In this paper, we present an approach to automatic detection and recognition of signs from natural scenes, and its application to a sign translation task. The proposed approach embeds multiresolution and multiscale edge detection, adaptive searching, color analysis, and affine rectification in a hierarchical framework for sign detection, with different emphases at each phase to handle the text in different sizes, orientations, color distributions and backgrounds. We use affine rectification to recover deformation of the text regions caused by an inappropriate camera view angle. The procedure can significantly improve text detection rate and optical character recognition (OCR) accuracy. Instead of using binary information for OCR, we extract features from an intensity image directly. We propose a local intensity normalization method to effectively handle lighting variations, followed by a Gabor transform to obtain local features, and finally a linear discriminant analysis (LDA) method for feature selection. We have applied the approach in developing a Chinese sign translation system, which can automatically detect and recognize Chinese signs as input from a camera, and translate the recognized text into English.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1109/tip.2003.819223 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Computer vision based automatic evaluation method of YO steel coating performance with SEM image.
Sci Rep
January 2025
State Key Laboratory of Baiyunobo Rare Earth Resource Researches and Comprehensive Utilization, Baotou Research Institute of Rare Earths, Baotou, 014030, China.
This study introduces a deep learning-based automatic evaluation method for analyzing the microstructure of steel with scanning electron microscopy (SEM), aiming to address the limitations of manual marking and subjective assessments by researchers. By leveraging advanced computer vision algorithms, specifically a suitable model for long-term dendritic solidifications named Tang Rui Detect (TRD), the method achieves efficient and accurate detection and quantification of microstructure features. This approach not only enhances the training process but also simplifies loss function design, ultimately leading to a proper evaluation of surface modifications in steel materials.
View Article and Find Full Text PDFAn efficient deep learning system for automatic detection of Acute Lymphoblastic Leukemia.
ISA Trans
January 2025
Department of Electronics and Telecommunication, C. V. Raman Global University, Bhubaneswar 752054, Odisha, India. Electronic address:
Early and highly accurate detection of rapidly damaging deadly disease like Acute Lymphoblastic Leukemia (ALL) is essential for providing appropriate treatment to save valuable lives. Recent development in deep learning, particularly transfer learning, is gaining a preferred trend of research in medical image processing because of their admirable performance, even with small datasets. It inspires us to develop a novel deep learning-based leukemia detection system in which an efficient and lightweight MobileNetV2 is used in conjunction with ShuffleNet to boost discrimination ability and enhance the receptive field via convolution layer succession.
View Article and Find Full Text PDFDetection of Glycopeptide Resistance and Virulence Genes in Enterococci Isolated from Cheese and Investigation of the Clonal Relationship of E. faecium Species with Rectal Surveillance Isolates.
Microb Pathog
January 2025
Kahramanmaraş Sütçü İmam University, Technical Sciences Vocational School, Department of Food Processing, Kahramanmaraş, Türkiye. Electronic address:
Objective: This study aimed to investigate the presence of glycopeptide resistance and virulence genes in Enterococcus spp. isolated from cheese and the clonal relationship of E. faecium species with rectal surveillance isolates.
View Article and Find Full Text PDFAutomatic medical imaging segmentation via self-supervising large-scale convolutional neural networks.
Radiother Oncol
January 2025
Department of Radiation Oncology and Winship Cancer Institute, Emory University, Atlanta, GA 30322, USA; Department of Biomedical Engineering, Emory University and Georgia Institute of Technology Atlanta, GA 30308, USA. Electronic address:
Purpose: This study aims to develop a robust, large-scale deep learning model for medical image segmentation, leveraging self-supervised learning to overcome the limitations of supervised learning and data variability in clinical settings.
Methods And Materials: We curated a substantial multi-center CT dataset for self-supervised pre-training using masked image modeling with sparse submanifold convolution. We designed a series of Sparse Submanifold U-Nets (SS-UNets) of varying sizes and performed self-supervised pre-training.
Examining tobacco use at the intersection of gender, sexual orientation, race, and ethnicity using national U.S. data of sexual and gender diverse youth.
Addict Behav
January 2025
University of Connecticut, Storrs, CT, USA.
Objectives: To expand the literature documenting that tobacco use inequities persist and continue to increase for minoritized youth populations by exploring patterns of tobacco use across multiple intersections of sexual, gender, racial, and ethnic identities. Studies with this focus are needed to understand the degree to which tobacco use varies across groups who hold multiple minoritized identities.
Methods: The current study used a novel analytical approach- Exhaustive Chi-square Automatic Interaction Detection - to examine lifetime cigarette use among a U.
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!