Text extraction and character recognition in manuscripts are a very important part of image processing and pattern recognition. The recently proposed Gamma Correction Method (GCM) is a popular method used in the processing of a color image and in particular in the extraction of text from a complex image. However, The GCM consumes a lot of time to extract the text and this is because of the complex calculations of different operations in the different blocks of GCM which is not suitable to real-time applications. In this paper, we propose an efficient Gamma Correction Method acceleration. Our proposal allows to minimize the GCM execution time while ensuring the same reliability of the initial version. The experimental results show an important optimization compared to the literature.
This paper presents hardware (HW) architecture for fast parallel computation of Gray Level Cooccurrence Matrix (GLCM) in high throughput image analysis applications. GLCM has proven to be a powerful basis for use in texture classification. Various textural parameters calculated from the GLCM help understand the details about the overall image content. However, the calculation of GLCM is very computationally intensive. In this paper, an FPGA accelerator for fast calculation of GLCM is designed and implemented. We propose an FPGA-based architecture for parallel computation of symmetric cooccurrence matrices. This architecture was implemented on a Xilinx Zedboard and Virtex 5 FPGAs using Vivado HLS. The performance is then compared against other implementations. The validation results show an optimization on the order of 33% in latency number by contribution to the literature implementation.
International audienceIn this paper, we present a complexity study of the Gamma correction method for automatic text extraction from complex images. This study is based on the build of a simple and adequate algorithm for future hardware solution. Then, a profiling study for each function of the proposed solution was done. After validation, using C/C++ environment, a comparison with the OpenCV based algorithm developed by ESIEE Paris was performed. We show a clear improvement in the run time. Profiling and experimental results, using diverse images prove that our study achieves an excellent balancebetween simplicity, precision, and computational speed.This study will be operated in the future work of hardware implementation
In the context of constructing an embedded system to help visually impaired people to interpret text, in this paper, an efficient High-level synthesis (HLS) Hardware/Software (HW/SW) design for text extraction using the Gamma Correction Method (GCM) is proposed. Indeed, the GCM is a common method used to extract text from a complex color image and video. The purpose of this work is to study the complexity of the GCM method on Xilinx ZCU102 FPGA board and to propose a HW implementation as Intellectual Property (IP) block of the critical blocks in this method using HLS flow with taking account the quality of the text extraction. This IP is integrated and connected to the ARM Cortex-A53 as coprocessor in HW/SW codesign context. The experimental results show that the HLS HW/SW implementation of the GCM method on ZCU102 FPGA board allows a reduction in processing time by about 89% compared to the SW implementation. This result is given for the same potency and strength of SW implementation for the text extraction.
This paper presents an FPGA accelerator based on circular buffer unit per orientation for a fast and optimized Gray Level Co-occurrence Matrix (GLCM) and four Texture features computation. The Four texture features namely, contrast, energy, dissimilarity and correlation are computed using Xilinx FPGA. However, the computation of GLCM and four textures features are very complex and consume a lot of execution time. In this paper, an FPGA accelerator for fast computation of GLCM and four texture features are designed and implemented. This architecture was implemented on a Xilinx Zc-702 using Vivado HLS. The obtained results are then compared against other related works. The synthesis results on FPGA prove a significant gain (about 17%) in execution time compared to the previous work.
The challenge faced by the visually impaired persons in their day-today lives is to interpret text from documents. In this context, to help these people, the objective of this work is to develop an efficient text recognition system that allows the isolation, the extraction, and the recognition of text in the case of documents having a textured background, a degraded aspect of colors, and of poor quality, and to synthesize it into speech. This system basically consists of three algorithms: a text localization and detection algorithm based on mathematical morphology method (MMM); a text extraction algorithm based on the gamma correction method (GCM); and an optical character recognition (OCR) algorithm for text recognition. A detailed complexity study of the different blocks of this text recognition system has been realized. Following this study, an acceleration of the GCM algorithm (AGCM) is proposed. The AGCM algorithm has reduced the complexity in the text recognition system by 70% and kept the same quality of text recognition as that of the original method. To assist visually impaired persons, a graphical interface of the entire text recognition chain has been developed, allowing the capture of images from a camera, rapid and intuitive visualization of the recognized text from this image, and text-to-speech synthesis. Our text recognition system provides an improvement of 6.8% for the recognition rate and 7.6% for the F-measure relative to GCM and AGCM algorithms.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.