Report on Artificial Intelligence Workshop conducted by IETE

Committee Feb 21, 2018

Artificial intelligence is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and other animals.The term “artificial intelligence” is applied when a machine mimics “cognitive” functions that humans associate with other human minds, such as “learning” and “problem solving”.

          Artificial Intelligence and Computer Vision workshop, conducted by the IETE-SF committee of our college, was scheduled to go on for 35 hours over 6 days: 21st, 26th,27th, 28th of January and 3rd and 4th of February. This workshop was conducted by Alumni Roma Jain, who is currently working with Jio and Sameer Kadam, who is working with Hotstar. It had 50 active participants willing to imbibe whatever information was given to them.

          The first day of the workshop took off with introduction of the alumni followed by a small surprise in the form of an app made by Sameer which conducted object and face recognition. It was an insight on what awaited us in the upcoming days. The rest of the day was a theory based learning, wherein we were taught on how the face recognition, object recognition and the basic concepts behind all those functions work.

          The next thing on the theory learning target was Python language, which was covered on the second day. The students were taught basic commands and functions of Python language along with the common errors and their debugging. We started off with simple program execution and then moved on to complex program execution such as performing mathematical operations on matrices. The day ended with introduction of Haar Cascade Algorithms.

          On the third day, we were taught about filters and image processing, which are commonly used to suppress either the high frequencies in the image, i.e. smoothing the image, or the low frequencies, i.e. enhancing or detecting edges in the image.Digital image processing is the use of computer algorithms to perform image processing on digital images.

          The fourth day kicked off with introduction of face and eye detection.Face detection is a computer technology being used in a variety of applications that identifies human faces in digital images. To check out the working and precision of these function, testing was done on saved pictures as well on webcam display.

          The fifth day was completely devoted to Facial Recognition. A facial recognition system is a computer application capable of identifying or verifying a person from a digital image or a video frame from a video source. For this a database was needed. We were asked to model our faces in front of the webcam, so as to create a variety of expressions and emotions, these images created the database required for the program. A negative database was also feed to the machine to help it distinguish between features of one person from another. This gave the program learning space to develop on its own.

          The best part was saved for last, coding for emotional recognition was the most awaited program for all the participants. The concept behind it was complicated yet very interesting, and the outcome was exhilarating.  The participants were taught how to apply the concepts of computer vision and machine learning to identify human emotions based on facial expression. This was followed by a general discussion on the Artificial Intelligence domain and the correlation between the concepts of Computer vision and deep learning.        

          Every participant was awarded a participation certificate. This workshop was a huge success as it was not only informative but also interactive, with a lot of practical learning and concept based programming.

Call for Articles

Want to get featured? Send us your name, article, and if you want, social links to [email protected]!

Great! You've successfully subscribed.
Great! Next, complete checkout for full access.
Welcome back! You've successfully signed in.
Success! Your account is fully activated, you now have access to all content.