CIS520 Final Project Report
نویسندگان
چکیده
The task of gender and age classification based on texts and facial images has been studied extensively in the natural language processing community and the computer vision community respectively. Machine learning algorithms are particularly relevant in solving such classification problems. In the final project for CIS520 Machine Learning, we are presented with the task of gender and age classification in (1) blog postings, and (2) facial images. Our group conducted research on current literature and implemented prediction algorithms for the above tasks, using techniques such as tfidf, kNN, eigenfaces and SVM. We achieved decent classification results and successfully beat all 4 baseline requirements. This report will describe in detail our methods and findings.
منابع مشابه
Final Project Report of the DFG-Transferbereich 42:
This final project report summarizes the objectives, realization, and the results of the DFG-Transferbereich 42. The report describes the flames considered, flame simulations, and results of flame simulations. A summary of project publication records, the transfer of project results and planned future activities will be also given.
متن کاملForecasting Final Schedule and Cost of Projects by Using Statistical and Mathematical Method
Earned value management (EVM) has prepared some methods to forecast final costs of projects. These methods were not developed since the start of formation and were gradually completed, of course with one exception that is its authenticity, they are still remained unchanged. At the present time EVM guide does not apply from schedule indices to forecast schedule for completion of project and ...
متن کاملMath 521: Group Final Project Report: Is It a Cat or a Dog?
This report documents the methods we used to process the cat/dog images and build classifiers for the Spring 2012 group final project for Math 521.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2009