Using A KNN and MOG Based Algorithm for Static Hand Posture Recognition

نویسنده

  • Abhishek Ranjan
چکیده

Several machine learning algorithms have been applied to the problem of static hand posture recognition. K-nearesr neighbor (KNN) performs very well in flexible posture recognition, but speed and memory requirements of the algorithm make it difficult to use in real time applications. In this paper we propose an approach to speed up the KNN without changing its behavior. We use the mixture of gaussians (MOG) to model the input training data and apply KNN on this model.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Controlling Computer Music Player Based On Human Hand Activity by Using CAMSHIFT Algorithm

The intent of the paper is to apply computer vision technique to control the music player by CAMSHIFT algorithm. Based on the human hand activity, gesture and posture recognition are used to communicate with computers. Gesture is the physical movement of a hand, expressive of an idea. Posture is the static morph of a hand. In this paper skin colour segmentation is used for hand detection, after...

متن کامل

Estimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks

Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...

متن کامل

یک سیستم نوین هوشمند تشخیص هویت نویسنده فارسی زبان بر اساس سبک نوشتاری - مقاله برگزیده هفدهمین کنفرانس ملی انجمن کامپیوتر ایران

The rapid development of communication by the Internet and the misuse of the anonymity embedded in the nature of online written documents have led to serious security issues. Anonymous identity of the Internet tools such as emails, blogs, and Web sites have made them target methods of interest for criminal activities. On the other hand, world social and political relations have made a great int...

متن کامل

Vision-Based Algorithm for Real-Time Hand Posture Recognition

Importance of human-computer interaction (HCI) systems is increasing since they revolutionized the way people interact with computers. Gesture and posture analysis, especially hand gesture and posture recognition, is one of the more recent areas in the HCI with ever widening field of applications. In this paper we propose an algorithm for hand posture recognition that is based on skin detection...

متن کامل

Face Recognition in Thermal Images based on Sparse Classifier

Despite recent advances in face recognition systems, they suffer from serious problems because of the extensive types of changes in human face (changes like light, glasses, head tilt, different emotional modes). Each one of these factors can significantly reduce the face recognition accuracy. Several methods have been proposed by researchers to overcome these problems. Nonetheless, in recent ye...

متن کامل

ذخیره 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 2003