Text-pose estimation in 3D using edge-direction distributionsBulacu, M. L. & Schomaker, L. R. B., 2005, Proceedings of the International Conference on Image Analysis and Recognition (ICIAR 2005). Kamel, M. & Campilho, A. (eds.). BERLIN: Springer, Vol. LNCS 3656. p. 625-634 10 p. (Lecture Notes in Computer Science; vol. 3656).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Academic › peer-review
This paper presents a method for estimating the orientation of planar text surfaces using the edge-direction distribution (EDD) extracted from the image as input to a neural network. We consider canonical rotations and we developed a mathematical model to analyze how the EDD changes with the rotation angle under orthographic projection. In order to improve performance and solve quadrant ambiguities, we adopt an active-vision approach by considering a pair of images (instead of only one) with a slight rotation difference between them. We then use the difference between the two EDDs as input to the network. Starting with camera-captured front-parallel images with text, we apply single-axis synthetic rotations to verify the validity of the EDD transform model and to train and test the network. The presented text-pose estimation method is intended to provide navigation guidance to a mobile robot capable of reading the textual content encountered in its environment.
|Title of host publication||Proceedings of the International Conference on Image Analysis and Recognition (ICIAR 2005)|
|Editors||M. Kamel, A. Campilho|
|Place of Publication||BERLIN|
|Number of pages||10|
|Publication status||Published - 2005|
|Event||2nd International Conference on Image Analysis and Recognition - , Canada|
Duration: 28-Sep-2005 → 30-Sep-2005
|Name||Lecture Notes in Computer Science|
|Other||2nd International Conference on Image Analysis and Recognition|
|Period||28/09/2005 → 30/09/2005|
2nd International Conference on Image Analysis and Recognition
28/09/2005 → 30/09/2005Canada