This paper proposes a method to recognize digits in a natural scene, such as telephone numbers on a signboard. Candidate regions of digits are extracted from an image through contrast enhancement, edge extraction, and labeling. Since the target text patterns are in a 3D space, unlike traditional character recognition problems, we have to deal with the image transformation effect due to the orientation in the 3D space and projection. We have to cancel the effect as much as possible before digit recognition. In our method, the image transformation effect is modeled as skew and slant. In the proposed method, simplified Hough transform is used for the skew normalization. After the skew normalization, the remaining effect of image transformation is corrected by circumscribing digit patterns with tilted rectangles and affine transformation. In experiments, we tested a total of 1,332 images of signboards with 11,939 digits. We obtained a digit extraction rate of 99.2% and a correct digit recognition rate of 98.8%.Received: 15 December 2003, Accepted: 21 October 2004, Published online: 2 February 2005 相似文献
A pattern recognition system has been developed which is capable of recognizing high contrast two-dimensional visual patterns and which is insensitive to the translation, rotation and size of a pattern. The unique characteristics of the system are its speed, its low cost and the fact that it is completely self-contained.
A new technique for image recognition, suitable for applications such as industrial robotics, is presented. The technique provides invariance to rotation, translation and magnification of the image. An intelligent camera system is used to input an image, to center it, to normalize it with respect to size and to convert it into polar coordinate form. The image is then integrated over r and θ to provide two orthogonal profiles. The input profiles are compared to the reference images using a threshold comparison technique designed to provide a simple hardware implementation. Rotation of the image is handled by a one-dimensional shifting of the radial profile.
Seven experiments were performed to test the system. The results of these experiments are discussed and possible improvements to the system are suggested. 相似文献
An automatic mosaic acquisition and processing system for a multiphoton microscope is described for imaging large expanses of biological specimens at or near the resolution limit of light microscopy. In a mosaic, a larger image is created from a series of smaller images individually acquired systematically across a specimen. Mosaics allow wide‐field views of biological specimens to be acquired without sacrificing resolution, providing detailed views of biological specimens within context. The system is composed of a fast‐scanning, multiphoton, confocal microscope fitted with a motorized, high‐precision stage and custom‐developed software programs for automatic image acquisition, image normalization, image alignment and stitching. Our current capabilities allow us to acquire data sets comprised of thousands to tens of thousands of individual images per mosaic. The large number of individual images involved in creating a single mosaic necessitated software development to automate both the mosaic acquisition and processing steps. In this report, we describe the methods and challenges involved in the routine creation of very large scale mosaics from brain tissue labelled with multiple fluorescent probes. 相似文献