Two-Staged Method for Ice Channel Identification Based on Image Segmentation and Corner Point Regression

Identification of the ice channel is the basic technology for developing intelligent ships in ice-covered waters,which is important to ensure the safety and economy of navigation.In the Arctic,merchant ships with low ice class often navigate in channels opened up by icebreakers.Navigation in the ice channel often depends on good maneuverability skills and abundant experience from the captain to a large extent.The ship may get stuck if steered into ice fields off the channel.Under this circumstance,it is very important to study how to identify the boundary lines of ice channels with a reliable method.In this paper,a two-staged ice channel identification method is developed based on image segmentation and corner point regression.The first stage employs the image segmentation method to extract channel regions.In the second stage,an intelligent corner regression network is proposed to extract the channel boundary lines from the channel region.A non-intelligent angle-based filtering and clustering method is proposed and compared with corner point regression network.The training and evaluation of the segmentation method and corner regression network are carried out on the synthetic and real ice channel dataset.The evaluation results show that the accuracy of the method using the corner point regression network in the second stage is achieved as high as 73.33%on the synthetic ice channel dataset and 70.66%on the real ice channel dataset,and the processing speed can reach up to 14.58frames per second.

Deep Transfer Learning Models for Mobile-Based Ocular Disorder Identification on Retinal Images

Mobile technology is developing significantly.Mobile phone technologies have been integrated into the healthcare industry to help medical practitioners.Typically,computer vision models focus on image detection and classification issues.MobileNetV2 is a computer vision model that performs well on mobile devices,but it requires cloud services to process biometric image information and provide predictions to users.This leads to increased latency.Processing biometrics image datasets on mobile devices will make the prediction faster,but mobiles are resource-restricted devices in terms of storage,power,and computational speed.Hence,a model that is small in size,efficient,and has good prediction quality for biometrics image classification problems is required.Quantizing pre-trained CNN(PCNN)MobileNetV2 architecture combined with a Support Vector Machine(SVM)compacts the model representation and reduces the computational cost and memory requirement.This proposed novel approach combines quantized pre-trained CNN(PCNN)MobileNetV2 architecture with a Support Vector Machine(SVM)to represent models efficiently with low computational cost and memory.Our contributions include evaluating three CNN models for ocular disease identification in transfer learning and deep feature plus SVM approaches,showing the superiority of deep features from MobileNetV2 and SVM classification models,comparing traditional methods,exploring six ocular diseases and normal classification with 20,111 images postdata augmentation,and reducing the number of trainable models.The model is trained on ocular disorder retinal fundus image datasets according to the severity of six age-related macular degeneration(AMD),one of the most common eye illnesses,Cataract,Diabetes,Glaucoma,Hypertension,andMyopia with one class Normal.From the experiment outcomes,it is observed that the suggested MobileNetV2-SVM model size is compressed.The testing accuracy for MobileNetV2-SVM,InceptionV3,and MobileNetV2 is 90.11%,86.88%,and 89.76%respectively while MobileNetV2-SVM,InceptionV3,and MobileNetV2 accuracy are observed to be 92.59%,83.38%,and 90.16%,respectively.The proposed novel technique can be used to classify all biometric medical image datasets on mobile devices.

Soil pore identification with the adaptive fuzzy C-means method based on computed tomography images

The complex geometry and topology of soil is widely recognised as the key driver in many ecological processes. X-ray computed tomography (CT) provides insight into the internal structure of soil pores automatically and accurately. Until recently, there have not been methods to identify soil pore structures. This has restricted the development of soil science, particularly regarding pore geometry and spatial distribution. Through the adoption of the fuzzy clustering theory and the establishment of pore identification rules, a novel pore identification method is described to extract pore structures from CT soil images. The robustness of the adaptive fuzzy C-means method (AFCM), the adaptive threshold method, and Image-Pro Plus tools were compared on soil specimens under different conditions, such as frozen, saturated, and dry situations. The results demonstrate that the AFCM method is suitable for identifying pore clusters, especially tiny pores, under various soil conditions. The method would provide an optional technique for the study of soil micromorphology.

Automated detection and identification of white-backed planthoppers in paddy fields using image processing

A survey of the population densities of rice planthoppers is important for forecasting decisions and efficient control. Tra- ditional manual surveying of rice planthoppers is time-consuming, fatiguing, and subjective. A new three-layer detection method was proposed to detect and identify white-backed planthoppers （WBPHs, Sogatella furcifera （Horvath）） and their developmental stages using image processing. In the first two detection layers, we used an AdaBoost classifier that was trained on a histogram of oriented gradient （HOG） features and a support vector machine （SVM） classifier that was trained on Gabor and Local Binary Pattern （LBP） features to detect WBPHs and remove impurities. We achieved a detection rate of 85.6% and a false detection rate of 10.2%. In the third detection layer, a SVM classifier that was trained on the HOG features was used to identify the different developmental stages of the WBPHs, and we achieved an identification rate of 73.1%, a false identification rate of 23.3%, and a 5.6% false detection rate for the images without WBPHs. The proposed three-layer detection method is feasible and effective for the identification of different developmental stages of planthoppers on rice plants in paddy fields.

Rapid identification of landslide,collapse and crack based on low-altitude remote sensing image of UAV

Landslides,collapses and cracks are the main types of geological hazards,which threaten the safety of human life and property at all times.In emergency surveying and mapping,it is timeconsuming and laborious to use the method of field artificial investigation and recognition and using satellite image to identify ground hazards,there are some problems,such as time lag,low resolution,and difficult to select the map on demand.In this paper,a10 cm per pixel resolution photogrammetry of a geological hazard-prone area of Taohuagou,Shanxi Province,China is carried out by DJ 4 UAV.The digital orthophoto model(DOM),digital surface model(DSM) and three-dimensional point cloud model(3 DPCM) are generated in this region.The method of visual interpretation of cracks based on DOM(as main)-3 DPCM(as auxiliary) and landslide and collapse based on 3 DPCM(as main)-DOM and DSM(as auxiliary) are proposed.Based on the low altitude remote sensing image of UAV,the shape characteristics,geological characteristics and distribution of the identified hazards are analyzed.The results show that using UAV low altitude remote sensing image,the method of combination of main and auxiliary data can quickly and accurately identify landslide,collapse and crack,the accuracy of crack identification is 93%,and the accuracy of landslide and collapse identification is 100%.It mainly occurs in silty clay and mudstone geology and is greatly affected by slope foot excavation.This study can play a great role in the recognition of sudden hazards by low altitude remote sensing images of UAV.

Deep learning of rock microscopic images for intelligent lithology identification: Neural network comparison and selection

An intelligent lithology identification method is proposed based on deep learning of the rock microscopic images.Based on the characteristics of rock images in the dataset,we used Xception,MobileNet_v2,Inception_ResNet_v2,Inception_v3,Densenet121,ResNet101_v2,and ResNet-101 to develop microscopic image classification models,and then the network structures of seven different convolutional neural networks(CNNs)were compared.It shows that the multi-layer representation of rock features can be represented through convolution structures,thus better feature robustness can be achieved.For the loss function,cross-entropy is used to back propagate the weight parameters layer by layer,and the accuracy of the network is improved by frequent iterative training.We expanded a self-built dataset by using transfer learning and data augmentation.Next,accuracy(acc)and frames per second(fps)were used as the evaluation indexes to assess the accuracy and speed of model identification.The results show that the Xception-based model has the optimum performance,with an accuracy of 97.66%in the training dataset and 98.65%in the testing dataset.Furthermore,the fps of the model is 50.76,and the model is feasible to deploy under different hardware conditions and meets the requirements of rapid lithology identification.This proposed method is proved to be robust and versatile in generalization performance,and it is suitable for both geologists and engineers to identify lithology quickly.

Flow pattern identification in oil wells by electromagnetic image logging

Petroleum production logging needs to determine the interpretation models first and flow pattern identification is the foundation, but traditional flow pattern identification methods have some limitations. In this paper, a new method of flow pattern identification in oil wells by electromagnetic image logging is proposed. First, the characteristics of gas-water and oil-water flow patterns in horizontal and vertical wellbores are picked up. Then, the continuous variation of the two phase flow pattern in the vertical and horizontal pipe space is discretized into continuous fluid distribution models in the pipeline section. Second, the electromagnetic flow image measurement responses of all the eight fluid distribution models are simulated and the characteristic vector of each response is analyzed in order to distinguish the fluid distribution models. Third, the time domain changes of the fluid distribution models in the pipeline section are used to identify the flow pattern. Finally, flow simulation experiments using electromagnetic flow image logging are operated and the experimental and simulated data are compared. The results show that the method can be used for flow pattern identification of actual electromagnetic image logging data.

Identification Method of Gas-Liquid Two-phase Flow Regime Based on Image Multi-feature Fusion and Support Vector Machine

The knowledge of flow regime is very important for quantifying the pressure drop, the stability and safety of two-phase flow systems. Based on image multi-feature fusion and support vector machine, a new method to identify flow regime in two-phase flow was presented. Firstly, gas-liquid two-phase flow images including bub- bly flow, plug flow, slug flow, stratified flow, wavy flow, annular flow and mist flow were captured by digital high speed video systems in the horizontal tube. The image moment invariants and gray level co-occurrence matrix texture features were extracted using image processing techniques. To improve the performance of a multiple classifier system, the rough sets theory was used for reducing the inessential factors. Furthermore, the support vector machine was trained by using these eigenvectors to reduce the dimension as flow regime samples, and the flow regime intelligent identification was realized. The test results showed that image features which were reduced with the rough sets theory could excellently reflect the difference between seven typical flow regimes, and successful training the support vector machine could quickly and accurately identify seven typical flow regimes of gas-liquid two-phase flow in the horizontal tube. Image multi-feature fusion method provided a new way to identify the gas-liquid two-phase flow, and achieved higher identification ability than that of single characteristic. The overall identification accuracy was 100%, and an estimate of the image processing time was 8 ms for online flow regime identification.

Fully Convolutional Networks for Street Furniture Identification in Panorama Images

Panoramic images are widely used in many scenes,especially in virtual reality and street view capture.However,they are new for street furniture identification which is usually based on mobile laser scanning point cloud data or conventional 2D images.This study proposes to perform semantic segmentation on panoramic images and transformed images to separate light poles and traffic signs from background implemented by pre-trained Fully Convolutional Networks(FCN).FCN is the most important model for deep learning applied on semantic segmentation for its end to end training process and pixel-wise prediction.In this study,we use FCN-8s model that pre-trained on cityscape dataset and finetune it by our own data.Then replace cross entropy loss function with focal loss function in the FCN model and train it again to produce the predictions.The results show that in all results from pre-trained model,fine-tuning,and FCN model with focal loss,the light poles and traffic signs are detected well and the transformed images have better performance than panoramic images in the prediction according to the Recall and IoU evaluation.

A novel approach for feature extraction from a gamma‑ray energy spectrum based on image descriptor transferring for radionuclide identification

This study proposes a novel feature extraction approach for radionuclide identification to increase the precision of identification of the gamma-ray energy spectrum set.For easier utilization of the information contained in the spectra,the vectors of the gamma-ray energy spectra from Euclidean space,which are fingerprints of the different types of radionuclides,were mapped to matrices in the Banach space.Subsequently,to make the spectra in matrix form easier to apply to image-based deep learning frameworks,the matrices of the gamma-ray energy spectra were mapped to images in the RGB color space.A deep convolutional neural network(DCNN)model was constructed and trained on the ImageNet dataset.The mapped gamma-ray energy spectrum images were applied as inputs to the DCNN model,and the corresponding outputs of the convolution layers and fully connected layers were transferred as descriptors of the images to construct a new classification model for radionuclide identification.The transferred image descriptors consist of global and local features,where the activation vectors of fully connected layers are global features,and activations from convolution layers are local features.A series of comparative experiments between the transferred image descriptors,peak information,features extracted by the histogram of the oriented gradients(HOG),and scale-invariant feature transform(SIFT)using both synthetic and measured data were applied to 11 classical classifiers.The results demonstrate that although the gamma-ray energy spectrum images are completely unfamiliar to the DCNN model and have not been used in the pre-training process,the transferred image descriptors achieved good classification results.The global features have strong semantic information,which achieves an average accuracy of 92.76%and 94.86%on the synthetic dataset and measured dataset,respectively.The results of the statistical comparison of features demonstrate that the proposed approach outperforms the peak-searching-based method,HOG,and SIFT on the synthetic and measured datasets.

A Secure Transfer of Identification Information in Medical Images by Steganocryptography

The fast growth of the exchange traffic in medical imagery on the Internet justifies the creation of adapted tools guaranteeing the quality and the confidentiality of the information while respecting the legal and ethical constraints, specific to this field. The joint usage of steganography and cryptography brings an efficient solution, whose implementation in medical routine is realistic, thanks to the current progress in data processing (broad band Internet access and grid computing).

AGGREGATE IMAGE BASED TEXTURE IDENTIFICATION USING GRAY LEVEL CO-OCCURRENCE PROBABILITY AND BP NEURAL NETWORK

Classifying the texture of granules in 2D images has aroused manifold research atten-tion for its technical challenges in image processing areas.This letter presents an aggregate texture identification approach by jointly using Gray Level Co-occurrence Probability(GLCP) and BP neural network techniques.First, up to 8 GLCP-associated texture feature parameters are defined and computed, and these consequent parameters next serve as the inputs feeding to the BP neural network to calculate the similarity to any of given aggregate texture type.A finite number of aggregate images of 3 kinds, with each containing specific type of mineral particles, are put to the identification test, experimentally proving the feasibility and robustness of the proposed method.

Metaheuristic Based Noise Identification and Image Denoising Using Adaptive Block Selection Based Filtering

Image denoising has become one of the major forms of image enhancement methods that form the basis of image processing. Due to the inconsistencies in the machinery producing these signals, medical images tend to require these techniques. In real time, images do not contain a single noise, and instead they contain multiple types of noise distributions in several indistinct regions. This paper presents an image denoising method that uses Metaheuristics to perform noise identification. Adaptive block selection is used to identify and correct the noise contained in these blocks. Though the system uses a block selection scheme, modifications are performed on pixel- to-pixel basis and not on the entire blocks;hence the image accuracy is preserved. PSO is used to identify the noise distribution, and appropriate noise correction techniques are applied to denoise the images. Experiments were conducted using salt and pepper noise, Gaussian noise and a combination of both the noise in the same image. It was observed that the proposed method performed effectively on noise levels up-to 0.5 and was able to produce results with PSNR values ranging from 20 to 30 in most of the cases. Excellent reduction rates were observed on salt and pepper noise and moderate reduction rates were observed on Gaussian noise. Experimental results show that our proposed system has a wide range of applicability in any domain specific image denoising scenario, such as medical imaging, mammogram etc.

Identification of Microplankton in South China Sea with Image-Matching Individual PCR

In this study, marine microplankton were identified by combining standard light microscopy with Sanger 18S rRNA gene sequencing. The image-matching individual PCR technique was applied to identify the image collectable unicellular microplankton to genera. Instead of pure strain culture and morphological identification, microplankton individual cells were isolated and fixed with glutaraldehyde, frozen and stored for months. Finally, they were imaged under a microscope and molecularly identified via phylogenetic analysis of their 18S ribosomal RNA gene(18S rDNA). Microplankton cells were collected at 30 locations in South China Sea, and were assigned to 21 known and 4 unidentified genera(2 uncultured fungi and 2 uncultured stramenopiles) with phylogenetic analysis in parallel to the morphological identification.

An Insect Imaging System to Automate Rice Light-Trap Pest Identification

Identification and counting of rice light-trap pests are important to monitor rice pest population dynamics and make pest forecast. Identification and counting of rice light-trap pests manually is time-consuming, and leads to fatigue and an increase in the error rate. A rice light-trap insect imaging system is developed to automate rice pest identification. This system can capture the top and bottom images of each insect by two cameras to obtain more image features. A method is proposed for removing the background by color difference of two images with pests and non-pests. 156 features including color, shape and texture features of each pest are extracted into an support vector machine （SVM） classifier with radial basis kernel function. The seven-fold cross-validation is used to improve the accurate rate of pest identification. Four species of Lepidoptera rice pests are tested and achieved 97.5% average accurate rate.

Automatic fracture–vug identification and extraction from electric imaging logging data based on path morphology

We present a path morphology method to separate total rock pore space into matrix, fractures and vugs and derive their pore structure spectrum. Thus, we can achieve fine pore evaluation in fracture–vug reservoirs based on electric imaging logging data. We automatically identify and extract fracture–vug information from the electric imaging images by adopting a path morphological operator that remains flexible enough to fit rectilinear and slightly curved structures because they are independent of the structuring element shape. The Otsu method was used to extract fracture–vug information from the background noise caused by the matrix. To accommodate the differences in scale and form of the different target regions,including fracture and vug path, operators with different lengths were selected for their recognition and extraction at the corresponding scale. Polynomial and elliptic functions are used to fit the extracted fractures and vugs, respectively, and the fracture–vug parameters are deduced from the fitted edge. Finally, test examples of numerical simulation data and several measured well data have been provided for the verification of the effectiveness and adaptability of the path morphology method in the application of electric imaging logging data processing. This also provides algorithm support for the fine evaluation of fracture–vug reservoirs.

Identifying Materials of Photographic Images and Photorealistic Computer Generated Graphics Based on Deep CNNs

Currently,some photorealistic computer graphics are very similar to photographic images.Photorealistic computer generated graphics can be forged as photographic images,causing serious security problems.The aim of this work is to use a deep neural network to detect photographic images(PI)versus computer generated graphics(CG).In existing approaches,image feature classification is computationally intensive and fails to achieve realtime analysis.This paper presents an effective approach to automatically identify PI and CG based on deep convolutional neural networks(DCNNs).Compared with some existing methods,the proposed method achieves real-time forensic tasks by deepening the network structure.Experimental results show that this approach can effectively identify PI and CG with average detection accuracy of 98%.

Application of Multispectral Imaging Method in Rapid Identification and Analysis of Chinese Herbal Medicine Powders

Five kinds of traditional flower Chinese medicine powders (TFCMD) were identified using tuneable liquid spectral imaging instrument, to discuss the application range and advantages of spectral imaging technology in Chinese medicine identification and analysis field. The testing system is the liquid crystal multispectral imaging system designed by ourselves. All the tests are standard samples supplied by National Institute for Drug Control. The spectral cubes of Campsis grandiflora, Carthamus tinctorius, Albizzia julibrissin, Dendranthema morifolium, and Dendranthema indicum were captured, and then the normalized characteristic spectral curves of them were picked up. The spectral resolution is 5 nm, and the spectral range is 400 nm - 650 nm. The result shows that different TFCMD has different normalized characteristic fluorescence spectral curve. Spectral imaging technology can be used to identify TFCMD, and the testing course is convenient, quick, noninvasive and without pre-treatment.

Multispectral Imaging for Authenticity Identification and Quality Evaluation of <i>Flos carthami</i>

The identification and quality evaluation of Flos carthami were studied using tunable liquid spectral imaging instrument, to discuss the application range and advantages of spectral imaging technology in Chinese medicine identification and quality control field. The Flos carthami was indentified by extracting the normalized characteristic spectral curves of Flos carthami, Crocus sativus and Dendranthema morifolium, which were standard samples supplied by National Institute for Drug Control. The qualities of Flos carthamies collecting from different pharmacies were evaluated by extracting their normalized characteristic spectral curves. The imaging spectrum testing system was designed independently. The spectral resolution was 5 nm, and the spectral range was from 400 nm to 680 nm. The results showed that the normalized characteristic spectral curve of Flos carthami was significantly different from those of Crocus sativus’ and Dendranthema morifolium’s, and the fluorescence intensity of Flos carthami from different commercial sources were different. Spectral imaging technology could be used to identify and evaluate Flos carthami, and operation method was rapid, convenient and non-destructive.

Application of Computer Vision Technique to Maize Variety Identification

Variety identification is important for maize breeding, processing and trade. The computer vision technique has been widely applied to maize variety identification. In this paper, computer vision technique has been summarized from the following technical aspects including image acquisition, image processing, characteristic parameter extraction, pattern recognition and programming softwares. In addition, the existing problems during the application of this technique to maize variety identification have also been analyzed and its development tendency is forecasted.