Active Scene Text Recognition for a Domestic Service Robot
نویسندگان
چکیده
We developed a scene text recognition system with active vision capabilities, namely: auto-focus, adaptive aperture control and auto-zoom. Our localization system is able to delimit text regions in images with complex backgrounds, and is based on an attentional cascade, asymmetric adaboost, decision trees and Gaussian mixture models. We think that text could become a valuable source of semantic information for robots, and we aim to raise interest in it within the robotics community. Moreover, thanks to the robot's pan-tilt-zoom camera and to the active vision behaviors, the robot can use its a ordances to overcome hindrances to the performance of the perceptual task. Detrimental conditions, such as poor illumination, blur, low resolution, etc. are very hard to deal with once an image has been captured and can often be prevented. We evaluated the localization algorithm on a public dataset and one of our own with encouraging results. Furthermore, we o er an interesting experiment in active vision, which makes us consider that active sensing in general should be considered early on when addressing complex perceptual problems in embodied agents.
منابع مشابه
Extracting Low Resolution Text with an Active Camera for OCR
Reading text in any scene is useful in the context of wearable computing, robotic vision or as an aid for visually handicapped people. Here, we present a novel automatic text reading system using an active camera focused on text regions already located in the scene (using our recent work). A region of text found is analysed to determine the optimal zoom that would foveate onto it. Then a number...
متن کاملAutonomous Knowledge Acquisition of a Service Robot by Probabilistic Perception Planning
This paper presents a concept for active scene modeling by autonomous knowledge acquisition of a service robot in a kitchen scenario. Perceiving complex scenes with multiple objects at arbitrary positions is often difficult from a single measurement due to object ambiguities, object occlusions or environmental influences. The incorporation of several sequential measurements helps to improve sce...
متن کاملRobot Arm Performing Writing through Speech Recognition Using Dynamic Time Warping Algorithm
This paper aims to develop a writing robot by recognizing the speech signal from the user. The robot arm constructed mainly for the disabled people who can’t perform writing on their own. Here, dynamic time warping (DTW) algorithm is used to recognize the speech signal from the user. The action performed by the robot arm in the environment is done by reducing the redundancy which frequently fac...
متن کاملUsing Spatial Context Knowledge in Gesture Recognition for Commanding a Domestic Service Robot
متن کامل
Johnny: An Autonomous Service Robot for Domestic Environments
In this article we describe the architecture, algorithms and real-world benchmarks performed by Johnny Jackanapes, an autonomous service robot for domestic environments. Johnny serves as a research and development platform to explore, develop and integrate capabilities required for real-world domestic service applications. We present a control architecture which allows to cope with various and ...
متن کامل