Post graduation diploma in Data Science from IIIT-Banglore| Pursuing MS Data Science at LJMU, UK

2 年

Great work

NABINA GOSWAMI

Analyst @ Annalect India | Data Extraction, Computer

2 年

Great work Rythm ??

要查看或添加评论,请登录

社区洞察

其他会员也浏览了