Computer vision based food grain classification: A comprehensive survey
طبقه بندی دانه های غذایی مبتنی بر بینایی رایانه ای: یک مرور جامع-2021
This manuscript presents a comprehensive survey on recent computer vision based food grain classification techniques. It includes state-of-the-art approaches intended for different grain varieties. The approaches pro- posed in the literature are analyzed according to the processing stages considered in the classification pipeline, making it easier to identify common techniques and comparisons. Additionally, the type of images considered by each approach (i.e., images from the: visible, infrared, multispectral, hyperspectral bands) together with the strategy used to generate ground truth data (i.e., real and synthetic images) are reviewed. Finally, conclusions highlighting future needs and challenges are presented.
Keywords: Computer vision approaches | Quality inspection | Food grain identification | Machine vision
Plant trait estimation and classification studies in plant phenotyping using machine vision – A review
برآورد و طبقه بندی صفات گیاهی در فنوتیپ سازی گیاهان با استفاده از بینایی ماشین - مرور-2021
Today there is a rapid development taking place in phenotyping of plants using non-destructive image based machine vision techniques. Machine vision based plant phenotyping ranges from single plant trait estimation to broad assessment of crop canopy for thousands of plants in the field. Plant phenotyping systems either use single imaging method or integrative approach signifying simultaneous use of some of the imaging techniques like visible red, green and blue (RGB) imaging, thermal imaging, chlorophyll fluorescence imaging (CFIM), hyperspectral imaging, 3-dimensional (3-D) imaging or high resolution volumetric imaging. This paper provides an overview of imaging techniques and their applications in the field of plant phenotyping. This paper presents a comprehensive survey on recent machine vision methods for plant trait estimation and classification. In this paper, information about publicly available datasets is provided for uniform comparison among the state-of-the-art phenotyping methods. This paper also presents future research directions related to the use of deep learning based machine vision algorithms for structural (2-D and 3-D), physiological and temporal trait estimation, and classification studies in plants.
Keywords: Plant phenotyping | Machine vision | Plant trait estimation | Imaging techniques | Leaf segmentation and counting | Plant classification studies
Application of spectral features for separating homochromatic foreign matter from mixed congee
کاربرد ویژگیهای طیفی برای جداسازی مواد خارجی هم رنگ از مخروط مخروطی-2021
Foreign matter (FM) in mixed congee not only reduces the quality of the congee but may also harm consumers. However, the common computer vision methods with poor recognition ability for the homochromatic FM. This study used hyperspectral reflectance images with the pattern recognition model to detect homochromatic FM on the mixed congee surface. First, spectral features corresponding to homochromatic FM and background were extracted from hyperspectral images. Then, based on the optimal spectral preprocessing method, LDA, K-nearest neighbor, backpropagation artificial neural network, and support vector machine (SVM) were used to classify the spectral features. The results revealed that the SVM model input with raw spectra principal components exhibited optimal identification rates of 99.17%. Finally, most of the pixels for homochromatic FM were classified correctly by using the SVM model. To summarized, hyperspectral images combined with pattern recognition are an effective method for recognizing homochromatic FM in mixed congee.
Keyword: Mixed congee | Homochromatic foreign matter | Hyperspectral imaging technology | Pattern recognition | Chemometrics
Oocyte and embryo evaluation by AI and multi-spectral autofluorescence imaging: Livestock embryology needs to catch-up to clinical practice
ارزیابی تخمک و جنین توسط هوش مصنوعی و تصویربرداری خودکار فلورسانس چند طیفی: جنین شناسی دام باید به مراحل بالینی برسد-2020
A highly accurate ‘non-invasive quantitative embryo assessment for pregnancy’ (NQEAP) technique that determines embryo quality has been an elusive goal. If developed, NQEAP would transform the selection of embryos from both Multiple Ovulation and Embryo Transfer (MOET), and even more so, in vitro produced (IVP) embryos for livestock breeding. The area where this concept is already having impact is in the field of clinical embryology, where great strides have been taken in the application of morphokinetics and artificial intelligence (AI); while both are already in practice, rigorous and robust evidence of efficacy is still required. Even the translation of advances in the qualitative scoring of human IVF embryos have yet to be translated to the livestock IVP industry, which remains dependent on the MOET-standardised 3- point scoring system. Furthermore, there are new ways to interrogate the biochemistry of individual embryonic cells by using new, light-based methodologies, such as FLIM and hyperspectral microscopy. Combinations of these technologies, in particular combining new imaging systems with AI, will lead to very accurate NQEAP predictive tools, improving embryo selection and recipient pregnancy success.
Keywords: Embryo selection | Machine learning | Pregnancy establishment | Embryo metabolism | Morphokinetics
Identifying non-O157 Shiga toxin-producing Escherichia coli (STEC) using deep learning methods with hyperspectral microscope images
شناسایی اشرشیا کولی تولید کننده سم غیر شیتا Sh157 با استفاده از روشهای یادگیری عمیق با تصاویر میکروسکوپ فوق قطبی-2020
Non-O157 Shiga toxin-producing Escherichia coli (STEC) serogroups such as O26, O45, O103, O111, O121 and O145 often cause illness to people in the United States and the conventional identification of these “Big-Six” are complex. The label-free hyperspectral microscope imaging (HMI) method, which provides spectral “fingerprints” information of bacterial cells, was employed to classify serogroups at the cellular level. In spectral analysis, principal component analysis (PCA) method and stacked auto-encoder (SAE) method were conducted to extract principal spectral features for classification task. Based on these features, multiple classifiers including linear discriminant analysis (LDA), support vector machine (SVM) and soft-max regression (SR) methods were evaluated. Different sizes of datasets were also tested in search for the suitable classification models. Among the results, SAE-based classification models performed better than PCA-based models, achieving classification accuracy of SAE-LDA (93.5%), SAE-SVM (94.9%) and SAE-SR (94.6%), respectively. In contrast, classification results of PCA-based methods such as PCA-LDA, PCA-SVM and PCA-SR were only 75.5%, 85.7% and 77.1%, respectively. The results also suggested the increasing number of training samples have positive effects on classification models. Taking advantage of increasing dataset, the SAE-SR classification model finally performed better than others with average accuracy of 94.9% in classifying STEC serogroups. Specifically, O103 serogroup was classified with the highest accuracy of 97.4%, followed by O111 (96.5%), O26 (95.3%), O121 (95%), O145 (92.9%) and O45 (92.4%), respectively. Thus, the HMI technology coupled with SAE-SR classification model has the potential for “Big-Six” identification.
Keywords: Foodborne bacteria | Classification | Food safety | Machine learning | Stacked auto-encoder | Optical method
Data mining of the best spectral indices for geochemical anomalies of copper: A study in the northwestern Junggar region, Xinjiang
داده کاوی از بهترین شاخص های طیفی برای ناهنجاری های ژئوشیمیایی مس: یک مطالعه در منطقه شمال غربی جونگگر ، سین کیانگ-2019
Hyperspectral remote sensing allows sampling at high temporal resolutions as well as rapid and non-destructive characterization of a wide range of mineralization, enabling identification of element content through spectral features. It provides data for prospecting in areas without sufficient geochemical data, and thus is of vital significance in prospecting for ores in such regions. However, approaches for remotely sensing elements are still lacking, particularly for element content. In this study, a level analysis of Cu content via spectral indices in the northwestern Junggar region, Xinjiang, was conducted. Based on four levels (0–100 ppm, 100–1000 ppm, 1000–10,000 ppm, and>10,000 ppm) of Cu content and corresponding spectral reflectance, simple and useful spectral indices for estimating Cu content at different levels were explored. The best wavelength domains for a given type of index were determined from four types of spectral indices by screening all combinations using correlation analysis. The coefficient of determination (R2) for Cu was calculated for all indices derived from the spectra of rock samples and was found to range from 0.02 to 0.75. With sensitive wavelengths and a significant correlation coefficient (R2=0.63, P < 0.005), the Normalized Difference (ND)-type index was the most sensitive to Cu content exceeding 10,000 ppm. Although the ND-type index has a few limitations, it is a useful, simple, and robust indicator for determining Cu at high concentrations.
Keywords: Cu element | Spectral indices | Geochemical anomaly | Northwestern Junggar region of Xinjiang | Normalized Difference-type index
ارزیابی سلامت جنگل برای برنامه ریزی و مدیریت جغرافیایی محیط زیست در مناطق معادن تپه ای با استفاده از داده های Hyperion و Landsat-2019
This work focuses on assessing the health condition of the forest using Hyperspectral and Multispectral satellite imagery and validating it with field spectra data. The field-based spectroradiometer and PCE instrument were used for collection of forest health spectra and measurement of dust accumulation on leaves respectively. In the study area, mining activities have very high potential to induce forestry health and environmental problem which necessitated a proper forest health assessment and its monitoring. The result of the Discrimination analysis (21 spectral wavebands) were used for forest health classification. The result shows that healthy forest parts are found in the upper as well as the lower hilly side of Kiriburu and Meghahatuburu mines. Some healthy pixels are located within 1.5 km from mines because it was situated off the hillside. Furthermore, it also exhibits positive relation amongst different forest health class, distance from mines and foliar dust concentration. Hyperspectral (narrow-bands) Hyperion data used with Vegetation Indices (VIs) model shows better accuracy for forest health assessment (overall accuracy 81.52%, kappa statistic 0.79) than Spectral Angle Mapper (overall accuracy 79.99%, kappa statistic 0.75) as well as Support Vector Machine (overall accuracy 76.53%, kappa statistic 0.71). It was observed that the health assessment accuracy (using SVM algorithm) achieved with Hyperion bands was significantly higher than multispectral (broad-bands) Landsat-OLI data (overall accuracy 67.27%, kappa statistic 0.62). Finally, the forest health assessment results were validated by 60 field sampled spectra data obtained from spectroradiometer. The forest health map obtained provides a guideline for geoenvironmental planning and management in mining proximity forest area
Keywords: Hyperspectral Remote sensing | Discrimination analysis | VIs model | Mining | Forest health assessment
Detection of nutrition deficiencies in plants using proximal images and machine learning: A review
تشخیص کمبودهای تغذیه ای در گیاهان با استفاده از تصاویر تقریبی و یادگیری ماشین: مرور-2019
During the last decade, the combination of digital images and machine learning techniques for tackling agricultural problems has been one of the most explored elements of digital farming. In the specific case of proximal images, most efforts have been directed to the detection and classification of plant diseases and crop-damaging pests. Important progress has also been made on the use of close-range images to determine vegetal nutrient status, but because such studies are fewer and more scattered, it is difficult to draw a complete picture on the state of art of this type of research. In this context, a thorough literature search was carried out in order to identify as many relevant investigations on the subject as possible. Every kind of imaging sensor was considered (visible range, multispectral, hyperspectral, chlorophyll fluorescence, etc.), provided that images were captured at close range, thus excluding research using Unmanned Aerial Vehicles (UAVs), airplanes and satellites. A careful analysis of the techniques for detection and classification was carried out and used as basis for an indepth discussion on the main challenges yet to be overcome. Some directions for future research are also suggested, having as target to increase the practical adoption of this kind of technology.
Keywords: Image processing | Computer vision | Plant nutrition | Machine learning
Pixel-level aflatoxin detecting based on deep learning and hyperspectral imaging
تشخیص آفلاتوکسین در سطح پیکسل مبتنی بر یادگیری عمیق و تصویربرداری hyperspectral-2019
Aflatoxin is a kind of virulent and strong carcinogenic substance, and it is found widely in peanut, Maize and their agricultural products. In order to detect Aflatoxin in peanut, we first built a hyperspectral imaging system using a grating module, SCOMS camera, and electric displacement platform, and acquired 146 hyperspectral images cubes of 73 peanut samples before and after contaminated with aflatoxin. Then, we proposed a reshaped image method of pixel spectral for the CNN method. By studying on random selection data-sets and comparing with different identification models, we found that: (1) Reshape image established by the pixel level spectral is good enough for aflatoxin detected problems, overall recognition rate reached above 95% on pixel-level. (2) The deep learning method is worked well and it is better than traditional identification models, not only on the pixel level but also on the kernel identification. The recognition rate of above 90% on the kernel level can quickly use in sorting machines design.
Keywords: Aflatoxin | Deep learning | CNN | Reshape image of pixel spectral | Hyperspectral images
A deep manifold learning approach for spatial-spectral classification with limited labeled training samples
یک رویکرد یادگیری منیفولد عمیق برای طبقه بندی مکانی طیفی با نمونه های آموزش دارای برچسب محدود-2019
One major challenge of designing deep learning systems for hyperspectral data classification is the lack of labeled training samples. Inspired by recent manifold learning researches, this paper presents a novel Lo- cality Preserving Convolutional Network to address this challenge. The proposed method invents a semi- supervised locality-preserving regularization operation, and inserts a new layer in the three-dimensional convolutional neural network for end-to-end spatial-spectral classification. The benefits are three-fold. First, by using unlabeled training samples which are more easily available, the proposed method re- duces the number of labeled samples required for training a deep learning model; Second, the proposed method incorporates the intrinsic geographical correlation among nearby samples into the extracted fea- tures, which prevents it from losing accuracy when only limited labeled samples are available; Third, with a three-dimensional architecture, the proposed method can extract the spatial and spectral features simultaneously from the hyperspectral data for classification. A gradient-decent based approach is de- ployed to train the whole network in a unified way. Experiments over different benchmarks show that, the proposed method relieves the Hughes phenomenon for deep learning, and achieves competitively high classification accuracy compared to other state-of-the-art approaches.
Keywords: Deep learning | Hyperspectral images | Limited labeled samples | Locality preserving convolutional network