scholarly journals Challenges in Curating 2D Multimedia Data in the Application of Machine Learning in Biodiversity Image Analysis

2021 ◽  
Vol 5 ◽  
Author(s):  
Yasin Bakış ◽  
Xiaojun Wang ◽  
Hank Bart
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Image Analysis ◽  
Image Quality ◽  
Multimedia Data ◽  
Computational Techniques ◽  
Search Results ◽  
Quality Issues

Over 1 billion biodiversity collection specimens ranging from fungi to fish to fossils are housed in more than 1,600 natural history collections across the United States. The digitization of these specimens has risen significantly within the last few decades and this is only likely to increase, as the use of digitized data gains more importance every day. Numerous experiments with automated image analysis have proven the practicality and usefulness of digitized biodiversity images by computational techniques such as neural networks and image processing. However, most of the computational techniques to analyze images of biodiversity collection specimens require a good curation of this data. One of the challenges in curating multimedia data of biodiversity collection specimens is the quality of the multimedia objects—in our case, two dimensional images. To tackle the image quality problem, multimedia needs to be captured in a specific format and presented with appropriate descriptors. In this study we present an analysis of two image repositories each consisting of 2D images of fish specimens from several institutions—the Integrated Digitized Biocollections (iDigBio) and the Great Lakes Invasives Network (GLIN). Approximately 70 thousand images have been processed from the GLIN repository and 450 thousand images have been processed from the iDigBio repository and their suitability assessed for use in neural network-based species identification and trait extraction applications. Our findings showed that images that came from the GLIN dataset were more successful for image processing and machine learning purposes. Almost 40% of the species have been represented with less than 10 images while only 20% have more than 100 images per species. We identified and captured 20 metadata descriptors that define quality and usability of the image. According to the captured metadata information, 70% of the GLIN dataset images were found to be useful for further analysis according to the overall image quality score. Quality issues with the remaining images included: curved specimens, non-fish objects in the images such as tags, labels and rocks that obstructed the view of the specimen; color, focus and brightness issues; folded or overlapping parts as well as missing parts. We used both the web interface and the API (Application Programming Interface) for downloading images from iDigBio. We searched for all fish genera, families and classes in three different searches with the images-only option selected. Then we combined all of the search results and removed duplicates. Our search on the iDigBio database for fish taxa returned approximately 450 thousand records with images. We narrowed this down to 90 thousand fish images aided by the multimedia metadata with the downloaded search results, excluding some non-fish images, fossil samples, X-ray and CT (computed tomography) scans and several others. Only 44% of these 90 thousand images were found to be suitable for further analysis. In this study, we discovered some of the limitations of biodiversity image datasets and built an infrastructure for assessing the quality of biodiversity images for neural network analysis. Our experience with the fish images gathered from two different image repositories has enabled describing image quality metadata features. With the help of these metadata descriptors, one can simply create a dataset for a desired image quality for the purpose of analysis. Likewise, the availability of the metadata descriptors will help advance our understanding of quality issues, while helping data technicians, curators and the other digitization staff be more aware of multimedia.

scholarly journals Analysis of the Nosema Cells Identification for Microscopic Images

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3068
Author(s):  
Soumaya Dghim ◽  
Carlos M. Travieso-González ◽  
Radim Burget
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Image Processing ◽  
Deep Learning ◽  
The Other ◽  
Support Vector ◽  
Learning Approaches ◽  
Microscopic Images ◽  
Trained Neural Network ◽  
Nosema Disease

The use of image processing tools, machine learning, and deep learning approaches has become very useful and robust in recent years. This paper introduces the detection of the Nosema disease, which is considered to be one of the most economically significant diseases today. This work shows a solution for recognizing and identifying Nosema cells between the other existing objects in the microscopic image. Two main strategies are examined. The first strategy uses image processing tools to extract the most valuable information and features from the dataset of microscopic images. Then, machine learning methods are applied, such as a neural network (ANN) and support vector machine (SVM) for detecting and classifying the Nosema disease cells. The second strategy explores deep learning and transfers learning. Several approaches were examined, including a convolutional neural network (CNN) classifier and several methods of transfer learning (AlexNet, VGG-16 and VGG-19), which were fine-tuned and applied to the object sub-images in order to identify the Nosema images from the other object images. The best accuracy was reached by the VGG-16 pre-trained neural network with 96.25%.

scholarly journals Implementasi Metode Super Resolusi Untuk Meningkatkan Kualitas Citra Hasil Screenshot

2020 ◽  
Vol 7 (3) ◽  
pp. 432
Author(s):  
Windi Astuti
Keyword(s):  
Image Processing ◽  
Image Quality ◽  
Median Filter ◽  
Super Resolution ◽  
Linear Interpolation ◽  
Resolution Method ◽  
Image Zooming ◽  
Image Enlargement ◽  
Three Stages

Various types of image processing that can be done by computers, such as improving image quality is one of the fields that is quite popular until now. Improving the quality of an image is necessary so that someone can observe the image clearly and in detail without any disturbance. An image can experience major disturbances or errors in an image such as the image of the screenshot is used as a sample. The results of the image from the screenshot have the smallest sharpness and smoothness of the image, so to get a better image is usually done enlargement of the image. After the screenshot results are obtained then, the next process is cropping the image and the image looks like there are disturbances such as visible blur and cracked. To get an enlarged image (Zooming image) by adding new pixels or points. This is done by the super resolution method, super resolution has three stages of completion, first Registration, Interpolation, and Reconstruction. For magnification done by linear interpolation and reconstruction using a median filter for image refinement. This method is expected to be able to solve the problem of improving image quality in image enlargement applications. This study discusses that the process carried out to implement image enlargement based on the super resolution method is then built by using R2013a matlab as an editor to edit programs

scholarly journals Real-Time Automated Classification of Sky Conditions Using Deep Learning and Edge Computing

2021 ◽  
Vol 13 (19) ◽  
pp. 3859
Author(s):  
Joby M. Prince Czarnecki ◽  
Sathishkumar Samiappan ◽  
Meilun Zhou ◽  
Cary Daniel McCraine ◽  
Louis L. Wasson
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Image Quality ◽  
Convolutional Neural Network ◽  
Precision Agriculture ◽  
Edge Computing ◽  
Training Data ◽  
Learning Approaches ◽  
Sky Conditions

The radiometric quality of remotely sensed imagery is crucial for precision agriculture applications because estimations of plant health rely on the underlying quality. Sky conditions, and specifically shadowing from clouds, are critical determinants in the quality of images that can be obtained from low-altitude sensing platforms. In this work, we first compare common deep learning approaches to classify sky conditions with regard to cloud shadows in agricultural fields using a visible spectrum camera. We then develop an artificial-intelligence-based edge computing system to fully automate the classification process. Training data consisting of 100 oblique angle images of the sky were provided to a convolutional neural network and two deep residual neural networks (ResNet18 and ResNet34) to facilitate learning two classes, namely (1) good image quality expected, and (2) degraded image quality expected. The expectation of quality stemmed from the sky condition (i.e., density, coverage, and thickness of clouds) present at the time of the image capture. These networks were tested using a set of 13,000 images. Our results demonstrated that ResNet18 and ResNet34 classifiers produced better classification accuracy when compared to a convolutional neural network classifier. The best overall accuracy was obtained by ResNet34, which was 92% accurate, with a Kappa statistic of 0.77. These results demonstrate a low-cost solution to quality control for future autonomous farming systems that will operate without human intervention and supervision.

An Image Quality Improvement Method Based on Neural Network for Digital Radiography Security Inspection System

2020 ◽  
Author(s):  
Zhiying Leng ◽  
Zhentao Wang
Keyword(s):  
Neural Network ◽  
Image Quality ◽  
Digital Radiography ◽  
Scanning Speed ◽  
Inspection System ◽  
Image Quality Improvement ◽  
Security Inspection ◽  
High Scanning Speed ◽  
Statistical Noise

Abstract As an essential method for security inspection in nuclear facilities, digital radiography has the ability to find hidden contraband efficiently. However, the images obtained by current scanning digital radiography system can be degraded by several factors, such as statistical noise and response time of detectors. At high scanning speed, the statistical noise and vibration of the system deteriorates the quality of images. In addition, the reduction of image quality will influence the accuracy of image observation and recognition. To meet the demand of detection efficiency and quality, it is necessary to guarantee the quality of images under high scanning speed. Thus, to improve image quality of vehicles’ digital radiography at a certain scanning speed, we proposed an approach (VDR-CNN) to reduce or eliminate image noise, which is a convolutional neural network (CNN) with residual learning. The high-quality images obtained at low scanning speed of system served as the ground-truth image for VDR-CNN, while the low-quality counterpart corresponding to the high scanning speed served as the input. Then, the two images mentioned above constitute a training pair. By training this network with a set of training pairs, the mapping function of promoting image quality will be automatically learned so that the restored image can be obtained from the low-quality counterpart through the trained VDR-CNN. Moreover, this method avoids the difficulty in figuring and analyzing the complicated image degradation model. A series of experiments was carried out through the 60Co inspection system developed by Institute of Nuclear and New Energy Technology, Tsinghua University. The experimental result shows that this method has attained a satisfying result in denoising and preserving details of images and outperforms BM3D algorithm in terms of both image quality improvement and the processing speed. In conclusion, the proposed method improves the image quality of vehicles’ digital radiography and it is proved better than traditional methods.

Recent Advances in Medical Image Processing

2020 ◽  
pp. 1-14
Author(s):  
Zhen Huang ◽  
Qiang Li ◽  
Ju Lu ◽  
Junlin Feng ◽  
Jiajia Hu ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Machine Learning ◽  
Image Processing ◽  
Medical Imaging ◽  
Medical Image ◽  
Medical Image Processing ◽  
Convolution Neural Network ◽  
Artificial Intelligence Technology ◽  
Deep Convolution Neural Network

<b><i>Background:</i></b> Application and development of the artificial intelligence technology have generated a profound impact in the field of medical imaging. It helps medical personnel to make an early and more accurate diagnosis. Recently, the deep convolution neural network is emerging as a principal machine learning method in computer vision and has received significant attention in medical imaging. <b><i>Key Message:</i></b> In this paper, we will review recent advances in artificial intelligence, machine learning, and deep convolution neural network, focusing on their applications in medical image processing. To illustrate with a concrete example, we discuss in detail the architecture of a convolution neural network through visualization to help understand its internal working mechanism. <b><i>Summary:</i></b> This review discusses several open questions, current trends, and critical challenges faced by medical image processing and artificial intelligence technology.

Study on Image Processing of Wheel Valve Hole Based on Machine Vision

2011 ◽  
Vol 63-64 ◽  
pp. 541-546 ◽  
Author(s):  
Chang Chun Li ◽  
Shi Feng Wang ◽  
Jing Yu ◽  
Hua Guan Liu
Keyword(s):  
Image Processing ◽  
Image Quality ◽  
Machine Vision ◽  
Edge Detection ◽  
Basic Principle ◽  
Image Acquisition ◽  
Wheel Speed ◽  
Hole Edge

This paper discusses the basic principle for automatic searching the wheel valve hole based on machine vision. Image acquisition and image processing have been done, and we analyzed the factors that impact the image quality of wheel valve hole. This paper argues that many parameters such as the wheel speed, painting color, the distance between the camera and the valve hole, edge detection operator, and they will affect the quality of the image acquisition and image processing of valve hole.

Compact Disc Visual Inspection Using Neural Network

2012 ◽  
Vol 433-440 ◽  
pp. 727-732
Author(s):  
Anton Satria Prabuwono ◽  
Siti Rahayu Zulkipli ◽  
Doli Anggia Harahap ◽  
Wendi Usino ◽  
A. Hasniaty
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Visual Inspection ◽  
Processing Technique ◽  
Compact Disc ◽  
Image Processing Technique ◽  
Accuracy Rate ◽  
Network Training ◽  
Fields Of Study

Image processing is widely used in various fields of study including manufacturing as product inspection. In compact disc manufacturing, image processing has been implemented to recognize defect products. In this research, we implemented image processing technique as pre-processing processes. The aim is to acquire simple image to be processed and analyzed. In order to express the object from the image, the features were extracted using Invariant Moment (IM). Afterward, neural network was used to train the input from IM’s results. Thus, decision can be made whether the compact disc is accepted or rejected based on the training. Two experiments have been done in this research to evaluate 40 datasets of good and defective images of compact discs. The result shows that accuracy rate increased and can identify the quality of compact discs based on neural network training.

scholarly journals MACHINE LEARNING IMPLEMENTATION FOR THE CLASSIFICATION OF ATTACKS ON WEB SYSTEMS. PART 1

2017 ◽  
Vol 9 (2) ◽  
Author(s):  
K. Smirnova ◽  
A. Smirnov ◽  
O. Olshevska
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Web Application ◽  
Main Idea ◽  
Approximate Model ◽  
Training Sample ◽  
Network Layers ◽  
Entire Network

The possibility of applying machine learning is considered for the classification of malicious requests to a Web application. This approach excludes the use of deterministic analysis systems (for example, expert systems), and based on the application of a cascade of neural networks or perceptrons on an approximate model to the real human brain. The main idea of the work is to enable to describe complex attack vectors consisting of feature sets, abstract terms for compiling a training sample, controlling the quality of recognition and classifying each of the layers (networks) participating in the work, with the ability to adjust not the entire network, But only a small part of it, in the training of which a mistake or inaccuracy crept in.  The design of the developed network can be described as a cascaded, scalable neural network.  The developed system of intrusion detection uses a three-layer neural network. Layers can be built independently of each other by cascades. In the first layer, for each class of attack recognition, there is a corresponding network and correctness is checked on this network. To learn this layer, we have chosen classes of things that can be classified uniquely as yes or no, that is, they are linearly separable. Thus, a layer is obtained not just of neurons, but of their microsets, which can best determine whether is there some data class in the query or not. The following layers are not trained to recognize the attacks themselves, they are trained that a set of attacks creates certain threats. This allows you to more accurately recognize the attacker's attempts to bypass the defense system, as well as classify the target of the attack, and not just its fact. Simple layering allows you to minimize the percentage of false positives.

scholarly journals A Survey of Crowdsourcing in Medical Image Analysis

2020 ◽  
Vol 7 ◽  
pp. 1-26 ◽  
Author(s):  
Silas Nyboe Ørting ◽  
Andrew Doyle ◽  
Arno Van Hilten ◽  
Matthias Hirth ◽  
Oana Inel ◽  
...  
Keyword(s):  
Machine Learning ◽  
Image Processing ◽  
Image Analysis ◽  
Medical Image ◽  
Large Scale ◽  
Medical Image Analysis ◽  
Machine Learning Algorithms ◽  
Imaging Analysis ◽  
High Quality ◽  
Comprehensive Literature Review

Rapid advances in image processing capabilities have been seen across many domains, fostered by the  application of machine learning algorithms to "big-data". However, within the realm of medical image analysis, advances have been curtailed, in part, due to the limited availability of large-scale, well-annotated datasets. One of the main reasons for this is the high cost often associated with producing large amounts of high-quality meta-data. Recently, there has been growing interest in the application of crowdsourcing for this purpose; a technique that has proven effective for creating large-scale datasets across a range of disciplines, from computer vision to astrophysics. Despite the growing popularity of this approach, there has not yet been a comprehensive literature review to provide guidance to researchers considering using crowdsourcing methodologies in their own medical imaging analysis. In this survey, we review studies applying crowdsourcing to the analysis of medical images, published prior to July 2018. We identify common approaches, challenges and considerations, providing guidance of utility to researchers adopting this approach. Finally, we discuss future opportunities for development within this emerging domain.

scholarly journals Digital Image Based Identification of Rice Variety Using Image Processing and Neural Network

2015 ◽  
Vol 16 (1) ◽  
pp. 182
Author(s):  
Lilik Sumaryanti ◽  
Aina Musdholifah ◽  
Sri Hartati
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Classification Accuracy ◽  
Rice Variety ◽  
Texture Features ◽  
Rice Varieties ◽  
Food Grains ◽  
Average Accuracy ◽  
Neural Network Algorithm

The increased of consumer concern on the originality of rice  variety and the quality of rice leads to originality certification of rice by existing institutions. Technology helps human to perform evaluations of food grains using images of objects. This study developed a system used as a tool to identify rice varieties. Identification process was performed by analyzing rice images using image processing. The analyzed features for identification consisted of six color features, four morphological features, and two texture features. Classifier used LVQ neural network algorithm. Identification results using a combination of all features gave average accuracy of 70,3% with the highest classification accuracy level of 96,6% for Mentik Wangi and the lowest classification accuracy of 30%  for Cilosari.

Sign in / Sign up

Export Citation Format

Share Document