Handwriting segmentation of unconstrained Oriya text

Segmentation of handwritten text into lines, words and characters is one of the important steps in the handwritten text recognition process. In this paper we propose a water reservoir concept-based scheme for segmentation of unconstrained Oriya handwritten text into individual characters. Here, at first, the text image is segmented into lines, and the lines are then segmented into individual words. For line segmentation, the document is divided into vertical stripes. Analysing the heights of the water reservoirs obtained from different components of the document, the width of a stripe is calculated. Stripe-wise horizontal histograms are then computed and the relationship of the peak-valley points of the histograms is used for line segmentation. Based on vertical projection profiles and structural features of Oriya characters, text lines are segmented into words. For character segmentation, at first, the isolated and connected (touching) characters in a word are detected. Using structural, topological and water reservoir concept-based features, characters of the word that touch are then segmented. From experiments we have observed that the proposed “touching character” segmentation module has 96.7% accuracy for two-character touching strings.     

基于胶囊网络的汉字笔迹鉴定算法

由于采集脱机汉字手写样本时忽略了书写人的心理和生理等因素对书写活动的影响,因而传统笔迹鉴定算法的泛化能力较低。针对上述问题,提出基于胶囊网络的汉字笔迹鉴定算法,并构建了跟踪采集数据集以模拟复杂背景下产生的汉字。胶囊网络构建活动向量表示特定类型的实例化参数,通过动态路由算法将活动向量路由到下一层相应的胶囊中,使下一层胶囊得到更清晰的输入信号。分别采用5种算法对HWDB1.1数据集和跟踪采集数据集进行了测试,实验结果表明：本文算法的分类准确率比其他4种算法的都高,HWDB1.1数据集和跟踪采集数据集中算法的分类准确率分别为95.82%, 94.39%;本文算法具有较强的泛化性能,对训练样本数的依赖程度较低,弥补了卷积神经网络池化层的信息丢失缺陷。     

基于卷积神经网络的模糊车牌自动识别

目前,清晰的车牌识别算法已经成熟,但是对于人眼不能识别的模糊车牌,传统车牌识别算法的识别率较低或者根本无法识别。鉴于此,提出了一种基于卷积神经网络的车牌字符识别算法。制作了含9 720幅模糊字符样本集,用8 748幅样本对卷积神经网络进行训练,测试样本时,先对模糊车牌字符进行盲分割等预处理,再调用训练好的卷积神经网络对盲分割后的字符进行识别。实验结果表明:该算法对训练集的准确识别率约为99.17%,对测试集的准确识别率约为93.32%,这说明该算法对模糊车牌的识别具有鲁棒性,能应用于各种场景。     

基于脉冲神经网络的钢材表面缺陷识别研究

目的 针对现有钢材缺陷识别算法特征图利用不充分、识别准确率低、参数量大等问题,基于脉冲神经网络,提出一种用于钢材缺陷识别的稠密卷积脉冲神经网络(DCSNN)模型,减少系统消耗和内存占用。方法 首先,采用卷积编码,对输入图片进行特征提取和编码。其次,采用稠密连接算法搭建稠密卷积脉冲神经网络,实现特征重复利用,抑制梯度消失,并通过替代梯度下降算法进行网络训练。最后,在带钢数据集上进行测试,实现带钢缺陷识别。结果 实验结果显示,DCSNN在测试集上的准确率为98.61%,参数量为0.5万,结论 在钢材表面缺陷识别问题上表现出良好效果。     

EMS表单中手写体中文识别图像预处理方法研究

目的在脱机手写体文字识别系统中,由于自由书写的字符不可避免地受到图像背景不均匀、图像倾斜和字符粘连及大小不一等因素的影响,为了确保字符切分和识别的正确性,对EMS表单中手写体汉字字符图像预处理方法进行探讨,展示了EMS表单图像预处理的全过程。方法采用最小二乘法作拟合直线的方法,对目标图像进行定位和分割,用基于大津阈值的分块阈值算法处理目标图像的背景不均问题,并减少噪声干扰。结果该图像预处理方法在1020张真实EMS图像上进行测试,识别正确率达到了86.3%。结论该方法有一定的灵活性和抗干扰性,减少了图像噪声对汉字字符切分和识别的影响。     

GDX1包装机IPC控制系统的研发

目的 为加强银行智能办理业务的设备性能,提高票据数字的识别效率,研究一种改进的算法来获得更高的数字识别效果。方法 根据银行票据的印刷数字特性进行字符的提取和分割,经过图像采集、降噪、二值化之后使用起点直方图法结合步长法进行字符的分割,然后使用改进的LENET卷积神经网络用于提取数字特征,进行分类。结果 通过实验,结果表明文中提出的方法进行复杂环境下的印刷数字识别,准确率达到95%以上,识别速率为1.169 s/张。结论 利用新的字符分割算法与改进的LENET神经网络相结合,可以很好地识别干扰强的印刷票据,准确率高。     

卷积神经网络在印刷品缺陷检测的应用

目的 为了改善传统机器检测印刷产品缺陷存在误费率高的不足。方法 提出以卷积神经网络为控制核心的印刷品缺陷检测系统。设计可在实际检测中应用的卷积神经网络,设计在线印刷质量检测系统的硬件结构。结果 对结构相同而训练次数、学习率不同的卷积神经网络进行了缺陷检测的性能对比,验证了该卷积神经网络在学习率小于0.01时,可以获得较好的识别效果;在学习率大于0.05时,网络不容易收敛。网络训练次数越多,精度越高,相应的训练时间也较长。在满足快速性和精确度的条件下,确定了适应某印刷品的缺陷检验网络训练次数为50,学习率为0.005,此时的识别率为90%。结论 经过实验证明,该检测系统具有良好的缺陷识别能力,缺陷类型的分类准确率较高。该系统具有一定的实用价值。     

An Optimized Approach to Vehicle-Type Classification Using a Convolutional Neural Network

Vehicle type classification is considered a central part of an intelligent traffic system. In recent years, deep learning had a vital role in object detection in many computer vision tasks. To learn high-level deep features and semantics, deep learning offers powerful tools to address problems in traditional architectures of handcrafted feature-extraction techniques. Unlike other algorithms using handcrated visual features, convolutional neural network is able to automatically learn good features of vehicle type classification. This study develops an optimized automatic surveillance and auditing system to detect and classify vehicles of different categories. Transfer learning is used to quickly learn the features by recording a small number of training images from vehicle frontal view images. The proposed system employs extensive data-augmentation techniques for effective training while avoiding the problem of data shortage. In order to capture rich and discriminative information of vehicles, the convolutional neural network is fine-tuned for the classification of vehicle types using the augmented data. The network extracts the feature maps from the entire dataset and generates a label for each object (vehicle) in an image, which can help in vehicle-type detection and classification. Experimental results on a public dataset and our own dataset demonstrated that the proposed method is quite effective in detection and classification of different types of vehicles. The experimental results show that the proposed model achieves 96.04% accuracy on vehicle type classification.     

A Novel Combinational Convolutional Neural Network for Automatic Food-Ingredient Classification

With the development of deep learning and Convolutional Neural Networks (CNNs), the accuracy of automatic food recognition based on visual data have significantly improved. Some research studies have shown that the deeper the model is, the higher the accuracy is. However, very deep neural networks would be affected by the overfitting problem and also consume huge computing resources. In this paper, a new classification scheme is proposed for automatic food-ingredient recognition based on deep learning. We construct an up-to-date combinational convolutional neural network (CBNet) with a subnet merging technique. Firstly, two different neural networks are utilized for learning interested features. Then, a well-designed feature fusion component aggregates the features from subnetworks, further extracting richer and more precise features for image classification. In order to learn more complementary features, the corresponding fusion strategies are also proposed, including auxiliary classifiers and hyperparameters setting. Finally, CBNet based on the well-known VGGNet, ResNet and DenseNet is evaluated on a dataset including 41 major categories of food ingredients and 100 images for each category. Theoretical analysis and experimental results demonstrate that CBNet achieves promising accuracy for multi-class classification and improves the performance of convolutional neural networks.     

Two-tier architecture for unconstrained handwritten character recognition

In this paper, we propose an approach that combines the unsupervised and supervised learning techniques for unconstrained handwritten numeral recognition. This approach uses the Kohonen self-organizing neural network for data classification in the first stage and the learning vector quantization (LVQ) model in the second stage to improve classification accuracy. The combined architecture performs better than the Kohonen self-organizing map alone. In the proposed approach, the collection of centroids at different phases of training plays a vital role in the performance of the recognition system. Four experiments have been conducted and experimental results show that the collection of centroids in the middle of the training gives high performance in terms of speed and accuracy. The systems developed also resolve the confusion between handwritten numerals.     

基于改进双流卷积递归神经网络的RGB-D物体识别方法

为了提高基于图像的物体识别准确率,提出一种改进双流卷积递归神经网络的RGB-D物体识别算法(Re-CRNN).将RGB图像与深度光学信息结合,基于残差学习对双流卷积神经网络(CNN)进行改进:增加顶层特征融合单元,在RGB图像和深度图像中学习联合特征,将提取的RGB和深度图像的高层次特征进行跨通道信息融合,继而使用So...     

A Method for Improving CNN-Based Image Recognition Using DCGAN

Image recognition has always been a hot research topic in the scientific community and industry. The emergence of convolutional neural networks(CNN) has made this technology turned into research focus on the field of computer vision, especially in image recognition. But it makes the recognition result largely dependent on the number and quality of training samples. Recently, DCGAN has become a frontier method for generating images, sounds, and videos. In this paper, DCGAN is used to generate sample that is difficult to collect and proposed an efficient design method of generating model. We combine DCGAN with CNN for the second time. Use DCGAN to generate samples and training in image recognition model, which based by CNN. This method can enhance the classification model and effectively improve the accuracy of image recognition. In the experiment, we used the radar profile as dataset for 4 categories and achieved satisfactory classification performance. This paper applies image recognition technology to the meteorological field.     

基于卷积神经网络的典型农作物叶病害识别算法

目前,典型的一些农作物叶病害诊断主要依靠人工,但该方式耗时费力。针对大豆、棉花、水稻、小麦和玉米5类典型农作物的常见叶病害诊断问题,提出了一种基于卷积神经网络的典型农作物叶病害识别方法。从Plantvillage数据库以及其他网站收集典型农作物的叶病害图像,并对这些图像进行预处理,构建了含12 836张的数据集。参照AlexNet框架,构建8层卷积神经网络,采用迁移学习训练网络,最后通过测试集验证网络的识别准确率和损失值。分析不同的卷积神经网络的性能,实验结果表明：本算法对典型农作物的叶病害有良好的识别效果;迁移学习模式下,学习率为0.001时本算法在训练集的识别准确率约为99.47%,在测试集的识别准确率约为96.18%。     

Improved VGG Model for Road Traffic Sign Recognition

Road traffic sign recognition is an important task in intelligent transportation system. Convolutional neural networks (CNNs) have achieved a breakthrough in computer vision tasks and made great success in traffic sign classification. In this paper, it presents a road traffic sign recognition algorithm based on a convolutional neural network. In natural scenes, traffic signs are disturbed by factors such as illumination, occlusion, missing and deformation, and the accuracy of recognition decreases, this paper proposes a model called Improved VGG (IVGG) inspired by VGG model. The IVGG model includes 9 layers, compared with the original VGG model, it is added max-pooling operation and dropout operation after multiple convolutional layers, to catch the main features and save the training time. The paper proposes the method which adds dropout and Batch Normalization (BN) operations after each fully-connected layer, to further accelerate the model convergence, and then it can get better classification effect. It uses the German Traffic Sign Recognition Benchmark (GTSRB) dataset in the experiment. The IVGG model enhances the recognition rate of traffic signs and robustness by using the data augmentation and transfer learning, and the spent time is also reduced greatly.     

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.     

Enhancing breast pectoral muscle segmentation performance by using skip connections in fully convolutional network

The precise detection and segmentation of pectoral muscle areas in mediolateral oblique (MLO) views is an essential step in the development of a computer-aided diagnosis system to access breast malignant lesions or parenchyma. The goal of this article is to develop a robust and fully automatic algorithm for pectoral muscle segmentation from mammography images. This paper presents an image enhancement approach that improves the quality of mammogram scans and a convolutional neural network-based fully convolutional network architecture enhanced with residual connections for automatic segmentation of the pectoral muscle from the MLO views of a digital mammogram. For this purpose, the model is tested and trained on three different mammogram datasets named MIAS, INBREAST, and DDSM. The ground truth labels of the pectoral muscle were identified under the supervision of experienced radiologists. For training and testing, 10-fold cross-validation was used. The proposed model was compared with baseline U-Net-based architecture. Finally, we used a postprocessing step to find the actual boundary of the pectoral muscle. Our presented architecture generated a mean Intersection over Union (IoU) of 97%, dice similarity coefficient (DSC) of 96% and 98% accuracy on testing data. The proposed architecture for pectoral muscle segmentation from the MLO views of mammogram images with high accuracy and dice score can be quickly merged with the breast tumor segmentation problem.