基于颜色名和OpponentSIFT特征的鳞翅目昆虫图像识别

【目的】本研究旨在探索使用先进的计算机视觉技术实现对昆虫图像的自动分类方法。【方法】通过预处理对采集的昆虫标本图像去除背景,获得昆虫图像的前景蒙板,并由蒙板确定的轮廓计算出前景图像的最小包围盒,剪切出由最小包围盒确定的前景有效区域,然后对剪切得到的图像进行特征提取。首先提取颜色名特征,把原来的RGB（Red-Green-Blue）图像的像素值映射到11种颜色名空间,其值表示RGB值属于该颜色名的概率,每个颜色名平面划分成3×3像素大小的网格,用每格的概率均值作为网格中心点的描述子,最后用空阈金字塔直方图统计的方式形成颜色名视觉词袋特征;其次提取OpponentSIFT(Opponent Scale Invariant Feature Transform)特征,首先把RGB图像变换到对立色空间,对该空间每通道提取SIFT特征,最后用空域池化和直方图统计方法形成OpponentSIFT视觉词袋。将两种词袋特征串接后得到该昆虫图像的特征向量。使用昆虫图像样本训练集提取到的特征向量训练SVM（Support Vector Machine）分类器,使用这些训练得到的分类器即可实现对鳞翅目昆虫的分类识别。【结果】该方法在包含10种576个样本的昆虫图像数据库中进行了测试,取得了100%的识别正确率。【结论】试验结果证明基于颜色名和OpponentSIFT特征可以有效实现对鳞翅目昆虫图像的识别。     

基于稀疏编码和SCG BPNN的鳞翅目昆虫图像识别

【目的】为了给林业、 农业或植物检疫等行业人员提供一种方便快捷的昆虫种类识别方法, 本文提出了一种新颖的鳞翅目昆虫图像自动识别方法。【方法】首先通过预处理对采集的昆虫标本图像去除背景, 分割出双翅, 并对翅图像的位置进行校正。然后把校正后的翅面分割成多个超像素, 用每个超像素的l, a, b颜色及x, y坐标平均值作为其特征数据。接下来用稀疏编码(SC)算法训练码本、 生成编码并汇集成特征向量训练量化共轭梯度反向传播神经网络（SCG BPNN）, 并用得到的BPNN进行分类识别。【结果】该方法对包含576个样本的昆虫图像的数据库进行了测试, 取得了高于99%的识别正确率, 并有理想的时间性能、 鲁棒性及稳定性。【结论】实验结果证明了本文方法在识别鳞翅目昆虫图像上的有效性。     

基于Mel倒谱系数和矢量量化的昆虫声音自动鉴别

为了给生产单位害虫管理的普通技术人员提供简便易操作的昆虫种类鉴别方法, 本研究把人类语音识别领域的先进技术应用于昆虫识别, 提出了一种新颖的昆虫声音自动鉴别方法, 用声音参数化技术为昆虫声纹识别设计了一种简单易行的方案。声音信号经过预处理、分段得到一系列的声音样本, 从声音样本提取Mel倒谱系数（MFCC）, 并用Linde-Buzo-Gray（LBG）算法对提取的MFCC进行矢量量化(VQ), 所得码字作为声音样本的特征模型。特征参数之间的匹配用搜索最近邻的方法实现。本文方法在包含70种昆虫声音的库中进行了试验, 取得了超过96%的识别率和理想的时间性能。试验结果证明了该方法的有效性。     

实蝇科果实蝇属昆虫数字图像自动识别系统的构建和测试

针对双翅目实蝇科果实蝇属昆虫的自动识别,本文提出利用翅及中胸背板图像的局部二进制模式（local binary pattern, LBP）特征,采用Adaboost算法, 设计和开发“实蝇科果实蝇属昆虫数字图像自动识别系统”（Automated Fruit fly Identification System-Bactrocera, AFIS-B）。该系统包括图像采集、图像裁剪、预处理、特征提取、分类器设计、识别和显示,共7个模块。研究结果表明： LBP特征可以有效鉴别实蝇科果实蝇属昆虫;在对实蝇科果实蝇属8个种的测试中, 该系统表现出较高的准确性和稳定性,平均识别率可达80%以上。此外,还对果实蝇属昆虫翅膀及中胸背板图像在光照不均匀、姿态扭曲、样本受损及样本量大小等不同条件下的识别率进行了试验测试。结果表明, 该系统对测试样本的光照不均匀、 姿态扭曲和样本受损都表现出良好的鲁棒性,正确识别率与训练集样本各个种数量在一定条件下明显正相关,与训练集样本物种总量负相关。该项研究为实蝇科有害昆虫自动识别系统的构建及实际应用提供了理论、 方法及基础数据的支撑, 亦可为其他昆虫自动识别系统的研究和构建提供有益借鉴。 关键词：     

数学形态学在昆虫分类学上的应用研究.Ⅰ.在目级阶元上的应用研究

根据昆虫图像,对半翅目（Hemiptera）、鳞翅目（Lepidoptera）、鞘翅目（Coleoptera）的34种昆虫提取形状参数、叶状性、球状性等7项数学形态特征进行了统计分析,从而论证了各项数学形态特征在目级昆虫分类阶元上作为分类特征的可行性和可靠性,并从数学形态学角度对所涉及到的同阶元昆虫类群的亲缘关系做了描述。结果表明,在作为目级阶元分类特征时,各项特征的可靠性依次为：(似圆度、偏心率、亮斑数)＞(叶状性、球状性、圆形性)＞形状参数。由这些特征的差异显著性可知,从数学形态特征角度讲,3个目的亲缘关系远近大小依次为：半翅目与鞘翅目＞半翅目与鳞翅目＞鳞翅目与鞘翅目。     

数学形态学在昆虫分类学上的应用研究.Ⅰ.在目级阶元上的应用研究

根据昆虫图像,对半翅目（Hemiptera）、鳞翅目（Lepidoptera）、鞘翅目（Coleoptera）的34种昆虫提取形状参数、叶状性、球状性等7项数学形态特征进行了统计分析,从而论证了各项数学形态特征在目级昆虫分类阶元上作为分类特征的可行性和可靠性,并从数学形态学角度对所涉及到的同阶元昆虫类群的亲缘关系做了描述。结果表明,在作为目级阶元分类特征时,各项特征的可靠性依次为：(似圆度、偏心率、亮斑数)＞(叶状性、球状性、圆形性)＞形状参数。由这些特征的差异显著性可知,从数学形态特征角度讲,3个目的亲缘关系远近大小依次为：半翅目与鞘翅目＞半翅目与鳞翅目＞鳞翅目与鞘翅目。     

用于昆虫分类鉴定的几何形态计量学方法研究:相对扭曲分析

几何形态计量学着重研究生物形态的拓扑结构信息,不受昆虫标本大小和形状等因素的影响.本文提出利用几何形态计量学中的相对扭曲分析来实现昆虫分类鉴定的研究,做为方法论的探索,本文以鳞翅目夜蛾科6种蛾类昆虫的翅脉图像样本为试验材料.首先利用软件TpsDig2获取6种蛾180个右前翅翅脉样本的标记点,再运用软件TpsSuper对其进行普氏叠加分析,消除非形状因素等多余的信息,最后利用软件TpsRelw进行相对扭曲分析,通过分析得到的相对扭曲图像可以使昆虫的分类实现二维可视化,因此可以更直观地做出其种类的鉴定.研究结果表明本文为蛾类昆虫的可视化鉴定提供了一种可行的方法,对于昆虫分类鉴定的形态学测量数据可视化具有重要意义.     

粗糙集模糊聚类分析法在昆虫分类研究中的应用

本文根据昆虫图像,对半翅目、鳞翅目、鞘翅目的28种昆虫提取的形状参数、叶状性、球状性等7项数学形态特征进行了粗糙集模糊聚类分析。在粗糙集处理的基础上,分别进行7指标和3指标（相对约简）两种不同的模糊聚类分析法相比较。结果显示,在作为目级阶元分类指标时,各项特征的重要性依次为：(似圆度、偏心率)＞（亮斑数、球状性、圆形性）＞（叶状性、形状参数）;粗糙集分类正确率优于模糊聚类分析法;粗糙集处理后的3指标分类正确率优于未处理的7指标分类正确率。结论认为,粗糙集理论在昆虫依据数学形态特征进行分类方面与统计分析方法相比更有优势,粗糙集滤过指标后再进行模糊聚类法分析在昆虫分类研究上具有重要意义。     

粗糙集理论在昆虫分类学上的应用

研究了昆虫的数学形态特征在目级昆虫分类阶元上作为分类特征的可行性、可靠性和重要性,以及3个目的亲缘关系远近.根据昆虫图像,对半翅目、鳞翅目、鞘翅目的28种昆虫提取形状参数、叶状性、球状性等7项数学形态特征进行了粗糙集理论与方法的论证和运算,并与赵汗青等人统计分析的结果加以比较.在作为目级阶元分类时,各项特征的重要性依次为:(似圆度、偏心率)＞(亮斑数、球状性、圆形性)＞(叶状性、形状参数).从数学形态特征角度讲,3个目的亲缘关系远近大小依次为:半翅目与鞘翅目＞鳞翅目与鞘翅目＞半翅目与鳞翅目.粗糙集理论在昆虫依据数学形态特征进行分类方面与统计分析方法相比有更为理想的作用.     

Impact of quantization algorithm and number of gray level intensities on variability and repeatability of low field strength magnetic resonance image-based radiomics texture features

PurposeThe purpose of this work was to investigate the impact of quantization preprocessing parameter selection on variability and repeatability of texture features derived from low field strength magnetic resonance (MR) images.MethodsTexture features were extracted from low field strength images of a daily image QA phantom with four texture inserts. Feature variability over time was quantified using all combinations of three quantization algorithms and four different numbers of gray level intensities. In addition, texture features were extracted using the same combinations from the low field strength MR images of the gross tumor volume (GTV) and left kidney of patients with repeated set up scans. The impact of region of interest (ROI) preprocessing on repeatability was investigated with a test-retest study design.ResultsThe phantom ROIs quantized to 64 Gy level intensities using the histogram equalization method resulted in the greatest number of features with the least variability. There was no clear method that resulted in the highest repeatability in the GTV or left kidney. However, eight texture features extracted from the GTV were repeatable regardless of ROI processing combination.ConclusionLow field strength MR images can provide a stable basis for texture analysis with ROIs quantized to 64 Gy levels using histogram equalization, but there is no clear optimal combination for repeatability.     

The redder the better: wing color predicts flight performance in monarch butterflies

The distinctive orange and black wings of monarchs (Danaus plexippus) have long been known to advertise their bitter taste and toxicity to potential predators. Recent work also showed that both the orange and black coloration of this species can vary in response to individual-level and environmental factors. Here we examine the relationship between wing color and flight performance in captive-reared monarchs using a tethered flight mill apparatus to quantify butterfly flight speed, duration and distance. In three different experiments (totaling 121 individuals) we used image analysis to measure body size and four wing traits among newly-emerged butterflies prior to flight trials: wing area, aspect ratio (length/width), melanism, and orange hue. Results showed that monarchs with darker orange (approaching red) wings flew longer distances than those with lighter orange wings in analyses that controlled for sex and other morphometric traits. This finding is consistent with past work showing that among wild monarchs, those sampled during the fall migration are darker in hue (redder) than non-migratory monarchs. Together, these results suggest that pigment deposition onto wing scales during metamorphosis could be linked with traits that influence flight, such as thorax muscle size, energy storage or metabolism. Our results reinforce an association between wing color and flight performance in insects that is suggested by past studies of wing melansim and seasonal polyphenism, and provide an important starting point for work focused on mechanistic links between insect movement and color.     

Using digitized museum collections to understand the effects of habitat on wing coloration in the Puerto Rican monarch

Given the recent emphasis on Lepidoptera wing color and temperature in macroecology, we briefly describe known drivers of wing color and outline the use of images for understanding color variation across space and time. As a case study, we quantify wing color using museum specimens of the non‐migratory Puerto Rican monarch. In contrast to recent findings, we report darker individuals in coastal habitats, underscoring the need to include other selection factors. We detail how international digitization initiatives can resolve this paradox by adopting standards and protocols for high‐throughput image analysis. Abstract in Spanish is available with online material.     

Enhanced Performance of Brain Tumor Classification via Tumor Region Augmentation and Partition

Automatic classification of tissue types of region of interest (ROI) plays an important role in computer-aided diagnosis. In the current study, we focus on the classification of three types of brain tumors (i.e., meningioma, glioma, and pituitary tumor) in T1-weighted contrast-enhanced MRI (CE-MRI) images. Spatial pyramid matching (SPM), which splits the image into increasingly fine rectangular subregions and computes histograms of local features from each subregion, exhibits excellent results for natural scene classification. However, this approach is not applicable for brain tumors, because of the great variations in tumor shape and size. In this paper, we propose a method to enhance the classification performance. First, the augmented tumor region via image dilation is used as the ROI instead of the original tumor region because tumor surrounding tissues can also offer important clues for tumor types. Second, the augmented tumor region is split into increasingly fine ring-form subregions. We evaluate the efficacy of the proposed method on a large dataset with three feature extraction methods, namely, intensity histogram, gray level co-occurrence matrix (GLCM), and bag-of-words (BoW) model. Compared with using tumor region as ROI, using augmented tumor region as ROI improves the accuracies to 82.31% from 71.39%, 84.75% from 78.18%, and 88.19% from 83.54% for intensity histogram, GLCM, and BoW model, respectively. In addition to region augmentation, ring-form partition can further improve the accuracies up to 87.54%, 89.72%, and 91.28%. These experimental results demonstrate that the proposed method is feasible and effective for the classification of brain tumors in T1-weighted CE-MRI.     

An easy,inexpensive, and sensitive method for the quantification of chitin in insect peritrophic membrane by image processing

ABSTRACT

Chitin, poly (β-(1→4)-N-acetyl-d-glucosamine), is an important biopolymer for insects that is utilized as a major component of peritrophic membrane. The chitin content in peritrophic membrane is of expedient interest from a pest control perspective, although it is hard to quantify chitin. In this study, we establish a facile method for the quantification of chitin in peritrophic membrane by image processing. In this method, chitin was indirectly quantified using chitosan–I₃^? complex, which exhibited a specific red-purple color. A calibration curve using a chitosan solution showed good linearity in a concentration range of 0.05–0.5 μg/μL. We quantified the amount of chitin in peritrophic membrane of Spodoptera litura (Lepidoptera: Noctuidae) larvae using this method. Throughout the study, only common inexpensive regents and easily attainable apparatuses were employed. This method can be easily applied to the sensitive quantification of the amounts of chitin and chitosan in materials by wide range of researchers.

Abbreviations: LOD: limit of detection; LOQ: limit of quantification; ROI: region of interest; RSD: relative standard deviation.     

Oil Adulteration Identification by Hyperspectral Imaging Using QHM and ICA

To investigate the feasibility of identification of qualified and adulterated oil product using hyperspectral imaging(HIS) technique, a novel feature set based on quantized histogram matrix (QHM) and feature selection method using improved kernel independent component analysis (iKICA) is proposed for HSI. We use UV and Halogen excitations in this study. Region of interest(ROI) of hyperspectral images of 256 oil samples from four varieties are obtained within the spectral region of 400–720nm. Radiation indexes extracted from each ROI are used as feature vectors. These indexes are individual band radiation index (RI), difference of consecutive spectral band radiation index (DRI), ratio of consecutive spectral band radiation index (RRI) and normalized DRI (NDRI). Another set of features called quantized histogram matrix (QHM) are extracted by applying quantization on the image histogram from these features. Based on these feature sets, improved kernel independent component analysis (iKICA) is used to select significant features. For comparison, algorithms such as plus L reduce R (plusLrR), Fisher, multidimensional scaling (MDS), independent component analysis (ICA), and principle component analysis (PCA) are also used to select the most significant wavelengths or features. Support vector machine (SVM) is used as the classifier. Experimental results show that the proposed methods are able to obtain robust and better classification performance with fewer number of spectral bands and simplify the design of computer vision systems.