CS 229 Project : Object ( Keyboard ) Identification in
نویسنده
چکیده
In this project, an object detection algorithm is implemented. The algorithm is capable of locating keyboards in images. Main component of the algorithm is based on GMM models which can be applied to objects other than keyboards as well, while parts of the algorithm is heuristics based on the characteristics of the keyboard object. The algorithm achieved 80% detection rate for this task.
منابع مشابه
YoloFlow Real - time Object Tracking in Video CS 229 Course Project
We reimplement YOLO, a fast, accurate object detector, in TensorFlow. To perform inference, we leverage weights that were trained for over one week on GPUs using ImageNet data, a publicly-available dataset containing several million natural images. We demonstrate the ability to reproduce detections comparable with the original implementation. We learn the parameters of the network and compare m...
متن کاملCS 229 = = Final Project Report SPEECH & NOISE SEPARATION
In this course project I investigated machine learning approaches on separating speech signals from background noise. Keywords—MFCC, SVM, noise separation, source separation, spectrogram
متن کاملSpectral Learning of General Latent-Variable Probabilistic Graphical Models:A Supervised Learning Approach
In this CS 229 project, I designed, proved and tested a new spectral learning algorithm for learning probabilistic graphical models with latent variables by reducing the hard learning problem into a pipeline of supervised learning tasks. This new algorithmic framework can provide us with more learning power by giving us the freedom to plug in all different kinds of supervised learning algorithm...
متن کامل