Author: kdodhia

This week we spent most of the time live testing. We collected new data and tested our system in various lighting conditions. The final results are good and we are hoping that we will have a successful demo on Monday.

This week I spent a lot of time on testing and fine tuning parameters for detection. The cascading classifier has been integrated into the mvp and is producing solid results. I also worked on the face alignment code to help get it integrated into the mvp. A lot of time was spent on live testing the entire system, and fine-tuning all the parts.

This week I made modifications (using help from https://medium.com/datadriveninvestor/understanding-and-implementing-the-viola-jones-image-classification-algorithm-85621f7fe20b) to the facial detection code and retrained the model to create a strong classifier comprising of 75 features. The results were very promising. I achieved 95% accuracy and live testing produced good results. Below is sample output:

Next week, the focus will be solely on raised hand detection. Everything is almost in place and we just need to fine tune algorithms to get higher accuracies.

The previous facial detection code was running too slow so I created a cascading classifier. The classifier works, producing accuracies of 80%. I am waiting for more AWS credit so that I can train the classifier on a larger scale with more images/features. This week was a bit slow, but I hope to catch up next week. I will work with Neeraj to integrate his PCA into the mvp script. I am waiting for waiting to train my cascading classifier before adding it to the mvp script. I will also be working on improving hand raised detection.

My facial detection code has been fully integrated into the mvp script. I made optimizations to the code to increase speeds. I did more research into hand raised detection and how I could improve the results, and have experimented with some of these approaches. I am shifting my attention to hand raised detection for the next week or so. Once we reach the desired accuracy, I will more to the mouth movement detection code.

On schedule.

This week I integrated my facial detection classifier into the MVP.  In addition, I made some changes to improve the accuracy of the classifier. I am still getting a relatively high rate of false-positives, and I have been trying to reduce this by continuing to conduct hard-negative mining and improving the training set. While I have been waiting for the classifier to train on AWS (which takes a couple days), I have also started looking into the raised-hand detection code and how I could improve it. I have started experimenting with some ideas that I found in various research papers.

Over the next week, I plan on retraining my classifier on AWS with my new training set and finish writing the cascading classifiers code. I will also continue working on the raised-hand detection code.

Overall, I think I am on schedule. I have an implementation of facial detection that works and has been integrated into the MVP. I have also began working on the raised-hand detection code. Over the next few weeks the goal will be to work on optimizing results and improving accuracy.

This week I worked on training the classifier on AWS. I set up my AWS, including setting up the environment to be able to run my code. I am training with a dataset of 10k negative and 8k positive images, selecting 400 classifiers. I also incorporated hard negative mining. Specifically, I take any false positives in the test set and add those negative example to my training set. The training is still going on, and should be complete by beginning of the week. Additionally, I began writing code for the cascading classifiers in order to increase detection speeds. Previously, it took around 4seconds to detect all the faces in an image. I optimize this by parallelizing the sliding window search, and hope to further increase performance by using cascading classifiers.

Once the classifier has been trained, I will incorporate my facial detector into the mvp. This should be done by early next week. After this, I will work on improving accuracy for hand detection. Overall, I am slightly behind, but this is mostly because the classifier takes extremely long to train (a couple days). This has hindered my progress the past couple weeks.

• What did you personally accomplish this week on the project?

Since I got back from spring break I have been working on optimizing my facial detection.  In order to increase the accuracy, I changed the dataset used for training and increased the the total number of training examples (1500 positive and 2000 negative). I also made some alterations to the adaboost algorithm. After making these changes, I am getting 88% accuracy for Faces, and 90% accuracy for Non-faces. This is only when  detecting a single face in a 24×24 image. I am using a test set of 500 positive and 500 negative images.

Next, I was working on the sliding window code to detect multiple faces in an image. This is the sample output:

There are multiple overlapping boxes, which is expected. I used Non-maximum suppression to merge overlapping boxes into one. The final output is as follows:

As you can see, there is a high false-positve rate. Additionally, not all the faces were detected. I am currently trying to improve the detection. I will try improve my training set, and use more examples. In addition, I will use more features (currently, I only select 100). The issue with these changes however, is that this will make training much slower.

• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

I think I am slightly behind schedule, as I was hoping to be completely done with detection by this week. This is mostly because I didn’t manage to get much done during spring break. However, I think I can catch up this following week.

• What deliverables do you hope to complete in the next week?

I will continue to optimize to get better accuracy and reduce the number of false-positives. I will also integrate my code into the MVP script.

18500-Design-Review-Report

• What did you personally accomplish this week on the project?

This was a short week for me since I have been traveling since Wednesday. This week I continued my work on the facial detection code. I have finished coding the Ada-boost classifier that works decently well. I am getting 95% accuracy for Faces, and 50% accuracy for Non-faces. Currently the code is only able to detect a single face in a 24×24 image. The next steps will be to write the sliding window code so that multiple faces can be detected in larger images. I used https://github.com/Simon-Hohberg/Viola-Jones to help guide my implementation.

• Is your progress on schedule or behind? If you are behind, what actions will be taken to catch up to the project schedule?

I think I am on schedule to fully implement a working version of the facial detection by the first week after spring break.

• What deliverables do you hope to complete in the next week?

As mentioned earlier, I have written a classifier that works with images containing a single face. I will now work on the sliding window code to detect multiple faces in a larger image. Once the sliding window is complete, I will continue to optimize to get better accuracy and reduce the number of false-positives.