Internship Assessment Task for BaggageAI.

Overview

BaggageAI Internship Task

Problem Statement:

  • You are given two sets of images:- background and threat objects. Background images are the background x-ray images of baggage that gets generated after passing through a X-ray machine at airport. Threat images are the x-ray images of threats that are prohibited at airport while travelling.

  • Your task is to cut the threat objects, scale it down, rotate with 45 degree and paste it into the background images using image processing techniques in python.

  • Threat objects should be translucent, means it should not look like that it is cut pasted. It should look like that the threat was already there in the background images. Translucent means the threat objects should have shades of background where it is pasted.

  • Threat should not go outside the boundary of the baggage. ** difficult **

  • If there is any background of threat objects, then it should not be cut pasted into the background images, which means while cutting the threat objects, the boundary of a threat object should be tight-bound.

Solution:

Libraries Used :

  • OpenCV
  • numpy
  • glob
  • os
  • matplotlib
  • itertools

Methodology

To start with, we read the threat images, background images using the read_images function. For each threat image, it is first converted to grayscale and then dilated with 5x5 matrix of ones with iteration 2. Thi sis done to smooth out the image since the bright area around the threat image gets dilated around the background. Next, we create a mask for the threat object using a threshold value for white and the cv2 function inRange(). Then, the threat image is cropped to a square using a threshold value using the form_square() function. The images are padded dynamically so that when the threat is rotated 45 degrees, the whole threat image is covered and nothing is cut out. Loop through the background images and find the coordinates of the centre of the largest contour found in the background image using get_xy() function. Next, we fix the threat image according to the x, y position in background image. Finally we lace the threat in the background image using the place_threat() function.

The saved images are stored in the output folder for future reference.

Documentation:

  1. read_images(path): This function reads the .jpg files from a specific location and returns a list of images as numpy array and the number of images read.
  2. form_square(image): This function takes in a image(threat, with the background set to black using the inRange() OpenCV function) and finds the left, right, top, and bottom of the threat object, therby removing the extra background. NOTE: The threat object is not guaranteed to be a square. So this function also checks the image for the height and width of the cropped threat image and pad black portion in top-buttom of left-right making it a square image.
  3. pad_image(image): This function calculates the diagonal length of the image and set the height and width of the image equal to diagonal length.
  4. get_xy(background): This function craeates a binary image of the baggage using inRange() function and then inverts it. Next it finds the contours in the binary image and then the contour with maximum area is selected and the center of the countour is found using moments().
  5. place_threat(background, threat, x=0, y=0): This function places the threat image in the background image in (x, y) location on the background. Defaults to x=0 and y=0.
Owner
Arya Shah
Computer Science Junior with Honors in Business Systems | Software Development Engineering | Machine Learning |
Arya Shah
Repo for 2021 SDD assessment task 2, by Felix, Anna, and James.

SoftwareTask2 Repo for 2021 SDD assessment task 2, by Felix, Anna, and James. File/folder structure: helloworld.py - demonstrates various map backgrou

null 4 Aug 14, 2021
Easy and comprehensive assessment of predictive power, with support for neuroimaging features

Documentation: https://raamana.github.io/neuropredict/ News As of v0.6, neuropredict now supports regression applications i.e. predicting continuous t

Pradeep Reddy Raamana 88 Dec 15, 2021
MagFace: A Universal Representation for Face Recognition and Quality Assessment

MagFace MagFace: A Universal Representation for Face Recognition and Quality Assessment in IEEE Conference on Computer Vision and Pattern Recognition

Qiang Meng 437 Apr 20, 2022
Code for paper "A Critical Assessment of State-of-the-Art in Entity Alignment" (https://arxiv.org/abs/2010.16314)

A Critical Assessment of State-of-the-Art in Entity Alignment This repository contains the source code for the paper A Critical Assessment of State-of

Max Berrendorf 14 Apr 6, 2021
[CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment

RADN [CVPRW 2021] Code for Region-Adaptive Deformable Network for Image Quality Assessment [Paper on arXiv] Overview Update [2021/5/7] add codes for W

IIGROUP 46 Apr 4, 2022
NIMA: Neural IMage Assessment

PyTorch NIMA: Neural IMage Assessment PyTorch implementation of Neural IMage Assessment by Hossein Talebi and Peyman Milanfar. You can learn more from

Kyryl Truskovskyi 271 Apr 12, 2022
A PyTorch Implementation of Neural IMage Assessment

NIMA: Neural IMage Assessment This is a PyTorch implementation of the paper NIMA: Neural IMage Assessment (accepted at IEEE Transactions on Image Proc

yunxiaos 362 Apr 16, 2022
Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN", accepted to ACM MM 2021 BNI Track.

RecycleD Official PyTorch implementation of the paper "Recycling Discriminator: Towards Opinion-Unaware Image Quality Assessment Using Wasserstein GAN

Yunan Zhu 18 Mar 25, 2022
[ICCV 2021] Group-aware Contrastive Regression for Action Quality Assessment

CoRe Created by Xumin Yu*, Yongming Rao*, Wenliang Zhao, Jiwen Lu, Jie Zhou This is the PyTorch implementation for ICCV paper Group-aware Contrastive

Xumin Yu 23 Apr 1, 2022
Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis"

StrengthNet Implementation of "StrengthNet: Deep Learning-based Emotion Strength Assessment for Emotional Speech Synthesis" https://arxiv.org/abs/2110

RuiLiu 44 Apr 4, 2022
Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

Implementation of temporal pooling methods studied in [ICIP'20] A Comparative Evaluation Of Temporal Pooling Methods For Blind Video Quality Assessment

Zhengzhong Tu 3 Oct 10, 2021
Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment"

DSN-IQA Source code for paper "Deep Superpixel-based Network for Blind Image Quality Assessment" Requirements Python >=3.8.0 Pytorch >=1.7.1 Usage wit

null 6 Apr 4, 2022
A user-friendly research and development tool built to standardize RL competency assessment for custom agents and environments.

Built with ❤️ by Sam Showalter Contents Overview Installation Dependencies Usage Scripts Standard Execution Environment Development Environment Benchm

SRI-AIC 1 Nov 18, 2021
Lightweight Face Image Quality Assessment

LightQNet This is a demo code of training and testing [LightQNet] using Tensorflow. Uncertainty Losses: IDQ loss PCNet loss Uncertainty Networks: Mobi

Kaen 3 Jan 24, 2022
MRQy is a quality assurance and checking tool for quantitative assessment of magnetic resonance imaging (MRI) data.

Front-end View Backend View Table of Contents Description Prerequisites Running Basic Information Measurements User Interface Feedback and usage Descr

Center for Computational Imaging and Personalized Diagnostics 47 Mar 28, 2022
ZEBRA: Zero Evidence Biometric Recognition Assessment

ZEBRA: Zero Evidence Biometric Recognition Assessment license: LGPLv3 - please reference our paper version: 2020-06-11 author: Andreas Nautsch (EURECO

Voice Privacy Challenge 2 Dec 12, 2021
No-reference Image Quality Assessment(NIQA) Algorithms (BRISQUE, NIQE, PIQE, RankIQA, MetaIQA)

No-Reference Image Quality Assessment Algorithms No-reference Image Quality Assessment(NIQA) is a task of evaluating an image without a reference imag

Dae-Young Song 13 Apr 15, 2022
Pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion"

MOSNet pytorch implementation of "MOSNet: Deep Learning based Objective Assessment for Voice Conversion" https://arxiv.org/abs/1904.08352 Dependency L

null 6 Mar 16, 2022
To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

To propose and implement a multi-class classification approach to disaster assessment from the given data set of post-earthquake satellite imagery.

Kunal Wadhwa 2 Jan 5, 2022