Statistical feature extraction based iris recognition system

Iris recognition systems have been proposed by numerous researchers using different feature extraction techniques for accurate and reliable biometric authentication. In this paper, a statistical feature extraction technique based on correlation between adjacent pixels has been proposed and implemented. Hamming distance based metric has been used for matching. Performance of the proposed iris recognition system (IRS) has been measured by recording false acceptance rate (FAR) and false rejection rate (FRR) at different thresholds in the distance metric. System performance has been evaluated by computing statistical features along two directions, namely, radial direction of circular iris region and angular direction extending from pupil to sclera. Experiments have also been conducted to study the effect of number of statistical parameters on FAR and FRR. Results obtained from the experiments based on different set of statistical features of iris images show that there is a significant improvement in equal error rate (EER) when number of statistical parameters for feature extraction is increased from three to six. Further, it has also been found that increasing radial/angular resolution, with normalization in place, improves EER for proposed iris recognition system.     

Convolutional Neural Network Based Intelligent Handwritten Document Recognition

This paper presents a handwritten document recognition system based on the convolutional neural network technique. In today’s world, handwritten document recognition is rapidly attaining the attention of researchers due to its promising behavior as assisting technology for visually impaired users. This technology is also helpful for the automatic data entry system. In the proposed system prepared a dataset of English language handwritten character images. The proposed system has been trained for the large set of sample data and tested on the sample images of user-defined handwritten documents. In this research, multiple experiments get very worthy recognition results. The proposed system will first perform image pre-processing stages to prepare data for training using a convolutional neural network. After this processing, the input document is segmented using line, word and character segmentation. The proposed system get the accuracy during the character segmentation up to 86%. Then these segmented characters are sent to a convolutional neural network for their recognition. The recognition and segmentation technique proposed in this paper is providing the most acceptable accurate results on a given dataset. The proposed work approaches to the accuracy of the result during convolutional neural network training up to 93%, and for validation that accuracy slightly decreases with 90.42%.     

Motion tracking system in video based on extensive feature set

In recent years, object detection and tracking has been a dynamic research area. Rapid development of the multimedia and the associated technologies urge the processing of a huge database of video clips. The processing efficiency lies on the search methodologies utilised in the video processing system. Usage of unsuitable search methodologies may make the processing system ineffective. Hence, effective object detection and tracking system is an essential criterion for searching relevant videos from a huge collection of videos. This paper proposes a unique object detection and tracking system where video segmentation, feature extraction, object detection and tracking are combined perfectly using various features. Initially, the database video clips are segmented into different shots before performing the feature extraction process. The proposed system consists of two stages, namely, feature extraction and tracking of object in the video clips. In the feature extraction stage, firstly, colour feature is extracted based on colour quantisation. Next, edge density feature is extracted for the objects present in the query video. Then, the texture feature is extracted based on LGXP technique. Finally, based on these feature extracted, the object will be detected and the detected objects will be tracked by utilising both forward and backward tracking technique. The proposed methodology proved to be more effective and accurate in object detection and tracking.     

Deep Learning-Based Approach for Arabic Visual Speech Recognition

Lip-reading technologies are rapidly progressing following the breakthrough of deep learning. It plays a vital role in its many applications, such as: human-machine communication practices or security applications. In this paper, we propose to develop an effective lip-reading recognition model for Arabic visual speech recognition by implementing deep learning algorithms. The Arabic visual datasets that have been collected contains 2400 records of Arabic digits and 960 records of Arabic phrases from 24 native speakers. The primary purpose is to provide a high-performance model in terms of enhancing the preprocessing phase. Firstly, we extract keyframes from our dataset. Secondly, we produce a Concatenated Frame Images (CFIs) that represent the utterance sequence in one single image. Finally, the VGG-19 is employed for visual features extraction in our proposed model. We have examined different keyframes: 10, 15, and 20 for comparing two types of approaches in the proposed model: (1) the VGG-19 base model and (2) VGG-19 base model with batch normalization. The results show that the second approach achieves greater accuracy: 94% for digit recognition, 97% for phrase recognition, and 93% for digits and phrases recognition in the test dataset. Therefore, our proposed model is superior to models based on CFIs input.     

基于卷积神经网络的印刷套准识别方法

目的 针对目前印刷套准识别方法依赖于经验人工设计特征提取的问题,提出一种不需要人工提取图像特征的卷积神经网络模型,实现印刷套准状态的识别.方法 采用图像增强技术实现不均衡训练集的均衡化,增加训练集图像的数量,提高模型的识别准确率.设计基于AlexNet网络结构的印刷套准识别模型的结构参数,分析批处理样本数量和基础学习率对模型性能的影响规律.结果 文中方法获得的总印刷套准识别准确率为0.9860,召回率为1.0000,分类准确率几何平均数为0.9869.结论 文中方法能自动提取图像特征,不依赖于人工设计的特征提取方法.在构造的数据集上,文中方法的分类性能优于实验中的支持向量机方法.     

基于深度置信网络与信息融合的齿轮故障诊断方法

针对齿轮在复杂运行工况下故障特征提取困难,传统故障诊断方法的识别精度易受人工提取特征的影响,以及单传感器获取信息不全面等问题,提出基于深度置信网络(DBN)与信息融合的齿轮故障诊断方法。通过多传感器信息融合技术对每个传感器采集的振动信号进行数据层融合;利用DBN进行自适应特征提取从而实现故障分类。为了避免因人为选择DBN结构参数,导致模型识别精度下降的问题,利用改进的混合蛙跳算法(ISFLA)对DBN结构参数进行优化。试验表明,与BP神经网络、未经优化的DBN以及单传感器故障诊断相比,该研究提出的信息融合及优化方法具有更高的故障识别精度。     

A novel framework for writer identification based on pre-segmented Gurmukhi characters

Handwriting is an obtained apparatus utilized for correspondence of one’s recognition or sentiments. Components that judge a person’s handwriting is not merely subject to the individual’s handwriting depends on the background, additionally considers like nervousness, inspiration and the reason for the handwriting. In spite of the high variation, in a man’s handwriting, recent outcomes from various writers have demonstrated that it has adequate individual quality to be utilized as an identification strategy. In this paper, the authors are the pact with a novel approach to text dependent writer identification in view of pre-segmented Gurmukhi characters. The text dependent writer identification framework proposed in this paper includes distinctive stages like preprocessing, feature extraction, classification or identification. The feature extraction stage incorporates four schemes, zoning, diagonal, transitions and peak extent based features. To analyze the proposed framework execution, experiments are performed with two classifiers, namely, k-NN and SVM. SVM is also considered with linear-kernel in the present work. For experimental results, we have collected 31,500 samples from 90 different writers for 35 class problem. Maximum writer identification accuracy of 89.85% has been achieved by using a combination of zoning, transition and peak extent based features with Linear-SVM classifier when we have taken 70% data as the training set and remaining 30% data as the testing set. Using 10-fold cross validation, we have achieved an accuracy of 94.76% with a combination of zoning, transition and peak extent based features and Linear-SVM classifier.     

Feature classification techniques in model-based object recognition

We describe a system that performs model-based recognition of the projections of generalized cylinders, and present new results on the final classification of the feature data. Two classification methods are proposed and compared. The first is a Bayesian technique that ranks the object space according to estimated conditional probability distributions. The second technique is a new feed-forward “neural” implementation that utilizes the back-propagation learning algorithm. The neural approach yields a 31.8% reduction in classification error for a database of twenty models relative to the Bayesian approach, although it does not provide an ordered ranking of the object space. The accuracy results of the neural approach represent a significant performance advance in feature-based recognition by perceptual organization without the use of depth information. Examples are provided using the results of a simple segmentation system applied to real image data.     

基于OCT成像的淡水无核珍珠内部缺陷自动检测方法

光学相干层析技术(OCT)作为一种高分辨率的无损光学检测手段,已被用于珍珠的内部质量检测。针对淡水无核珍珠质层内部缺陷检测的需求,提出一种通过光学相干层析图像实现淡水无核珍珠内部缺陷自动检测的方法。根据珠层灰度变化的特点,识别图像中缺陷区域的梯度特征和缺陷位置变化特征,并利用缺陷特征建立反向传播神经网络模型。实验中采集了内部无缺陷和内部有多种类型缺陷淡水无核珍珠的光学相干层析图像各20幅,对图像进行预处理并提取特征,利用K-means算法检测样本类型与所提取特征的匹配度,用特征与类型相匹配的样本特征训练反向传播神经网络模型,使用反向传播网络模型对淡水无核珍珠内部缺陷层进行分类识别。实验结果表明该方法提取特征的匹配度为92.5%,分类准确率达到100%,验证了该方法的可行性和有效性,提出的方法能够作为淡水无核珍珠内部缺陷识别和自动分类的有效手段。     

A hybrid method for recognizing interacting machining features

Recognizing interacting features from a design part is a major challenge in the feature recognition problem. It is difficult to solve this problem using a single reasoning approach or artificial intelligence technique. A hybrid method, which is based on feature hints, graph theory and an artificial neural network--ART 2 net--has been proposed to recognize interacting machining features. Through enhancing the concepts of feature hints and graph representation schemes, which were presented in previous work to facilitate the extraction process of interacting features and reduce the searching space of recognition algorithms, a novel set of representations and methodologies to define generic feature hints (F-Loops), the interacting relationships between F-Loops and graph manipulations for F-Loops are developed to deduce potential features with various interacting relationships in a unified way. The obtained potential features are represented as F-Loop Graphs (FLGs), and these FLGs are input into an ART 2 neural network to be classified into different types of features eventually. The advantages of employing the ART 2 network are highlighted through comparing the computational results with another type of neural network, which is commonly utilized in the feature recognition domain. Case studies with complex interacting features show that the developed hybrid method can achieve optimal efficiency by benefiting from the diverse capabilities of the three techniques in the different phases of the recognition approach.     

Neuro-wavelet based intelligent medical image fusion

Imaging based sensitive clinical diagnosis is critically depending on image quality. In this article, the problem of enhancing fundus images is addressed by a novel fusion technique. The proposed approach utilizes the representation capability of wavelet transform and the learning ability of artificial neural networks. In this approach, input images are decomposed into wavelet transform followed by appropriate feature extraction for training of neural networks to obtain fused image. To ensure homogeneity, it employs consistency verification for minimizing the fusion artifacts. The visual and quantitative performance of the proposed approach is assessed using a number of experiments performed on the standard datasets of DRIVE and DRION-DB. The experimental results demonstrate that the proposed fusion technique offers high average structural similarity of “0.99.” The proposed approach outperforms state-of-the-art techniques which validates its effectiveness. The developed approach might be applied by the clinical diagnosis system for fundus related diseases.     

Efficient Analysis of Vertical Projection Histogram to Segment Arabic Handwritten Characters

The paper discusses the segmentation of words into characters, which is an essential task in the development process of character recognition systems, as poorly segmented characters will automatically be unrecognized. The segmentation of offline handwritten Arabic text poses a greater challenge because of its cursive nature and different writing styles. In this article, we propose a new approach to segment handwritten Arabic characters using an efficient analysis of the vertical projection histogram. Our approach was tested using a set of handwritten Arabic words from the IFN/ENIT database, and promising results were obtained.     

深度神经网络的语音深度特征提取方法

为了提升连续语音识别系统性能,将深度自编码器神经网络应用于语音信号特征提取。通过堆叠稀疏自编码器组成深度自编码器(Deep Auto-Encoding,DAE),经过预训练和微调两个步骤提取语音信号的本质特征,使用与上下文相关的三音素模型,以音素错误率大小为系统性能的评判标准。仿真结果表明相对于传统梅尔频率倒谱系数(Mel-Frequency Cepstral Coefficient,MFCC)特征以及优化后的MFCC特征,基于深度自编码器提取的深度特征更具优越性。     

一种基于GDLPP的人脸识别算法

针对人脸识别中的特征提取问题,本文提出了一种结合Gabor小波特征和判别保局投影的人脸识别算法-GDLPP.该算法首先对人脸图像进行多分辨率的Gabor小波变换,提取样本的高阶统计信息;然后更改保局投影(LPP)的目标函数,增加样本类间散布约束,从而提取更具判别性的特征.本文采用最小近邻分类器估算识别率.在USPS数据库、Yale人脸库以及AR人脸库的测试结果表明,在姿态、光照、表情、训练样本数目变化的情况下,GDLPP都具有较好的识别率.