基于支持向量机的纹理图像分类算法

研究纹理图像的分类问题,纹理特征提取和分类器设计是决定分类正确率高低的关键。由于库存图像较多,且质量受到噪声影响,使图像特征提取比较困难。针对传统特征提取和分类算法分类正确率不高的难题,提出一种基于支持向量机的纹理图像分类算法。首先采用Gabor滤波器对纹理特征进行提取,采用主成分分析对提取后的特征进行选择,最后采用支持向量机进行纹理图像的分类。采用Brodatz纹理库进行测试实验,实验结果表明,支持向量机分类算法提高了纹理图像的分类正确率,降低了误分率和拒分率,且分类速度加快,适用于更为复杂的纹理分类,为图像提取提供了参考。     

自适应的Haar型LBP纹理特征提取算法研究

在提取纹理图像的Haar型LBP特征中,人为设定的判断阈值主观性强、局部性差,导致提取的纹理细节和边缘模糊、纹理图像的局部性易被忽略。为此,提出了一种自适应的Haar型LBP纹理特征提取算法。该算法在二值化Haar型特征时引入高斯加权矩阵,以此获得客观、符合纹理图像局部特征的自适应判断阈值和Haar型LBP特征。实验结果表明,该算法能够有效地避免人为设定阈值对纹理特征的影响,可以准确地描述图像的纹理特征,Brodatz标准纹理库分类的正确率也得到了进一步的提高。     

混合特征下最优阈值预测的图像匹配

针对单一特征条件下图像匹配率较低,以及SIFT算法由于固定对比度阈值造成特征点数目提取不均的问题,提出一种混合特征下最优阈值预测的图像匹配算法。该算法首先采用SIFT算法提取图像特征点,然后利用纹理参数二阶矩自适应法得到最优阈值,并用描述性较强的纹理特征向量对SIFT匹配过程进行约束实现图像的匹配。实验结果表明,提出的算法根据图像灰度分布自适应选取对比度阈值,能够增强图像细节信息且使提取的特征点数量稳定,在匹配过程中引入纹理向量作为约束准则,避免了相似区域的误匹配,对光照和模糊图像有较好的鲁棒性。     

基于BEMD和LBP提取特征的纹理分类

对于纹理图像的分类,采用二维经验模式分解将图像分解成一系列的固有模态函数(IMF)和残差,并结合局部二值模式(LBP)对所提取到的各IMF图像和残差图像进行特征提取的方法。为了验证算法的有效性,对自然纹理进行特征提取,并结合支持向量机(SVM)算法对提取的特征向量进行分类,分类精确度达到98%以上。     

基于小波包变换和蚁群算法的纹理分类

提出了一种小波包变换和蚁群算法相结合的纹理分类新方法。首先采用小波包变换提取纹理图像的纹理特征向量,然后用蚁群算法进行训练和分类。实验表明小波包变换和蚁群算法应用到纹理分类领域,是一次有效的尝试。     

一种结合形状与纹理特征的植物叶片分类方法

根据植物叶片识别植物种类对于生物科学与生态科学具有重要的辅助作用。针对叶片分类,提出了一种基于形状与纹理特征的分类算法。在进行了去噪等预处理后,通过阈值分割和数学形态学方法获取叶片区域;在分割得到的二值区域图像上提取了形状特征,在灰度图像上提取了纹理特征;在所得特征的基础上,利用BP网络对叶片进行分类。在实际图片上的实验结果表明,相比于已有算法,该方法可以达到更高的正确分类率。     

基于纹理和BP神经网络的SAR图像分类

研究基于纹理和BP神经网络的SAR图像分类。首先用增强FROST滤波算法对SAR图像进行去噪处理。然后基于灰度共生矩阵理论提取去噪后的SAR图像多种纹理特征,并通过大量实验筛选出有效的纹理特征。最后,结合纹理特征,分别采用经典的最大似然分类法和BP神经网络分类法对SAR图像进行分类。实验结果表明：纹理信息辅助SAR图像的灰度进行分类,大大地提高了SAR图像的分类精度;基于BP神经网络的SAR图像分类精度高于最大似然分类法的分类精度。     

改进FCM和LFP相结合的白细胞图像分类

研究白细胞图像分类识别中有效的图像分割与特征提取方法,以提高白细胞图像的正确识别率.由于某些白细胞(粒细胞)中颗粒的存在,严重影响细胞核与细胞质区域的正确分割,通过将空间信息与核函数融入模糊C-均值聚类(FCM)算法,提出一种改进的FCM算法.应用该算法对白细胞图像进行分割,并采用数学形态学方法对分割后的图像进行处理,获得了很好的分割效果,解决了粒细胞的质核分割难题.对于细胞的纹理特征提取,通过对局部二值模式(LBP)中阈值参数的模糊化,建立了基于局部模糊模式(LFP)的纹理特征提取算法.运用本文方法进行图像分割和纹理提取,以支持向量机作为分类器,对CellAtlas的100幅白细胞图像进行了分类识别的实验,结果表明白细胞的正确识别率达到93％.     

基于Contourlet变换和仿生模式识别的纹理图像识别方法

纹理图像的分类是目前一个非常活跃的研究课题。针对现有纹理图像分类算法的局限性,本文提出了一种基于Contourlet变换和仿生模式识别方法的纹理图像识别算法。首先应用Contourlet变换获得能量特征的方法提取能量特征,进而利用仿生模式识别算法实现对纹理图像的识别。采用Vistex纹理库数据进行仿真实验,结果表明:与传统的分类方法相比,利用Contourlet变换和仿生模式识别结合进行纹理图像的识别能获得更高的正确率和速度,最佳正确率可达100%。     

新的木材显微细胞图像分类识别方法

提出一种基于纹理的木材显微细胞图像分类算法。通过非下采样的Contourlet变换模极值密度提取图像纹理特征,并采用K近邻分类方法进行分类,实现对木材显微细胞图像的分类。实验结果表明：平均识别正确率在85%以上。提出的方法能有效地实现对木材显微细胞图像的分类。     

多特征融合的瓷砖表面缺陷检测算法研究

鉴于单一特征在瓷砖种类较多的情况下,存在对瓷砖表面缺陷内容表达不明显,导致复杂瓷砖识别率较低。针对这个问题,在词袋模型（BoF）框架的基础上,提出一种有效的多特征融合算法用于瓷砖缺陷检测。该算法采用改进后的SIFT和颜色矩融合特征作为瓷砖图像的区域特征描述;根据每种特征对瓷砖被分类的准确率大小,给提取到的两种区域特征分配各自的权重系数实现特征的加权融合;形成综合特征向量送入SVM分类器达到瓷砖缺陷分类的目的。通过不同类型的瓷砖样本进行实验表明,该算法识别率高,对复杂瓷砖能实现较好的分类。     

瓷砖图像的纹理特征分类研究

在已有的瓷砖图像分类系统中,仅靠颜色特征和简单的纹理边缘信息只能对无花纹的单色砖或简单花纹的瓷砖进行有效分类,对复杂图案的瓷砖存在识别率低的问题。针对此种情况,结合瓷砖图像的灰度共生矩阵和统计几何特征,将这些特征输入支持向量机进行特征分层分类。采用基于径向基核函数和[K]交叉验证法所得到的最优参数构造支持向量机,解决瓷砖纹理特征具有非线性的分类问题。用瓷砖生产线上采集的大量图像进行实验表明,该方法准确率高,分类效果好。     

基于傅里叶变换的随机纹理瓷砖的高精度表面缺陷检测

针对经典缺陷检测算法不能很好地提取随机纹理瓷砖图像的缺陷的问题,提出一种基于傅里叶变换的随机纹理瓷砖表面缺陷高精度检测方法。在此基础上,完成了瓷砖表面缺陷检测硬件系统设计。对采集的瓷砖图像,首先利用傅里叶变换得到频率谱图像,然后研究截止频率参数对滤波的影响,设计最优化滤波器进行滤波,再通过傅里叶逆变换获得重构图像,达到抑制背景纹理信息,加强缺陷区域信息的目的,最后通过阈值化和形态学操作获得缺陷区域。实验结果表明: 本方法对不同的随机纹理瓷砖样本进行缺陷检测的准确率高,在瓷砖缺陷检测中具有较高的实用价值。     

基于机器视觉的随机纹理瓷砖的分选系统

针对日益加快的瓷砖生产速度与缓慢的人工分选速度之间不协调导致的瓷砖出产效率低下的问题,提出了以机器视觉软件HALCON 11.0为软件开发平台的结合瓷砖颜色、纹理特征提取的算法,以及针对多分类问题的改进多层感知器神经网络算法(MLPNN).首先对拍摄到的瓷砖图像进行去噪预处理,在HSI颜色空间中提取瓷砖的色调(Hue)特征并计算反映瓷砖的纹理特征的灰度共生矩阵(GLCM)和灰度幅值分布特征,再将得到的特征作为多层感知器的神经网络输入层神经元,然后设计以softmax为激活函数的多层感知器神经网络来进行模式匹配,并与BP神经网络模式匹配方法进行对比,最终搭建出具有简单人机交互界面的随机纹理瓷砖的分选实验样机.实验结果表明:本系统对实验的各类随机纹理瓷砖的分选准确率都在90%以上,具有较高的分选准确率,能应用于瓷砖生产实践.     

基于小波变换的图像纹理特征提取方法及其应用

针对瓷砖表面色差的在线检测问题,提出了一种基于小波变换的图像纹理特征提取方法.瓷砖图像经过预处理后,对图像各通道进行二层小波分解并提取各细节子图的能量特征.该能量信号融合了颜色和纹理的信息,将其作为区分不同色号瓷砖的特征量,并由最小距离分类器进行分类决策.实验结果表明,对比已有的研究中多采用的颜色直方图分布法,该方法能更好地反映颜色的空间分布信息,满足用户需求.     

A supervised approach for automated surface defect detection in ceramic tile quality control

Surface defect detection is very important to guarantee the quality of ceramic tiles production. At present, this process is usually performed manually in the ceramic tile industry, which is low efficiency and time-consuming. For small surface defects detection of high-resolution ceramic tiles image, an intelligent detection method for surface defects of ceramic tiles based on an improved you only look once version 5 (YOLOv5) algorithm is presented. Firstly, the high-resolution ceramic tile images are cropped into slices, and the Bottleneck module in the YOLOv5s network is optimized by introducing depthwise convolution and replaced in the whole network. Then, feature extraction is performed using the improved Shufflenetv2 backbone, and an attention mechanism is added to the backbone network to improve the feature extraction ability. The path aggregation network (PAN) and Feature Pyramid Networks (FPN) neck are used to enhance the feature extraction, and finally, the YOLO head is used to identify and locate the ceramic tile defects. The multiple sliding windows detection method is proposed to detect the original ceramic tile image which is faster than the single sliding window detection method. The experimental results show that compared with the original YOLOv5s detection algorithm, the parameters of the model are reduced by 20.46 %, the floating point operations are reduced by 26.22 %, and the mean average precision (mAP) of the proposed method is 96.73 % in the ceramic tile image slice test set which has 1.93 % improvement in mAP than the original YOLOv5s. Compare with other object detection methods, the method proposed in this paper also has certain advantages. In the high-resolution ceramic tile images test set, the mAP of the proposed algorithm is 86.44 % by using the multiple sliding window detection method. The ceramic defect detection experiment has verified the feasibility of the method proposed in this paper.     

基于直方图聚类的颜色分级方法

文章提出了一种利用颜色特征对瓷砖进行在线颜色分级的新方法。针对瓷砖图像数据量大的特点,采用了颜色空间分裂和与初始条件无关的聚类算法相结合的量化方法来提取瓷砖图像颜色特征,这既可满足算法实时性要求又充分考虑到了颜色分级对特征的精确性要求。实验结果证明了该方法的有效性。     

Efficient texture synthesis using strict Wang Tiles

Wang Tiles are constructed from four texture samples, arranged so they can always match a choice of other tiles at two edges. Because they are precomputed, Wang Tiles are a very efficient way to generate textures on the fly. But matching problems occur within tiles and at the corners of adjacent tiles. By replacing the edge-matching texture samples with a new sample in the center of the tile, and using the graph cut path-finding algorithm, we overcome these problems and introduce additional texture diversity. Our s-Wang Tiles are a stricter interpretation of the original Wang Tile design, and our tile set is also smaller than that required by ω-Tiles: only eight different tiles are required for a non-repetitive titling.     

A Study on Hovering Control of Small Aerial Robot by Sensing Existing Floor Features

Since precise self-position estimation is required for autonomous flight of aerial robots, there has been some studies on self-position estimation of indoor aerial robots. In this study, we tackle the self-position estimation problem by mounting a small downward-facing camera on the chassis of an aerial robot. We obtain robot position by sensing the features on the indoor floor. In this work, we used the vertex points (tile corners) where four tiles on a typical tiled floor connected, as an existing feature of the floor. Furthermore, a small lightweight microcontroller is mounted on the robot to perform image processing for the on-board camera. A lightweight image processing algorithm is developed. So, the real-time image processing could be performed by the microcontroller alone which leads to conduct on-board real time tile corner detection. Furthermore, same microcontroller performs control value calculation for flight commanding. The flight commands are implemented based on the detected tile corner information. The above mentioned all devices are mounted on an actual machine, and the effectiveness of the system was investigated.      

Monitoring defects of ceramic tiles using fuzzy subtractive clustering-based system identification method

In this paper, a subtractive clustering fuzzy identification method and a Sugeno-type fuzzy inference system are used to monitor tile defects in tile manufacturing process. The models for the tile defects are identified by using the firing mechanical resistance, water absorption, shrinkage, tile thickness, dry mechanical resistance and tiles temperature as input data, and using the concavity defect and surface defects as the output data. The process of model building is carried out by using subtractive clustering in both the input and output spaces. A minimum error model is developed through exhaustive search of clustering parameters. The fuzzy model obtained is capable of predicting the tile defects for a given set of inputs as mentioned above. The fuzzy model is verified experimentally using different sets of inputs. This study intends to examine and deal with the experimental results obtained during various stages of ceramic tile production during 90-day period. It is believed, that the results obtained from the present study could be considered in other ceramic tiles industries, which experienced similar forms of defects.