Awais Mazahir

The developed system uses a single-shot multi-box detection, an SSD algorithm for localization, and a customized lightweight deep convolutional neural network as a backbone network to classify defects generally found in industrial pipes and gun barrels. First, the image dataset is acquired from a real-time working environment using an indigenously developed borescope featuring a rotating camera and special hardware features. Later, the bounding boxes are calculated using extracted features to localize defects with SSD, which takes a single shot to detect multiple objects within the image. Finally, the defected regions are classified into five classes of commonly found issues of pitting, chipping, rusting, dirt, and thermal cracking by utilizing deep learning architecture of 53 layers. It is found that the proposed approach can indicate the exact location of the classified defect in terms of angle and distance from a reference point.

A Django-based web application that is used to search business websites on the web based on keywords and other AI-based search filters. It crawls the web to find the contact page, fetches the form fields, and submits the form with an automated filling of data. The tool can send multiple contact emails simultaneously.

A Python desktop application was developed to train a custom neural network with a single click. Said algorithm was able to do binary as well as multiclass classification. The project also involves the development of a fluent UI on PyQt5, which shows live training progress.

A complete IoT Solution was developed over AWS. The system consists of a proof of concept for public eCommerce delivery cabinets which can be unlocked with face detection. It had a Python-based front end that used the Boto3 library to store data in AWS DynamoDB through AWS IoT MQTT Broker after verifying the face through Amazon Rekognition. The system used Raspberry Pi for high-end processing and Arduino for necessary actuations.

A demonstration of the prototype can be seen in the following URL:
https://www.dropbox.com/s/pm2wyvf3ip9m1ub/Smart%20Locker.mp4?dl=0