Tejas Phase | Shivaji University, Kolhapur, India (original) (raw)
Phone: 9657769508
Address: Green Valley Apt. F-31, Sadar Bazar, Satara.
less
Uploads
Papers by Tejas Phase
International Journal of Engineering Research & Technology (IJERT), 2019
There are superior pre-trained HAAR-Cascade classifiers available on the Internet whose detection... more There are superior pre-trained HAAR-Cascade classifiers available on the Internet whose detection accuracy is quite impressive for the task of face detection in the presence of different illuminations conditions and different poses of the face. But the drawback to using such pre-trained classifies for any detection task is we never know how training of such classifiers can be done, how to prepare the dataset for a particular detection task and how to use different parameters of the classifiers while training. In this paper, we build our own Custom HAAR-Cascade Classifier using "Cascade Trainer GUI (a tool designed by Amin Ahmadi) to detect face/faces in any given image/images. We also create a dataset which includes positive and negative samples to use during training purpose. We also demonstrate how to retrain the classifier after analyzing the error matrix after each detection stage and how to increase the accuracy of the classifier in detection work.
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2019
This paper aims to detect the face in the given image and in live video. For this purpose, we are... more This paper aims to detect the face in the given image and in live video. For this purpose, we are using a pre-trained "Haar Cascade Classifier" to locate face/faces in the image and in live video. But before this, we are doing "Image Processing" for the purpose of Input Pre-processing. And then Image Enhancement to correct Non-uniform illuminations and then use pre-trained Cascade-Classifier to locate face/faces and eyes in the image and in live video.
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2019
Many social programs have a hard time making sure the right people receive the enough financial a... more Many social programs have a hard time making sure the right people receive the enough financial aid. It's tricky when a program focuses on the poorest segment of the population. This segment of population can't provide the necessary income and expense records to prove that they qualify to receive any financial aid under particular Govt. scheme. In this paper we predict someone's "Income Level" using the "Random Forest Classifier" based on the various attributes or features.
International Journal of Engineering Research & Technology (IJERT), 2019
There are superior pre-trained HAAR-Cascade classifiers available on the Internet whose detection... more There are superior pre-trained HAAR-Cascade classifiers available on the Internet whose detection accuracy is quite impressive for the task of face detection in the presence of different illuminations conditions and different poses of the face. But the drawback to using such pre-trained classifies for any detection task is we never know how training of such classifiers can be done, how to prepare the dataset for a particular detection task and how to use different parameters of the classifiers while training. In this paper, we build our own Custom HAAR-Cascade Classifier using "Cascade Trainer GUI (a tool designed by Amin Ahmadi) to detect face/faces in any given image/images. We also create a dataset which includes positive and negative samples to use during training purpose. We also demonstrate how to retrain the classifier after analyzing the error matrix after each detection stage and how to increase the accuracy of the classifier in detection work.
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2019
This paper aims to detect the face in the given image and in live video. For this purpose, we are... more This paper aims to detect the face in the given image and in live video. For this purpose, we are using a pre-trained "Haar Cascade Classifier" to locate face/faces in the image and in live video. But before this, we are doing "Image Processing" for the purpose of Input Pre-processing. And then Image Enhancement to correct Non-uniform illuminations and then use pre-trained Cascade-Classifier to locate face/faces and eyes in the image and in live video.
International Journal for Research in Applied Science & Engineering Technology (IJRASET), 2019
Many social programs have a hard time making sure the right people receive the enough financial a... more Many social programs have a hard time making sure the right people receive the enough financial aid. It's tricky when a program focuses on the poorest segment of the population. This segment of population can't provide the necessary income and expense records to prove that they qualify to receive any financial aid under particular Govt. scheme. In this paper we predict someone's "Income Level" using the "Random Forest Classifier" based on the various attributes or features.