- 标题
- 摘要
- 关键词
- 实验方案
- 产品
-
Optical Character Recognition System for Nastalique Urdu-Like Script Languages using Supervised Learning
摘要： There are two main techniques to convert written or printed text into digital format. The first technique is to create an image of written/printed text, but images are large in size so they require huge memory space to store, also text in image form cannot be further processed like edit, search, copy etc. The second technique is to use an Optical Character Recognition (OCR) system. OCR’s can read documents and convert manual text documents into digital text and this digital text can be processed to extract knowledge. A huge amount of Urdu language’s data is available in handwritten or in printed form that needs to be converted into digital format for knowledge acquisition. Highly cursive, complex structure, bi-directionality, and compound in nature etc. make the Urdu language too complex to obtain accurate OCR results. In this study supervised learning based OCR system is proposed for Nastalique Urdu language. The proposed system’s evaluations under variety of experimental settings apprehend 98.4 % accuracy, which is highest recognition rate ever achieved by any Urdu language OCR system. The proposed system is simple to implement especially in software front of OCR system also the proposed technique is useful for printed text as well as handwritten text and it will help for developing more accurate Urdu OCR’s software systems in the future.
关键词： Optical Character Recognition (OCR),Image Processing,Urdu Nastalique,Supervised Learning,Pattern Recognition
更新于2025-09-23 15:23:52
-
[Lecture Notes in Computer Science] Advances in Soft Computing Volume 10632 (16th Mexican International Conference on Artificial Intelligence, MICAI 2017, Enseneda, Mexico, October 23-28, 2017, Proceedings, Part I) || A Survey of Machine Learning Approaches for Age Related Macular Degeneration Diagnosis and Prediction
摘要： Age Related Macular Degeneration (AMD) is a complex disease caused by the interaction of multiple genes and environmental factors. AMD is the leading cause of visual dysfunction and blindness in developed countries, and a rising cause in underdeveloped countries. Currently, retinal images are studied in order to identify drusen in the retina. The classification of these images allows to support the medical diagnosis. Likewise, genetic variants and risk factors are studied in order to make predictive studies of the disease, which are carried out with the support of statistical tools and, recently, with Machine Learning (ML) methods. In this paper, we present a survey of studies performed in complex diseases under both approaches, especially for the case of AMD. We emphasize the approach based on the genetic variants of individuals, as it is a support tool for the prevention of AMD. According to the vision of personalized medicine, disease prevention is a priority to improve the quality of life of people and their families, as well as to avoid the inherent health burden.
关键词： Predictive diagnosis,Machine Learning,Classification,Automated diagnosis,Pattern recognition,AMD
更新于2025-09-23 15:23:52
-
Adaptive Fuzzy Switching Noise Reduction Filter for Iris Pattern Recognition
摘要： Noise reduction is a necessary procedure for the iris recognition systems. This paper proposes an adaptive fuzzy switching noise reduction (AFSNR) filter to reduce noise for iris pattern recognition. The proposed low complexity AFSNR filter removes noise pixels by fuzzy switching between an adaptive median filter and the filling method. The threshold values of AFSNR filter are calculated on the basis of the histogram statistics of eyelashes, pupils, eyelids, and light illumination. The experimental results on the CASIA V3.0 iris database, with genuine acceptance rate equals 99.72%, show the success of the proposed method.
关键词： fuzzy switching median,iris normalization,eyelash detection,fuzzy weighted median,noise reduction,Iris pattern recognition
更新于2025-09-23 15:23:52
-
Visibility graphs for image processing
摘要： The family of image visibility graphs (IVG/IHVGs) have been recently introduced as simple algorithms by which scalar fields can be mapped into graphs. Here we explore the usefulness of such an operator in the scenario of image processing and image classification. We demonstrate that the link architecture of the image visibility graphs encapsulates relevant information on the structure of the images and we explore their potential as image filters. We introduce several graph features, including the novel concept of Visibility Patches, and show through several examples that these features are highly informative, computationally efficient and universally applicable for general pattern recognition and image classification tasks.
关键词： image visibility graphs,image processing,pattern recognition,graph features,visibility patches,image classification
更新于2025-09-23 15:22:29
-
A Novel Regularized Nonnegative Matrix Factorization for Spectral-Spatial Dimension Reduction of Hyperspectral Imagery
摘要： Dimension reduction (DR) is an essential preprocessing for hyperspectral image (HSI) classification. Recently, nonnegative matrix factorization (NMF) has been shown as an effective tool for the DR of hyperspectral data given the fact that it provides interpretable results. However, the basic NMF ignores the geometric structure information of the HSI data, thus limiting its performance. To this end, a novel regularized NMF method, termed NMF with adaptive graph regularizer (NMFAGR), is proposed for the spectral-spatial dimension reduction of hyperspectral data in this paper. Specifically, to enhance the preservation ability of the geometric structure information, the NMFAGR performs the dimension reduction and graph learning simultaneously. Regarding the mutual correlation between these two tasks, a graph regularizer is added as an interaction. Moreover, to effectively utilize complementary information among spectral-spatial features, the NMFAGR allocates feature weight factors automatically without requiring any additional parameters. An efficient algorithm is utilized to solve the optimization problem. The effectiveness of the proposed method is demonstrated on three benchmark hyperspectral data sets through experimentation.
关键词： Hyperspectral images,feature extraction,pattern recognition
更新于2025-09-23 15:22:29
-
[IEEE 2018 19th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM) - Erlagol (2018.6.29-2018.7.3)] 2018 19th International Conference of Young Specialists on Micro/Nanotechnologies and Electron Devices (EDM) - The Problem of Biometric Identification of a Subject and Subject's Changed State: Perspectives of New Features Application in Analysis of Face and Neck Thermograms
摘要： The analysis of the current state in the field of subjects biometric identification is provided. The main methods of biometric identification, the process of features space formation used subsequently for decision-making on the subject's access to system resources, as well as new approaches to the use of biometric images for protection of data on electronic documents are considered. The new problem of identification of subject’s changed state, and perspectives of using subjects’ thermal images for the purpose of determining changed state, is discussed.
关键词： Pattern recognition,biometric identification,face thermal images,encryption key,user’s variant state detection
更新于2025-09-23 15:22:29
-
[IEEE 2017 International Conference on Computational Science and Computational Intelligence (CSCI) - Las Vegas, NV, USA (2017.12.14-2017.12.16)] 2017 International Conference on Computational Science and Computational Intelligence (CSCI) - Estimation of Illumination Map from Dermoscopy Images for Extracting Differential Structures Using Gabor Local Mesh Patterns
摘要： Melanoma is the most deadly form of skin cancer and its incidence rate is significantly increasing. The design of an assisted diagnosis system for the detection of melanoma is a challenging task involving various steps related to computer vision. Researchers have concluded that the accurate identification of melanoma requires robust preprocessing steps on dermoscopy images including hair removal, illumination correction etc., that can help in a better detection of melanoma. In this paper, we propose a novel illumination correction algorithm followed by robust feature extraction from dermoscopy images, leading to a better identification of cancer. Illumination correction is based on statistical estimation of illumination content in the images, followed by the extraction of differential structures using a combination of Gabor filtering followed by extracting local mesh patterns, which exhibit physiological significance based on various clinical rules for detecting melanoma. Our experiments show that the proposed technique outperforms all the other methods that have been considered in this paper.
关键词： Texture analysis,Optimization,Pattern recognition,Gabor filters,Melanoma
更新于2025-09-23 15:22:29
-
An artificial retina processor for track reconstruction at the LHC crossing rate
摘要： The goal of the INFN-RETINA R&D project is to develop and implement a computational methodology that allows to reconstruct events with a large number (> 100) of charged-particle tracks in pixel and silicon strip detectors at 40 MHz, thus matching the requirements for processing LHC events at the full bunch-crossing frequency. Our approach relies on a parallel pattern-recognition algorithm, dubbed artificial retina, inspired by the early stages of image processing by the brain. In order to demonstrate that a track-processing system based on this algorithm is feasible, we built a sizable prototype of a tracking processor tuned to 3 000 patterns, based on already existing readout boards equipped with Altera Stratix III FPGAs. The detailed geometry and charged-particle activity of a large tracking detector currently in operation are used to assess its performances. We report on the test results with such a prototype.
关键词： track reconstruction,artificial retina,pattern recognition,LHC,FPGA
更新于2025-09-23 15:21:21
-
Artificial optic-neural synapse for colored and color-mixed pattern recognition
摘要： The priority of synaptic device researches has been given to prove the device potential for the emulation of synaptic dynamics and not to functionalize further synaptic devices for more complex learning. Here, we demonstrate an optic-neural synaptic device by implementing synaptic and optical-sensing functions together on h-BN/WSe2 heterostructure. This device mimics the colored and color-mixed pattern recognition capabilities of the human vision system when arranged in an optic-neural network. Our synaptic device demonstrates a close to linear weight update trajectory while providing a large number of stable conduction states with less than 1% variation per state. The device operates with low voltage spikes of 0.3 V and consumes only 66 fJ per spike. This consequently facilitates the demonstration of accurate and energy efficient colored and color-mixed pattern recognition. The work will be an important step toward neural networks that comprise neural sensing and training functions for more complex pattern recognition.
关键词： optic-neural synaptic device,human vision system,pattern recognition,energy efficiency,h-BN/WSe2 heterostructure
更新于2025-09-23 15:21:21
-
[IEEE 2019 International Conference on Numerical Simulation of Optoelectronic Devices (NUSOD) - Ottawa, ON, Canada (2019.7.8-2019.7.12)] 2019 International Conference on Numerical Simulation of Optoelectronic Devices (NUSOD) - Design and Modeling of 1 Gbps Directed Optical XOR/OR Gates Using Integrated Semiconductor Ring Lasers
摘要： In this paper, we formulate a novel time series representation framework that captures the inherent data dependency of time series and that can be easily incorporated into existing statistical classification algorithms. The impact of the proposed data representation stage in the solution to the generic underlying problem of time series classification is investigated. The proposed framework, which we call structural generative descriptions moves the structural time series representation to the probability domain, and hence is able to combine statistical and structural pattern recognition paradigms in a novel fashion. Two algorithm instantiations based on the proposed framework are developed. The algorithms are tested and compared using different publicly available real-world benchmark data. Results reported in this paper show the potential of the proposed representation framework, which in the experiments investigated, performs better or comparable to state-of-the-art time series description techniques.
关键词： structural generative descriptions (SGDs),time series representation,time series classification,Statistical-structural pattern recognition
更新于2025-09-23 15:21:01