Real-Time Object Recognition Using Deep-Learning

Named Entity Recognition in Persian Text using Deep Learning

Named entities recognition is a fundamental task in the field of natural language processing. It is also known as a subset of information extraction. The process of recognizing named entities aims at finding proper nouns in the text and classifying them into predetermined classes such as names of people, organizations, and places. In this paper, we propose a named entity recognizer which benefi...

Real Time Object Recognition

Deep Learning Based Real-time Object Recognition System with Image Web Crawler

Recently, deep learning algorithm becomes a great solution for various field. Convolutional Neural Network (CNN), a kind of neural network, is known as suitable method for image processing. This paper proposes a realtime object recognition system with CNN. Since many images are needed for deep learning, this system contains image web crawler that collects images automatically. This paper will s...

Real-time activity recognition via deep learning of motion features

Activity recognition is a challenging computer vision problem with countless applications. Here we present a real time activity recognition system using deep learning of local motion feature representations. Our approach learns to directly extract energy based motion features from video blocks. We implement the system on a distributed computing architecture and evaluate its performance on the i...

Real-time object recognition using a modified generalized Hough transform

An approach for real-time object recognition in digital images based on the principle of the generalized Hough transform is proposed. It combines robustness against occlusions, distortions, and noise with invariance under rigid motion and local illumination changes. The computational effort is reduced by employing a novel efficient limitation of the search space in combination with a hierarchic...