Basic Image Manipulation Research Articles

Identification of CNN hyper-parameters for tobacco leaf quality classification on Nvidia Jetson Nano

At the moment, there are some inaccuracies in manual classification for tobacco leaf quality selection, which are influenced by some factors, such as human fatigue or poor lighting. These cases lead to the need for another method that is more consistent, faster and reliable. This research is an implementation of CNN (Convolutional Neural Network) in the classification of fresh tobacco leaves in terms of maturity grades. The primary objective is to develop an efficient CNN model capable to automize the classification of tobacco leaves into three maturity criteria: immature, mature, and old. This methodology consists of some key factors, including color thresholding strategies to purge the noise from the background, Basic Image Manipulation approaches, the systemized screening of different input sizes, and CNN models to enhance the results. The result of this research proves that the developed CNN model has 97.9 % accuracy achieved following 200 training sessions. The model is trained on a dataset comprising 1,249 fresh leaf photos, with a balanced 80:10:10 for train, validation and test ratio. However, the study emphasizes that the CNN model has successfully supported the tobacco leaf discrimination on a Jetson Nano Single-Board Computer with a Graphic Processing Unit (GPU). The study extends beyond the mere theoretical contribution to practical applications in sorting “Gagang Rejeb Sidi” tobacco leaf, the highest quality tobacco variety in South Malang, East Java, Indonesia. Classification using a webcam as an input device shows the fastest processing time of 203.17 ms and the maximum is 1,363 ms. This CNN model algorithm will be applied to a tobacco leaf selector machine, which has a high-speed conveyor and a three-position selector arm. The machine will be operated close to the field in post-harvest time under uniform lighting conditions. Overall, the result of this research is highly relevant in terms of the short duration and accuracy for understanding the commodity classification. It provides a new angle toward speeding up the classification process and improving Indonesian tobacco quality

Plant Disease Detection Using Deep Convolutional Neural Network

In this research, we proposed a novel 14-layered deep convolutional neural network (14-DCNN) to detect plant leaf diseases using leaf images. A new dataset was created using various open datasets. Data augmentation techniques were used to balance the individual class sizes of the dataset. Three image augmentation techniques were used: basic image manipulation (BIM), deep convolutional generative adversarial network (DCGAN) and neural style transfer (NST). The dataset consists of 147,500 images of 58 different healthy and diseased plant leaf classes and one no-leaf class. The proposed DCNN model was trained in the multi-graphics processing units (MGPUs) environment for 1000 epochs. The random search with the coarse-to-fine searching technique was used to select the most suitable hyperparameter values to improve the training performance of the proposed DCNN model. On the 8850 test images, the proposed DCNN model achieved 99.9655% overall classification accuracy, 99.7999% weighted average precision, 99.7966% weighted average recall, and 99.7968% weighted average F1 score. Additionally, the overall performance of the proposed DCNN model was better than the existing transfer learning approaches.

Towards high-performance deep learning models in tool wear classification with generative adversarial networks

Image-based deep learning (DL) applications have been increasingly applied in manufacturing processes in recent years and enable real-time decisions to be derived on the basis of raw image data. However, there are major obstacles that prevent a widespread application. The generation of extensively labeled datasets is associated with costly experiments, long downtimes and demanding measurement setups. Thus, users are usually faced with a trade-off problem, where they have to weigh between the profitability and the performance of their DL algorithms. For this reason, this paper demonstrates how this obstacle can be tackled through the application of data augmentation (DA) techniques. The investigations are based on an image dataset from a tool wear classification task in a blanking process, in which a pre-trained convolutional neural network (CNN) identifies correlations between cutting punch radii and workpiece images. It is shown how synthesized images in combination with transfer learning (TL) models affect classification accuracies using basic image manipulation, different types of generative adversarial networks (GAN) and their hybrid application, varying the number of available images in the training dataset between 160 and 4800. These augmentation techniques lead to accuracy improvements of up to 18%, although their effectiveness depends heavily on the amount of image data available.

A Study on Multiple Factors Affecting the Accuracy of Multiclass Skin Disease Classification

Diagnosis of skin diseases by human experts is a laborious task prone to subjective judgment. Aided by computer technology and machine learning, it is possible to improve the efficiency and robustness of skin disease classification. Deep transfer learning using off-the-shelf deep convolutional neural networks (CNNs) has huge potential in the automation of skin disease classification tasks. However, complicated architectures seem to be too heavy for the classification of only a few skin disease classes. In this paper, in order to study potential ways to improve the classification accuracy of skin diseases, multiple factors are investigated. First, two different off-the-shelf architectures, namely AlexNet and ResNet50, are evaluated. Then, approaches using either transfer learning or trained from scratch are compared. In order to reduce the complexity of the network, the effects of shortening the depths of deep CNNs are investigated. Furthermore, different data augmentation techniques based on basic image manipulation are compared. Finally, the choice of mini-batch size is studied. Experiments were carried out on the HAM10000 skin disease dataset. The results show that the ResNet50-based model is more accurate than the AlexNet-based model. The transferred knowledge from the ImageNet database helps to improve the accuracy of the model. The reduction in stages of the ResNet50-based model can reduce complexity while maintaining good accuracy. Additionally, the use of different types of data augmentation techniques and the choice of mini-batch size can also affect the classification accuracy of skin diseases.

From the air: the photographic record of Florida's lands

Purpose – To describe an LSTA‐funded project that digitized 88,000 black and white aerial photographs and 2,500 photomosaic indexes created for Florida by the US Department of Agriculture between 1938 and 1971. Technical specifications of digital capture, specialized programming, and project value are reviewed. Design/methodology/approach – The 9 × 9 inch aerial tiles were captured on flatbed scanners; the larger photomosaic indexes were captured using a large format camera. Three software tools were designed for the project: the first tracked each tile through the entire in‐house processing including receipt, assignment, scan completion, QC processing, FTPing to server, and archiving of images. The second automated image collection, from disparate scanning stations, performed basic image manipulation for quality control, and stored collected data in a database. The third tool performed routine image corrections, prepared and deployed web format images, and packed archival image formats preparatory to burning CDs. The tile layer of the GIS interface was created by georectifying the composite photomosaic indexes for each Florida county and linking tiles to appropriate points. Findings – Because aerial photographs are inherently spatial, the development team agreed that a GIS interface was the appropriate vehicle for web presentation. While this environment presents no difficulties for more sophisticated users, GIS functionality is not intuitive. A less complex interface is a top priority for future project refinements. Originality/value – The value of this project is documented in terms of site use and solicited user responses.

EDM 1.0: Electron direct methods

A computer program designed to provide a number of quantitative analysis tools for high-resolution imaging and electron diffraction data is described. The program includes basic image manipulation, both real space and reciprocal space image processing, Wiener-filtering, symmetry averaging, methods for quantification of electron diffraction patterns and two-dimensional direct methods. The program consists of a number of sub-programs written in a combination of C++, C and Fortran. It can be downloaded either as GNU source code or as binaries and has been compiled and verified on a wide range of platforms, both Unix based and PC's. Elements of the design philosophy as well as future possible extensions are described.

Radiology on handheld devices: image display, manipulation, and PACS integration issues.

Handheld personal digital assistants (PDAs) have undergone continuous and substantial improvements in hardware and graphics capabilities, making them a compelling platform for novel developments in teleradiology. The latest PDAs have processor speeds of up to 400 MHz and storage capacities of up to 80 Gbytes with memory expansion methods. A Digital Imaging and Communications in Medicine (DICOM)-compliant, vendor-independent handheld image access system was developed in which a PDA server acts as the gateway between a picture archiving and communication system (PACS) and PDAs. The system is compatible with most currently available PDA models. It is capable of both wired and wireless transfer of images and includes custom PDA software and World Wide Web interfaces that implement a variety of basic image manipulation functions. Implementation of this system, which is currently undergoing debugging and beta testing, required optimization of the user interface to efficiently display images on smaller PDA screens. The PDA server manages user work lists and implements compression and security features to accelerate transfer speeds, protect patient information, and regulate access. Although some limitations remain, PDA-based teleradiology has the potential to increase the efficiency of the radiologic work flow, increasing productivity and improving communication with referring physicians and patients.

The art and science of digital compositing

Acknowledgments Preface Chapter 1 Introduction to Digital Compositing Chapter 2 The Digital Representation of Visual Information Chapter 3 Basic Image Manipulation Chapter 4 Basic Image Compositing Chapter 5 Matte Creation and Manipulation Chapter 6 Time and Temporal Manipulations Chapter 7 Image Tracking and Stabilization Chapter 8 Interface Interactions Chapter 9 Image Viewing and Analysis Tools Chapter 10 Formats: Media, Resolution, and Aspect Ratios Chapter 11 Quality and Efficiency Chapter 12 Learning to See Chapter 13 Creating Elements Chapter 14 Integration Techniques Chapter 15 Advanced Topics Chapter 16 Case Studies Appendix A Digital Compositing Software: Tools and Features Appendix B Digital Compositing Software: Manufacturers Appendix C Digital Image File Formats Appendix D Common Film and Video Formats Bibliography Glossary Index

AN INTELLIGENT CAMERA FOR ACTIVE VISION

Much research is currently going on about the processing of one or two-camera imagery, possibly combined with other sensors and actuators, in view of achieving attentive vision, i.e. processing selectively some parts of a scene possibly with another resolution. Attentive vision in turn is an element of active vision where the outcome of the image processing triggers changes in the image acquisition geometry and/or of the environment. Almost all this research is assuming classical imaging, scanning and conversion geometries, such as raster based scanning and processing of several digitized outputs on separate image processing units. A consortium of industrial companies comprising Digital Equipment Europe, Thomson CSF, and a few others, have taken a more radical view of this. To meet active vision requirements in industry, an intelligent camera is being designed and built, comprised of three basic elements: – a unique Thomson CSF CCD sensor architecture with random addressing – the DEC Alpha 21064 275MHz processor chip, sharing the same internal data bus as the digital sensor output – a generic library of basic image manipulation, control and image processing functions, executed right in the sensor-internal bus-processor unit, so that only higher level results or commands get exchanged with the processing environment. Extensions to color imaging (with lower spatial resolution), and to stereo imaging, are relatively straightforward. The basic sensor is 1024*1024 pixels with 2*10 bits addresses, and a 2.5 ms (400 frames/second) image data rate compatible with the Alpha bus and 64 bits addressing. For attentive vision, several connex fields of max 40 000 pixels, min 5*3 pixels, can be read and addressed within each 2.5 ms image frame. There is nondestructive readout, and the image processing addressing over 64 bits shall allow for 8 full pixel readouts in one single word. The main difficulties have been identified as the access and reading delays, the signal levels, and dimensioning of some buffer arrays in the processor. The commercial applications targeted initially will be in industrial inspection, traffic control and document imaging. In all of these fields, selective position dependent processing shall take place, followed by feature dependent processing. Very large savings are expected both in terms of solutions costs to the end users, development time, as well as major performance gains for the ultimate processes. The reader will appreciate that at this stage no further implementation details can be given.