Summer Internship Program 2018

Machine Analytics & its Application
(May 14th, 2018 – June 30th, 2018)

Organized as a TEQIP Summer Training Program (STP) 2018, the STP covered topics in Machine Learning and was designed to provide the participants with an experience to implement the ML techniques on different projects.

_____________________________________________________________________________________________

Improving the images captured in dark and a new learning algorithm

Capturing the images in dark has always been difficult due to less SNR. An image processing pipeline  is the set of components commonly used between an image source  and an image renderer. Lot of development is done in the technology of camera sensors, but the image processing pipeline is still left behind. With this project we tried to develop a new pipeline to capture the images in the dark. The work is still in progress and we are using convolution neural network in our pipeline. A training algorithm is the process which carries out the learning procedure in neural networks. There are many different learning algorithms with different characteristics and performance. We have attempted to introduce a new algorithm and have named it ad Gain Root Mean Square(GRMS).

Project Team: 

darkimage.png
(From Left to Right): Aditi Chandra, Anukriti Singh

Aditi Chandra                                                        Anukriti Singh
2nd Year                                                                 2nd Year,
Banasthali Vidyapeeth, Jaipur                           Banasthali Vidyapeeth, Jaipur
chandra.aditi1997@gmail.com                          anukriti.runjhun@gmail.com

_____________________________________________________________________________________________

Emotion Detection and Characterization using Facial Features

In this project, a model is built that aims to detect an emotion from any given input image and deploys the emotion characteristics from images of human faces available in Cohn-Kanade dataset using machine learning algorithms. The dataset was initially segregated and organized according to their labels. The eyes and mouth were then detected and extracted using the Viola-Jones Algorithm and passed through the Gabor filter. The resulting data was further converted to pixel arrays, split into training data (80%) and testing data (20%), and eventually passed through a Support Vector Machine along with their respective labels for classification. The testing data returned a classification accuracy of 81%, at its latest.

Project Team:

emotiondetect
(From Left to Right): Charvi Jain, Kshitij Sawant, Mohammed Rehman, Riyancy Rudrancy Mawar

Charvi Jain                                                       Kshitij Sawant
3rd Year, IIIT Himachal Pradesh                 2nd Year, Manipal University, Jaipur
charvijain16@gmail.com                             kshitijsawant@gmail.com

Mohammed Rehman                                    Riyancy Rudrancy Mawar
2nd Year, Manipal University, Jaipur        4th Year, GEC Bikaner
rahmanrcks@gmail.com                             riyancymawar30@gmail.com

_____________________________________________________________________________________________

Handwritten Character Recognition

Handwritten Character Recognition is one of the most active research areas in the field of Image Processing and Pattern Recognition. It has numerous applications which include reading aid for blind, language translation, bank cheques and conversion of any handwritten document into structural text form. The aim of theproject is to recognise handwritten English uppercase letters using Neural Networks and Feature Extraction. The images of the dataset were subjected to preprocessing which involved steps like skew correction, binarization and resizing the image. The Histogram of Oriented Gradients feature extraction method has been used to extract the relevant features from the image. k- Nearest Neighbor is used as a classifier for the features. The dataset taken was from NIST handwritten dataset 2016. For 20,800 test cases, our program recognised 87% characters accurately.

Project Team:

IMG_20180625_154630
(From Left to Right): Kashish Wattal, Lakshay Dutta,
Manoj Kumar Prajapat, Preety Purohit

Kashish Wattal                                                    Lakshay Dutta
2nd Year, NIT Hamirpur                                   2nd Year, NIT Hamirpur
kashishwattal@gmail.com                              duttalakshay1498@gmail.com

Manoj Kumar Prajapat                                      Preety Purohit
3rd Year, College of Technology and              3rd Year, College of Technology and
Engineering, Udaipur                                        Engineering, Udaipur
mkp7728871560@gmail.com                          preetypurohit97@gmail.com

_____________________________________________________________________________________________

Access Control using Facial Recognition

A system which can detect and recognize face through a camera/image/video. We have implemented it using several methods. First using Haar Cascades, second by using tensor flow, third by creating our own Haar Cascade and forth by Backpropagation Network. All the programs are implemented using Python 3. We are currently working on facial recognition using (BPN) and trying to increase its accuracy.

Project Team:

IMG_20180626_153945
(From Left to Right): Aurangzeb Hussain, Vishvdeep Sharma, Harsh Mittal

Aurangzeb Hussain                                        Vishvdeep Sharma
4th Year                                                             3rd Year,
Dr. K.N Modi University, Jaipur                   Manipal Institute of Technology,
aurangzab01ak@gmail.com                         Manipal Karnataka
svishvdeep@yahoo.in

Harsh Mittal
3rd Year
The LNM Institute of Information Technology,
Jaipur
harshmittal2210@gmail.com