scholarly journals CNN-Based Illumination Estimation with Semantic Information

2020 ◽  
Vol 10 (14) ◽  
pp. 4806 ◽  
Author(s):  
Ho-Hyoung Choi ◽  
Hyun-Soo Kang ◽  
Byoung-Ju Yun
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Semantic Information ◽  
Color Constancy ◽  
Noisy Data ◽  
Image Data ◽  
Input Image ◽  
The Novel ◽  
Image Patches ◽  
Wide Range

For more than a decade, both academia and industry have focused attention on the computer vision and in particular the computational color constancy (CVCC). The CVCC is used as a fundamental preprocessing task in a wide range of computer vision applications. While our human visual system (HVS) has the innate ability to perceive constant surface colors of objects under varying illumination spectra, the computer vision is facing the color constancy challenge in nature. Accordingly, this article proposes novel convolutional neural network (CNN) architecture based on the residual neural network which consists of pre-activation, atrous or dilated convolution and batch normalization. The proposed network can automatically decide what to learn from input image data and how to pool without supervision. When receiving input image data, the proposed network crops each image into image patches prior to training. Once the network begins learning, local semantic information is automatically extracted from the image patches and fed to its novel pooling layer. As a result of the semantic pooling, a weighted map or a mask is generated. Simultaneously, the extracted information is estimated and combined to form global information during training. The use of the novel pooling layer enables the proposed network to distinguish between useful data and noisy data, and thus efficiently remove noisy data during learning and evaluating. The main contribution of the proposed network is taking CVCC to higher accuracy and efficiency by adopting the novel pooling method. The experimental results demonstrate that the proposed network outperforms its conventional counterparts in estimation accuracy.

scholarly journals Investigating Semantic Augmentation in Virtual Environments for Image Segmentation Using Convolutional Neural Networks

2021 ◽  
Vol 7 (8) ◽  
pp. 146
Author(s):  
Joshua Ganter ◽  
Simon Löffler ◽  
Ron Metzger ◽  
Katharina Ußling ◽  
Christoph Müller
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Virtual Environments ◽  
Semantic Information ◽  
Synthetic Data ◽  
Image Data ◽  
Network Models ◽  
Neural Network Models ◽  
Real World Data ◽  
Virtual Domain

Collecting real-world data for the training of neural networks is enormously time- consuming and expensive. As such, the concept of virtualizing the domain and creating synthetic data has been analyzed in many instances. This virtualization offers many possibilities of changing the domain, and with that, enabling the relatively fast creation of data. It also offers the chance to enhance necessary augmentations with additional semantic information when compared with conventional augmentation methods. This raises the question of whether such semantic changes, which can be seen as augmentations of the virtual domain, contribute to better results for neural networks, when trained with data augmented this way. In this paper, a virtual dataset is presented, including semantic augmentations and automatically generated annotations, as well as a comparison between semantic and conventional augmentation for image data. It is determined that the results differ only marginally for neural network models trained with the two augmentation approaches.

scholarly journals Detection of Neurons in the Proteomic and Genomic Image Data

2019 ◽  
Vol 8 (4) ◽  
pp. 11151-11157
Keyword(s):  
Neural Network ◽  
Human Body ◽  
Sensory System ◽  
Image Data ◽  
Input Image ◽  
The Body ◽  
Basic Unit ◽  
Biomedical Data ◽  
Information Flows ◽  
Network Method

Nowadays, the major biomedical data required for diagnosing the disease is neurons in the nerve cell. Just a brief timeframe after the neuron became recognized as the basic unit of the sensory system, the main endeavors were made to appraise the quantity of neurons in various parts of the sensory system. During the previous century, an incredible number of techniques have been utilized in making such gauges. In spite of the fact that the most generally utilized and acknowledged strategy is that of direct including in the magnifying lens, different systems, including photographic, projection, homogenate, programmed, and visual strategies have been planned. And in this project we are taking a brain tissue as an image data and from that image we are finding the number of neurons which are active in state for the first 24 hrs. and again check for 48 hrs. and finally for 72 hrs. so we here find how neurons are responding after giving information to a body and that information flows through nerves of the body and reaches to the neurons present in a human brain and the neurons react to the information and we take the data that how many neurons are responding to the information that is given to a human body. So, by finding the number of neurons responding to the information given to human body we could estimate the neurons which are alive, and which are dead by this we could declare the mental status of a person. So we are finding the number of neurons with the help of neural network method using MATLAB software and we created a page with the help of MATLAB so we can give input image in the page and the code we written will help to check the number of neurons.

Friction Compensation in the Inverted Pendulum Controller by Means of a Neural Network

2020 ◽  
Vol 22 (4) ◽  
pp. 875-884
Author(s):  
Marek Balcerzak
Keyword(s):  
Neural Network ◽  
Inverted Pendulum ◽  
Friction Model ◽  
The Novel ◽  
Practical Procedure ◽  
The Neural Network ◽  
Wide Range ◽  
Novel Method ◽  
Data Acquisition And Processing ◽  
Friction Modelling

AbstractThis paper presents an experimental confirmation of the novel method of friction modelling and compensation. The method has been applied to an inverted pendulum control system. The practical procedure of data acquisition and processing has been described. Training of the neural network friction model has been covered. Application of the obtained model has been presented. The main asset of the presented model is its correctness in a wide range of relative velocities. Moreover, the model is relatively easy to build.

Ship Transportation Forecasting Based on Extension Neural Network

2012 ◽  
Vol 241-244 ◽  
pp. 2055-2058
Author(s):  
Jia Xuan Yang
Keyword(s):  
Neural Network ◽  
Data Mining ◽  
Neural Networks ◽  
Service Systems ◽  
Extension Theory ◽  
Cluster Center ◽  
The Novel ◽  
Adaptive Process ◽  
New Information ◽  
Wide Range

Over the last decade, neural networks have found application for solving a wide range of areas from business, commerce, data mining and service systems. Hence, this paper constructs a new model based extension theory and neural network to forecast the ship transportation. The new neural network is a combination of extension theory and neural network. It uses an extension distance to measure the similarity between data and cluster center, and seek out the useless data, then to use neural network to forecast. When presenting a test example of prediction of ship transportation, the results verifies the effectiveness and applicability of the novel extension neural network. Compared with other forecasting techniques, especially other various neural networks, the extension neural network permits an adaptive process for significant and new information, and gives simpler structure, shorter learning times and higher accuracy.

Research of object recognition using neural network Inception-v3 model operating on Raspberry Pi B3+

2021 ◽  
Vol 15 (1) ◽  
pp. 13-22
Author(s):  
An Toan Nguyen ◽  
◽  
Ngoc Thien Nguyen ◽  
Thanh Truc Nguyen
Keyword(s):  
Neural Network ◽  
Operating System ◽  
Computer Vision ◽  
Image Classification ◽  
Input Image ◽  
Raspberry Pi ◽  
Practical Applications ◽  
The Neural Network ◽  
Audio Channel ◽  
Compact Size

Image Classification is the most important problem in the field of computer vision. It is very simple and has many practical applications, the image classifier is responsible for assigning a label to the input image from a fixed category group. This article has applied image classification to identify objects by giving the image of the object to be identified, then labeling the image and announcing the label name (object name) through the audio channel. The classification is based on the neural network Inception-v3 model that has been trained on Tensorflow and used Raspberian operating system running on the Raspberry Pi 3 B+ to create a device capable of recognizing objects which compact size and convenient to apply in many fields.

scholarly journals Computer vision, machine learning, and the promise of phenomics in ecology and evolutionary biology

2020 ◽  
Author(s):  
Moritz Lürig ◽  
Seth Donoughe ◽  
Erik Svensson ◽  
Arthur Porto ◽  
Masahito Tsuboi
Keyword(s):  
Machine Learning ◽  
Computer Vision ◽  
Image Analysis ◽  
Evolutionary Biology ◽  
Image Data ◽  
Phenotypic Trait ◽  
Biological Phenomena ◽  
Level Data ◽  
Wide Range ◽  
Insight Into

For centuries, ecologists and evolutionary biologists have used images such as drawings, paintings, and photographs to record and quantify the shapes and patterns of life. With the advent of digital imaging, biologists continue to collect image data at an ever-increasing rate. This immense body of data provides insight into a wide range of biological phenomena, including phenotypic trait diversity, population dynamics, mechanisms of divergence and adaptation and evolutionary change. However, the rate of image acquisition frequently outpaces our capacity to manually extract meaningful information from the images. Moreover, manual image analysis is low-throughput, difficult to reproduce, and typically measures only a few traits at a time. This has proven to be an impediment to the growing field of phenomics - the study of many phenotypic dimensions together. Computer vision (CV), the automated extraction and processing of information from digital images, is a way to alleviate this longstanding analytical bottleneck. In this review, we illustrate the capabilities of CV for fast, comprehensive, and reproducible image analysis in ecology and evolution. First, we briefly review phenomics, arguing that ecologists and evolutionary biologists can most effectively capture phenomic-level data by using CV. Next, we describe the primary types of image-based data, and review CV approaches for extracting them (including techniques that entail machine learning and others that do not). We identify common hurdles and pitfalls, and then highlight recent successful implementations of CV in the study of ecology and evolution. Finally, we outline promising future applications for CV in biology. We anticipate that CV will become a basic component of the biologist’s toolkit, further enhancing data quality and quantity, and sparking changes in how empirical ecological and evolutionary research will be conducted.

Comparative Analysis Of Efficient Image Segmentation Technique For Text Recognition And Human Skin Recognition

2021 ◽  
Vol 1 (1) ◽  
pp. 81-90
Author(s):  
Septian Cahyadi ◽  
Febri Damatraseta ◽  
Lodryck Lodefikus S
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Convolutional Neural Network ◽  
Human Skin ◽  
Skin Color ◽  
Color Space ◽  
Text Recognition ◽  
Lighting Conditions ◽  
Wide Range ◽  
Computer Vision Technology

Computer Vision and Pattern Recognition is one of the most interesting research subject on computer science, especially in case of reading or recognition of objects in realtime from the camera device. Object detection has wide range of segments, in this study we will try to find where the better methodologies for detecting a text and human skin. This study aims to develop a computer vision technology that will be used to help people with disabilities, especially illiterate (tuna aksara) and deaf (penyandang tuli) to recognize and learn the letters of the alphabet (A-Z). Based on our research, it is found that the best method and technique used for text recognition is Convolutional Neural Network with achievement accuracy reaches 93%, the next best achievement obtained OCR method, which reached 98% on the reading plate number. And also OCR method are 88% with stable image reading and good lighting conditions as well as the standard font type of a book. Meanwhile, best method and technique to detect human skin is by using Skin Color Segmentation: CIELab color space with accuracy of 96.87%. While the algorithm for classification using Convolutional Neural Network (CNN), the accuracy rate of 98% Key word: Computer Vision, Segmentation, Object Recognition, Text Recognition, Skin Color Detection, Motion Detection, Disability Application

CBIR-CNN: Content Based Image Retrieval on celebrity data using Deep Convolution Neural Network

2020 ◽  
Vol 13 ◽  
Author(s):  
Pushpendra Singh ◽  
P.N. Hrisheekesha ◽  
Vinai Kumar Singh
Keyword(s):  
Neural Network ◽  
Computer Vision ◽  
Deep Learning ◽  
Image Retrieval ◽  
Image Data ◽  
Content Based Image Retrieval ◽  
Facial Image ◽  
Huge Amount ◽  
Proposed Model ◽  
Deep Convolution Neural Network

Background: Finding region of interest in an image and content-based image analysis has been a challenging task for last two decades. With the advancement in image processing, computer vision field and huge amount of image data generation, to manage this huge amount of data Content-Based Image Retrieval System (CBIR) has attracted several researchers as a common technique to manage this huge amount of data. It is an approach of searching user interest, based on visual information present in an image. The requirement of high computation power and huge memory limits deployment of CBIR technique in real-time scenarios. Objective: In this paper an advanced deep learning model is applied for CBIR on facial image data. We design a deep convolution neural network architecture where activation of convolution layer is used for feature representation and include max pooling as feature reduction technique. Furthermore, our model uses partial feature mapping as image descriptor to incorporate the property that facial image contains repeated information. Method: Existing CBIR approaches primarily consider colour, texture and low-level features for mapping and localizing image segments. While deep learning has shown high performance in numerous fields of research, its application in CBIR is still very limited. Human face contains significant information to be used in a content driven task and applicable to various applications of computer vision and multimedia systems. In this research work, a deep learning-based model has been discussed for content-based image retrieval (CBIR). In CBIR, there are two important things 1) classification and 2) retrieval of image based on similarity. For the classification purpose a four-convolution layer model has been proposed. For the calculation of the similarity Euclidian distance measure has been used between the images. Results: Proposed model is completely unsupervised, and it is fast and accurate in comparison to other deep learning models applied for CBIR over facial dataset. The proposed method provided satisfactory results from the experiment. It outperforms other CNN-based models and other unsupervised techniques used for CBIR. The proposed method provided satisfactory results from the experiment and it outperforms other CNN-based models such as VGG16, Inception V3, ResNet50 and MobileNet. Moreover, the performance of proposed model has been compared with pre-trained models in terms of accuracy, storage space and inference time.

scholarly journals RazorNet: Adversarial Training and Noise Training on a Deep Neural Network Fooled by a Shallow Neural Network

2019 ◽  
Vol 3 (3) ◽  
pp. 43 ◽  
Author(s):  
Shayan Taheri ◽  
Milad Salem ◽  
Jiann-Shiun Yuan
Keyword(s):  
Neural Network ◽  
System Performance ◽  
Deep Neural Network ◽  
Noisy Data ◽  
Image Data ◽  
Detection Accuracy ◽  
Biometric Data ◽  
Different Types ◽  
Adversarial Training ◽  
Simulation Results

In this work, we propose ShallowDeepNet, a novel system architecture that includes a shallow and a deep neural network. The shallow neural network has the duty of data preprocessing and generating adversarial samples. The deep neural network has the duty of understanding data and information as well as detecting adversarial samples. The deep neural network gets its weights from transfer learning, adversarial training, and noise training. The system is examined on the biometric (fingerprint and iris) and the pharmaceutical data (pill image). According to the simulation results, the system is capable of improving the detection accuracy of the biometric data from 1.31% to 80.65% when the adversarial data is used and to 93.4% when the adversarial data as well as the noisy data are given to the network. The system performance on the pill image data is increased from 34.55% to 96.03% and then to 98.2%, respectively. Training on different types of noise can benefit us in detecting samples from unknown and unseen adversarial attacks. Meanwhile, the system training on the adversarial data as well as noisy data occurs only once. In fact, retraining the system may improve the performance further. Furthermore, training the system on new types of attacks and noise can help in enhancing the system performance.

Sign in / Sign up

Export Citation Format

Share Document